Browse Topic: Planning / scheduling

Items (1,164)
To ensure that NURBS curve interpolation meets motion constraints during machining while maintaining low velocity fluctuations, this paper proposes a nested look-ahead velocity planning algorithm. Traditional methods require identifying feedrate-sensitive points and segmenting the curve, which may lead to local velocity exceeding the limits and can involve significant computational effort. The proposed method does not require sensitive-point detection and instead constructs the velocity profile in a globally consistent manner. The algorithm combines a backtracking S-curve acceleration/deceleration strategy to ensure compliance with motion constraints with the Gear prediction–correction method for parameter interpolation, achieving low velocity fluctuation. Through nested iterative refinement, the planned feedrate is continuously corrected until all segments satisfy the imposed constraints. Simulation results show that the method effectively prevents local velocity overshoot, significantly reduces velocity fluctuations compared with conventional second-order Taylor expansion methods, and generates feedrate profiles with continuous acceleration that minimize dynamic shocks during motion. Therefore, the proposed approach provides an effective solution for NURBS-based machining, fully meeting motion constraints while maintaining low velocity fluctuation.
Hu, Jinpeng
This work aims to investigate how disturbance-aware, robustness-embedding reference trajectories translate into actual driving performance when executed by professional drivers in a dynamic driving simulator. The study compares three planned reference trajectories against a free-driving baseline (NO-REF) to assess the trade-offs between lap time (LT) performance and steering effort: NOM, the nominal time-optimal trajectory; TLC, a track-limit-robust, time-optimal trajectory obtained by tightening margins to the track edges; and FLC, a friction-limit-robust, time-optimal trajectory obtained by tightening against axle/tire saturation. All reference trajectories share the same minimum LT objective with a small steering-smoothness regularizer, and are evaluated with two professional drivers driving a high-performance car on a virtual track. The reference trajectories stem from a disturbance-aware minimum-LT framework recently proposed by some of the authors, where worst-case disturbance growth is propagated over a finite horizon and used to tighten tire-friction and track-limit constraints, preserving performance while delivering probabilistic safety margins. LT and steering energy (SE) are evaluated as indicators of driving performance and steering effort, respectively, while RMS values of lateral deviation, speed error, and drift angle are used to characterize driving style. The results reveal a Pareto-like trade-off between LT and SE: NOM achieves the shortest LT, but with the highest SE, TLC minimizes SE at the expense of longer LT, while FLC lies near the efficient frontier, markedly reducing SE relative to NOM with only a minor LT increase. Removing reference trajectories (NO-REF) leads to both higher SE and longer LT, confirming that trajectory guidance improves pace and control efficiency. Overall, the findings highlight reference-based and disturbance-aware planning, particularly the FLC variant, as effective tools for training and for achieving fast yet stable trajectories.
Masoni, MatteoPalermo, VincenzoGabiccini, MarcoGulisano, MartinoPreviati, GiorgioGobbi, MassimilianoComolli, FrancescoMastinu, GianpieroGuiggiani, Massimo
Vehicle fleet decarbonization is a key objective for the coming years, with electrification representing the primary pathway to achieving the targets set by the European Union. The share of battery electric trucks in new registrations has been gradually increasing especially in light and medium size trucks. The replacement rate of diesel long-haul trucks with zero emission trucks is still low due to challenges posed by added complexity and limitations of battery charging. Depot overnight charging is not sufficient to cover the energy needs of a truck covering large distances and careful planning of the route using public charging infrastructure is crucial for an optimized route minimizing extra costs and range anxiety. The current work aims to develop a methodology to propose the optimal charging locations for a given route of a battery electric truck based on nearby stations along the route. Our study uses an open-source optimization algorithm for the fixed route vehicle charging problem coupled with a powertrain simulation model that is used to calculate the energy consumption and the electric range of the vehicles. A variety of constraints, such as initial State of Charge, lowest allowed State of Charge threshold, maximum trip duration, distance deviation, have been implemented in different scenarios from real world locations with a goal to investigate the impact of planning constraints and charging infrastructure in the optimal planning of electric truck routing. The results of our analysis indicate that the integration of an accurate energy consumption calculation model to a route and charging optimisation algorithm can be proven beneficial for minimizing the time penalty due to charging.
Perdikopoulos, MichailDoulgeris, StylianosLivitsanos, GeorgiosKazakis, ThomasMellios, GiorgosNtziachristos, Leonidas
In the field of Aerospace, which has a long Life-Cycle process [20-30Years], Component Obsolescence has become a major problem as it prevents Maintenance & sustenance of a product with committed life-cycle period. Obsolescence Management plays a vital role by deriving strategic plans on proactive obsolescence where the system needs to be supported for several decades. This abstract analyzes the obsolescence challenges in the Aviation industry especially in Avionics System impacted by component obsolescence and present the possible proactive obsolescence management in terms of Engineering, Technology, and business/cost elements. The Obsolescence problem cannot be avoided but the impact of obsolescence and mitigate the risk can be minimized by planning and managing response. The obsolescence risk assessment for the Bill Of Materials (BOM) is a paramount activity to manage obsolescence proactively and cost-effectively. Digital Transformation of analyzing the component obsolescence status and integrated with statistical model to predict the End of Life (EOL) of sub-system/System. The EOL predictions would aid Obsolescence management plan, with mitigation strategies including Form-Fit-Function (FFF) replacements, component life extension through refurbishment, Lead-Free Control plan, component counterfeit and collaborative frameworks for modular, open-standard designs. This approach aimed at reducing unplanned costs by up to 40% on DMSMS (Diminishing Manufacturing Sources and Material Shortages) Management Plan, aligning with IEC 62402 (International standard for obsolescence management) and ARINC 662-1 (Guidelines for obsolescence management in commercial aircraft).
Dharmananyala, RohithMunirathnam, KrishnaMarokeyfrancis, JoisyjoseSadashivaiah, NageshKondamari, Harshitha
Aerospace manufacturing operates within an intricate ecosystem where quality, compliance and traceability are critical to success. Conventional digital thread frameworks provide connectivity but remain largely passive, lacking the intelligence to autonomously manage complex non-conformities across the product lifecycle. This paper introduces an Agentic Digital Thread powered by Agentic AI, designed to transform non-conformity management into an adaptive, self-orchestrating system that actively drives decision-making and corrective actions [1, 4]. The proposed architecture employs a Master Agent to coordinate workflows and maintain end-to-end data continuity, while specialized Agents autonomously manage domain-specific tasks. In the pre-manufacturing phase, these agents proactively validate requirements, material conformity and process planning through integration with PLM, MES, ERP, QMS and supplier systems. In the post-manufacturing phase, the framework extends to concession management, enabling structured workflows for identifying, evaluating and approving deviations during inspection or final assembly. By embedding AI-driven anomaly detection, semantic search of historical concessions, and Generative AI-powered report authoring, the system accelerates resolution and predicts concession acceptance with high confidence. Continuous feedback loops between design, production and quality assurance transform the digital thread from a static data conduit into an intelligent ecosystem that ensures compliance, reduces delays and rework, and fosters continuous improvement. This approach delivers a resilient and adaptive aerospace manufacturing process aligned with the demands of next-generation aircraft production [9, 10].
Veluri, SastryGopala Krishnan, Kannan
The safe integration of Unmanned Aerial Vehicles (UAVs) into shared airspace necessitates robust conflict detection and avoid (DAA) methods that scale effectively with multiple dynamic intruders. Geometric methods, such as those in the DO-365 standard, are provably safe for pairwise encounters but become intractable in dense environments. Conversely, applying kinodynamic motion planners designed for static obstacles to dynamic scenarios leads to unstable behavior, characterized by excessive re-planning and oscillatory motion, as they lack a predictive model of intruder trajectories. This paper introduces a closed-loop planning framework based on the Closed-Loop Rapidly-exploring Random Tree* (CL-RRT*) algorithm to prevent Loss of Well-Clear (LoWC) in multi-intruder scenarios. Our approach integrates a closed-loop dynamics model to guarantee dynamically feasible trajectories and incorporates a spatiotemporal planning strategy. A time-to-come metric is propagated from the tree root to all nodes, enabling prediction of the state and time at future trajectory points. Predicted states are continuously evaluated against known intruder trajectories (from ADS-B or perception system) using the formal DO-365 well-clear criteria, checking each point against the Hazard Area Zone (HAZ) via Horizontal Miss Distance (HMD) and Distance-Modification-for-Tau (DMOD) metrics. Simulations demonstrate that the proposed planner successfully generates safe and feasible trajectories that prevent LoWC in complex multi-intruder scenarios.
Dadkhah Tehrani, NavidCarlson, SeanCherepinsky, IgorMooney, David
The rapid expansion of electric aviation and eVTOL operations introduces tightly coupled challenges related to energy‑constrained aircraft design, battery and thermal management, mission planning, and the generation of certification‑relevant evidence. This paper presents an integrated simulation workflow developed by AVL, Unisphere, and blueflite that combines high‑fidelity electric powertrain and battery models with a guidance‑level, digital‑twin‑based 4‑D trajectory simulation driven by historical weather and operational constraints. At each mission time step, the trajectory layer provides time‑resolved environmental and routing conditions, while the system‑level models compute instantaneous power demand, state‑of‑charge evolution, and thermal response, enabling mission feasibility assessment under realistic wind, temperature, and airspace effects. The workflow is calibrated and validated using flight telemetry from blueflite's active eVTOL cargo aircraft development, ensuring alignment between simulation assumptions and real‑world mission execution. The validated framework is subsequently applied to seasonal route studies and large‑scale virtual flight campaigns spanning multiple regions and years, enabling statistically robust assessment of energy margins, thermal behavior, and mission‑duration variability. The results demonstrate how integrated, traceable simulation can bridge conceptual design and real‑world electric flight operations, supporting informed decision‑making by OEMs and operators in aircraft design, validation, and deployment planning.
Schneider, JürgenMcClearen, JamesAnger, Michael
The electrification of drayage fleets offers potential economic and operational benefits, but the financial viability of electrified vehicles remains sensitive to battery cost, energy price, and fleet usage patterns. While total cost of ownership (TCO) is a useful benchmark, fleet operators and investors are equally concerned with investment performance metrics such as payback period (PB) and Internal Rate of Return (IRR), which better reflect financial risks and investment return timelines. This study develops a unified techno-economic framework that jointly evaluates TCO, PB, and IRR to determine when electrified trucks become cost-effective alternatives to diesel trucks. Building on a previously developed cost modeling tool and using real-world telematics data from a Class 8 drayage fleet at the Port of Savannah, the analysis incorporates projected battery cost trajectories, electricity and diesel price trends, vehicle efficiency improvements, and multiple battery capacities. Parameter ranges reflect widely cited projections and observed drayage-duty-cycle variability. A surrogate-modeling method approximates economic performance across thousands of battery cost–electricity price combinations, enabling high-resolution identification of conditions that achieve TCO parity, acceptable PB thresholds, and target IRR levels. Additionally, the study estimates the evolving share of the fleet that can feasibly electrify over time under multiple economic metrics. This integrated framework offers a novel, data-driven approach to inform risk-aware decision-making for fleet electrification and supports investment planning under evolving cost and operational conditions.
Sun, RuixiaoSujan, VivekGoulet, NathanWang, Qixing
Negotiating Keys for applications such as message authentication within a vehicle presents many problems as, in designing the algorithm; the algorithm must be able to be utilized by small, fixed-point processors. In addition, if there is a desire to do this algorithm in the manufacturing environment, there are severe time constraints placed on how long this algorithm can take, as there are strict station time requirements, which are expensive to change, and any time utilized in the plant can negatively affect vehicle throughput. Additionally, negotiating these keys between many ECUs can greatly increase the time required to negotiate a common key using standard multi-party Diffie-Hellman. Timing would also be an issue in the case of using pair-wise Diffie-Hellman for encryption and distribution of keys utilizing a key master. To solve these problems in multi-party key negotiation, we have utilized the Elliptic Curve variation of the Burmester-Desmedt (ECBD) algorithm. ECBD is relatively fast for a large number of ECUs, though the primary benefit of utilizing this algorithm is that calculation times for key negotiation vary only slightly for a wide range of number of participants. This enables the easy planning of negotiation time based on the number of keys the vehicle requires without worrying about the number of ECUs that require each key. This approach also has advantages over key injection and direct key distribution schemes because it does not require a secure environment at any point in the process. Thus, ECBD can be implemented without a secure clean room in either the manufacturing or maintenance environments. This is especially valuable in the maintenance environment, as it enables easy compliance with right to repair laws without endangering vehicle cyber security.
Van Dam, TheoMazzara, Bill
Developing efficient fast-charging infrastructure along highway corridors is critical for reducing range anxiety and promoting long-distance electric travel. However, traditional static location approaches often fail to account for the stochastic interactions between continuous traffic flows and the stochastic variability of remaining driving ranges. To address these methodological gaps, this study develops a demand-driven optimization framework that integrates an improved Genetic Algorithm with the flow-capturing location-allocation model (GA-FCLM). Unlike static facility location approaches, the flow-capturing location-allocation component is specifically selected to maximize the interception of continuous traffic flows under strict range constraints, while the genetic algorithm efficiently navigates the high-dimensional discrete search space of simultaneous siting and sizing decisions. By synthesizing segment-level traffic flows with Monte Carlo simulations of state of charge (SOC) trajectories, the model accurately reconstructs corridor-level charging demand. For the Beijing-Hong Kong-Macao Expressway, the optimization identifies a robust layout with twenty active stations and 204 fast chargers, requiring a capital investment of 32 million Chinese Yuan (CNY). This configuration achieves a 99% aggregate coverage ratio, effectively eliminating long uncovered segments. Sensitivity analysis reveals that while profit increases linearly with pricing, infrastructure capacity exhibits a nonlinear response to rising electric vehicle (EV) penetration, necessitating strategic spatial rebalancing. The proposed GA-FCLM framework thus provides a scalable and methodologically superior tool for balancing investment costs, coverage continuity, and spatial equity on national highway networks.
Guo, HaifengZhang, JingzhongLian, Jintao
Global geopolitical volatility is recognized as a critical threat to the resilience of the electric vehicle battery supply chain. Static, manually updated databases are inadequate for capturing the sector’s rapid dynamics, resulting in significant information gaps for strategic planning. To address this, an Artificial Intelligence-driven methodology is proposed for constructing a comprehensive and dynamic database. An automated pipeline was implemented. First, real-time textual data are collected from curated news and industry sources using specialized web crawlers. Then, the unstructured data obtained undergo preprocessing, including deduplication and cleansing, to ensure quality. A core innovation involves the application of Large Language Models (LLMs) for deep semantic parsing and extraction of structured information. These models are utilized to accurately identify key entities—such as corporations, facilities, and production capacities—and to delineate complex multi-tier relationships spanning from raw material extraction to final distribution. The output is a structured database that provides a data-rich representation of the global supply chain. Experimental results demonstrate that the proposed semantic deduplication framework achieves a recall of 86.3% in identifying duplicate content across multilingual texts, significantly outperforming traditional methods. Through this system, over 200,000 news and industry reports have been successfully processed and structured, encompassing more than 5,000 companies worldwide. This approach highlights the transformative potential of LLMs in industrial intelligence, offering a critical tool for enhancing visibility, fostering resilience, and enabling data-driven decision-making for sustainable mobility amid global disruptions.
Zhu, JuntongLuo, WeiZhang, XiangYang, ZhifengOu, Shiqi(Shawn)He, Xin
Recent geopolitical events in Venezuela, Ukraine and other hot spots are a stark reminder that the long-term planning environment is fraught with challenges and opportunities that suppliers cannot control. The initiation of U.S. tariffs on its trading partners and various embargos also underscored that we have to be flexible in how we dole out capital and the risk we are assuming. The supply base is at the end of that chain. Any issues upstream will reverberate exponentially. It is obvious that the automotive world is re-regionalizing, and quickly. Why the concern? Some context. Until the '70s, every region essentially rowed its own boat. While there were some exports from one major region to another, there were regional OEMs that were sponsored by national governments due to job creation, tax base considerations and bragging rights. The U.S, France, Italy, Germany, Japan, South Korea and a host of others wanted to build national OEMs that could drive scale and become a global force.
Achieving noise reduction in rotorcraft requires an analysis of various design parameters and flight conditions. However, high-fidelity methods are computationally expensive. To overcome this limitation, reduced order model (ROM)-based surrogate models have been applied to aerodynamics and aeroacoustics prediction. This study proposes a ROM-based surrogate model employing a variational autoencoder (VAE) to predict rotor aerodynamic loads and associated noise. Train and test datasets were generated using reformulated vortex particle method across a wide range of flight conditions. The proposed framework was applied to a single rotor, and its performance was evaluated qualitatively and quantitively in comparison with proper orthogonal decomposition (POD)-based surrogate model. The results show that VAE-based model consistently outperformed the POD model in noise prediction. These results demonstrate that the proposed framework enables accurate rotor noise prediction under various flight conditions and provides a promising approach for low-noise rotorcraft design and operational planning.
Jeong, JaeheonCho, Huisang
As electric trucks become more central to modern logistics, the need for smarter, more adaptive route planning is growing rapidly. This paper presents a key navigation feature for analyzing and recalibrating such optimized routes in real time. Integrating map features into the navigation mode improves user experience by offering real-time navigation and dynamic route adjustments based on traffic updates, road closures, vehicle coordinates and deviation in expected energy consumption. This study compares the performance of Server sent events (SSE), web sockets, and Application programming interface (API) polling methodologies, focusing on metrics such as data transmission efficiency, latency, resource utilization, scalability, and reliability. Our results demonstrate the advantages and limitations of each method, providing insights into their suitability for real-time route optimization in electric truck logistics. The results highlight the potential of SSE in achieving efficient and timely data updates, contributing to more effective route planning and resource management. Additionally, we discuss how API Polling, Web sockets, and SSE each make sense in different scenarios when creating a navigation system (drive mode), considering factors such as the frequency of updates, network conditions, and system architecture. This research underscores the importance of choosing the right communication protocol and integrating advanced map features to enhance the performance and reliability of logistics systems.
Bhandari, MehulKaur, PrabhjotDadoo, VishalMahendrakar, ShrinidhiRamanaiah, Rachala
This paper presents a bidirectional digital twin developed for the Fischertechnik Smart Factory Kit, enabling real-time simulation and validation of production line modifications prior to actual deployment. The digital twin integrates with a Siemens Programmable Logic Controller (PLC) to mirror real-world operations, capturing live production data and visualizing key factory parameters, such as product, process, and resource metrics within a 3D environment. Engineers can test various optimization scenarios by adjusting robot speed and path, conveyor speeds, part & process sequences, and modifying equipment layout sizes to enhance efficiency. Based on the optimization scenarios, the best-performing configurations are identified using metrics such as throughput, cycle time, and resource utilization. Once validated, these changes are directly deployed to the PLC, ensuring seamless implementation. Beyond capacity optimization, this solution enhances overall production efficiency by minimizing idle time and parts waiting time, balancing workloads, and reducing unplanned disruptions. Additionally, by virtually simulating product variations and process changes, the digital twin helps identify design simplifications, reduce product complexity, and streamline manufacturing workflows. A digital twin of the manufacturing system serves as an integrated solution, unifying capabilities such as predictive maintenance, efficiency monitoring, simulation, and analytics in real time. By bridging technology gaps and offering a comprehensive view of the entire production process, it enhances decision-making, maximizes resource utilization, and facilitates seamless technology adoption across the factory. This approach significantly reduces downtime, accelerates response times, and boosts automation, demonstrating the transformative potential of digital twins in optimizing manufacturing operations [1].
Kumar, RahulSingh, Randhir
Path planning is a key element of autonomous vehicle navigation, allowing vehicles to calculate feasible paths in challenging environments for applications like automated parking and low speed autonomous driving. Algorithms such as Hybrid A*, Reeds-Shepp, and Dubins paths are widely used and can generate collision-free paths but tend to create curvature discontinuities. These discontinuities result in sudden steering transitions, which create control instabilities, higher mechanical stress, and lower passenger comfort. To overcome these issues, this paper suggests a path-smoothing technique based on the pure-pursuit algorithm to produce smoothed curve paths appropriate for real-world driving. This method utilizes the practical approach of the original path, but removes sudden transitions that destabilize control. By ensuring smooth curvature, the vehicle undergoes fewer jerky steering actions, improved energy efficiency, less actuator wear, and improved high-speed tracking. This paper provides a valuable approach to usual limitations of discrete path planning, on the contribution of control algorithms such as pure pursuit to bridging the gap between planning and execution towards more adaptable autonomous driving particularly automated parking systems.
S, ShriniyathiA, JosanaAnto Edwin J, JoelT, AkshayaaM, Senthil VelKumar, Vimal
The BioMap system represents a groundbreaking approach to collaborative mapping for autonomous vehicles, drawing inspiration from ant colony behavior and swarm intelligence. It implements a fully decentralized protocol where vehicles use virtual pheromone trails to mark areas of uncertainty, change, or importance, enabling efficient map consensus without centralized coordination. Key innovations include novel pheromone-based compression algorithms and bio-inspired consensus mechanisms that allow real-time adaptation to dynamic environments. In a simulated urban scenario (Town10HD), three vehicles achieved balanced load distribution (±1.8% variance) and comprehensive coverage of a 253.2m × 217.9m × 22.4m area. The final fused map contained 311 chunks with 72,785 particles and required only 10.4 MB of storage. Approximately 49.2% of map particles exceeded the pheromone significance threshold, indicating active importance marking, while no high-uncertainty regions remained. These results demonstrate that BioMap enables natural prioritization of critical navigation areas via virtual pheromones, producing high-confidence maps in real time. Overall, the system achieves its objectives of decentralized mapping, efficient communication, and adaptive coverage through bio-inspired mechanisms, marking a significant advance in multi-vehicle SLAM.
Bhargav, Anirudh SSubbarao, Chitrashree
Under the background of advancing the integration of urban and rural road passenger transport and the bus-oriented transformation of scheduled passenger transport, the traditional road passenger transport market has been severely impacted. There is an urgent need to promote the healthy development of chartered passenger transport to meet the public’s demand for high-quality travel. Based on the supply-demand balance theory, a prediction model for chartered passenger transport capacity scale was constructed, and the capacity scale of chartered passenger transport in a typical city was predicted as an example. Finally, countermeasures and suggestions for chartered passenger transport capacity allocation were proposed from five aspects: planning formulation, risk warning, mechanism clarification, performance evaluation, and responsibility implementation.
Zhao, HaibinZhao, XiangyuXing, LiWei, LinghongPeng, XiaoLiao, Kai
In the context of the accelerating urbanization process, the problem of urban traffic congestion has become more severe. Rail transit, with its advantages of high efficiency, convenience, and environmental friendliness, has become a key force in alleviating urban traffic pressure. An in - depth exploration of passengers’ willingness to travel by rail transit is of great significance for optimizing urban traffic planning, improving the service quality of rail transit, and promoting the sustainable development of cities. This article starts from two dimensions: objective factors and passengers’ subjective perceptions, and comprehensively uses a variety of research methods to conduct an in - depth study on passengers’ willingness to travel by rail transit. In terms of objective factors, this article analyzes the differences in subjective perceptions among different passenger groups from the perspectives of gender, age, education level, and occupation. In terms of subjective perceptions, this article deeply analyzes the impact of passengers’ perceptions of the internal value, external value, and comfort of rail transit on their travel willingness.
Wang, GangHuang, LeiYang, Yihao
In the context of mounting urban transportation demands, coupled with the imperatives for energy conservation and carbon reduction, incumbent tram systems confront a range of challenges. This paper proposes a green and low-carbon technological framework for tram, encompassing three phases of planning, design, construction, and operation management. It elucidates the energy-saving and environmental protection technical measures inherent in each phase, accompanied by a thorough analysis of their respective advantages and ramifications. The paper further puts forward suggestions for the green and low-carbon transformation of trams, providing both theoretical guidance and practical reference for the sustainable development of trams.
Luan, Zhi-GangZhou, Hai-ZhuWang, Yuan-QiaoCai, Jing-BiaoZhou, Li-NingZheng, Liang-JiTian, Jiu-Li
Intelligent capacity optimization of highways could realize intelligent enhancement of traffic capacity by optimizing traffic management, improving traffic efficiency and enhancing system synergy without significantly increasing physical lanes. However, there was a lack of a unified and perfect index system to scientifically evaluate the effectiveness of such projects. This paper analyzed the basic theory, evaluation indicator structure and system, and puts forward seven key evaluation dimensions, which including traffic efficiency enhancement, traffic safety improvement, economic and cost-benefit, environmental impacts, technology application and innovation, system reliability and resilience, and service experience. This paper screened the specific evaluation indexes of the seven dimensions and proposes the hierarchical structure of the index system and the weight determination method. This paper constructed a comprehensive, multi-dimensional evaluation index system for highway smart expansion projects, aiming to provide scientific basis and standardized tools for the planning, decision-making, implementation effect assessment and continuous optimization of highway smart expansion projects.
Che, XiaolinLi, WeichenZhu, LiliLi, XinWang, Lin
Cross-line operation is a key direction for the integrated development of multi-level rail transit systems in urban agglomerations. Optimizing train operation under cross-line conditions is essential for improving the overall efficiency and service quality of rail networks. This paper addresses the joint problem of suburban railway cross-line operation and express–local train coordination. This paper develops a train scheduling optimization framework that jointly selects service patterns and departure schedules, with the objective of reducing overall costs, including passenger travel time and operating expenses. To solve the model efficiently, an extended Adaptive Large Neighborhood Search (ALNS) algorithm is developed. The proposed approach provides a practical framework for timetable planning in complex cross-line rail systems and contributes to enhancing integrated transit operations.
Zhu, JingyiGuo, XinPan, Jianju
Accurate forecasting of port container throughput is essential for strategic port planning and infrastructure development. This paper systematically employed the GM (1,1) grey prediction model, quadratic exponential smoothing model and ARIMA model to forecast container throughput at Tianjin Port. Subsequently, a combined model was established through weighted integration of these individual predictors. The results demonstrated that the combined model achieved higher predictive accuracy and lower mean error compared to individual model, thereby providing valuable insights for Tianjin Port’s strategic development planning.
Shi, YujieZhou, Xin
Automatic driving technology can achieve precise control of the vehicle. Compared with manual driving, it can greatly avoid bad driving behaviors such as rapid acceleration, rapid deceleration, and idle driving, more stable, efficient and safer control of vehicles, thus reducing energy consumption and pollution emissions, has great potential for eco-driving. Previous research on eco-driving car-following strategy is usually based on the current vehicle state. However, the real driving scene is extremely complex and changeable, which makes the existing research easy to fall into the dilemma of local optimal solution when dealing with complex long-term planning tasks, and it is difficult to gain comprehensive insight into the path of global optimal solution. According to the literature, bad driving behaviors such as rapid acceleration and rapid deceleration have a great impact on the energy consumption and emissions of vehicles, in order to realize eco-driving, planning control method should be used to explore the range optimal strategy to approach the global optimal. Therefore, this paper discusses an eco-driving car-following strategy for autonomous vehicles based on the acceleration prediction of the leading vehicle, in this study, a Transformer-based acceleration prediction model for the leading vehicle is constructed, which uses the historical state time series data of the leading vehicle to predict its future state, so as to provide the future trajectory change trend of the leading vehicle for the following vehicle, the current state and the predicted state (through the feature fusion module) are used as decision variables for eco-driving, and the decision is adjusted according to the state change trend to achieve smooth driving, the strategy is suitable for the scenario where an autonomous vehicle follows a human-driven vehicle.
Luo, ShijeZhao, Qi
To address the rigid single-route adjustment problem in China's tobacco logistics, this work proposes an Improved NSGA-II and applies it to optimize cigarette distribution routes. First, a bi-objective model is established that comprehensively considers transportation costs and risks. Second, the algorithm is enhanced by introducing a multi-modal initialization strategy and adaptively adjusting crossover and mutation rates based on population entropy. Finally, validation through simulated data demonstrates that the Improved NSGA-II significantly enhances solution quality and diversity compared to traditional NSGA-II, highlighting its critical significance in the planning of cigarette distribution route.
Li, WenyongSun, QiLi, JiaweiLu, RuiLian, Guan
We present a novel processing approach to extract a ship traffic flow framework in order to cope with problems such as large volume, high noise levels and complexity spatio-temporal nature of AIS data. We preprocess AIS data using covariance matrix-based abnormal data filtering, develop improved Douglas-Peucker (DP) algorithm for multi-granularity trajectory compression, identify navigation hotspots and intersections using density-based spatial clustering and visualize chart overlays using Mercator projection. In experiments with AIS data from the Laotieshan waters in the Bohai Bay, we achieve compression rate up to 97% while maintaining a key trajectory feature retention error less than 0.15 nautical miles. We identify critical areas such as waterway intersections and generate traffic flow heatmap for maritime management, route planning, etc.
Kong, XiangyuShao, Guoyu
Aiming at the problem of efficiency loss caused by the independent optimization of traditional vehicle - cargo matching and route planning, this paper proposes a spatio - temporal collaborative optimization model. By constructing three - dimensional decision variables to describe the “vehicle - cargo - route” mapping relationship, a multi - objective mixed - integer programming model considering transportation costs, time - window constraints, and carbon emissions is established. An improved NSGA - II algorithm is designed to solve the Pareto optimal solution set, and the TOPSIS method is combined to achieve scheme optimization. Experiments show that the collaborative optimization model reduces the comprehensive cost by an average of 12.7% and the vehicle empty - running rate by 18.4% compared with the traditional two - stage method.
Yang, MeiruLiu, Jian
With the rapid development of e-commerce, the logistics industry also presents new features such as multi-level, integrated upstream-downstream operations, increasingly perfect service quality and low logistics costs. The exponential growth in online transactions and consumer expectations for faster, more reliable deliveries intensifies the pressure on logistics systems. The last-mile service network refers to the logistics nodes that have direct contact with consumers, and its geographical location and quantity will directly affect the service level, cost and customer service mode of the distribution network. However, with the rapid growth in the number of online shoppers and their imbalance on the Internet, these factors have gradually become an important basis for influencing the layout of terminal outlets. This imbalance, coupled with dynamic urban traffic conditions, renders traditional distribution planning methods inadequate. Therefore, in the e-commerce environment, how to fully explore the new features and effectively optimize the allocation of logistics according to its characteristics is a problem worth studying and urgently needs to be solved. Therefore, this paper investigates the site selection-path optimisation of multilevel logistics and distribution networks in the context of e-commerce. On this basis, an e-commerce distribution route optimisation method based on ant colony algorithm is proposed. The method incorporates enhancements to address the complexities of real-world e-commerce logistics, including dynamic constraints. The experiment proves that the method introduced in this paper can effectively reduce the distribution time, reduce the transport distance, increase the vehicle utilisation rate, improve the customer satisfaction and other issues, and has a good application prospect in enhancing the efficiency and sustainability of modern e-commerce logistics operations.
Tong, TongGu, XuefeiLi, Lingxiao
Accurate traffic flow prediction plays a crucial role in modern transportation management systems, enabling extensive applications ranging from congestion warning to optimized route planning. While current approaches have achieved progress in specific areas, they continue to face challenges such as multi-scale dynamics and constrained spatiotemporal modeling capacity. Addressing these limitations, we introduce a innovative model termed the Spatial-Temporal Fusion Convolution Transformer (STFCT). This framework integrates periodic patterns and traffic characteristics via adaptive spatiotemporal embeddings to produce a unified representation capturing both spatial and temporal relationships. Our architecture incorporates a gating mechanism for dynamic spatiotemporal integration, along with a temporal convolution component to simultaneously capture both short- and medium-term patterns. Experimental results from three different traffic datasets reveal STFCT’s advantages over competing methods in terms of all assessment indicators.
Zhou, JunhaoLiu, TingJiang, Yangwei
This paper introduces a comprehensive solution for predictive maintenance, utilizing statistical data and analytics. The proposed Service Planner feature offers customers real-time insights into the health of machine or vehicle parts and their replacement schedules. By referencing data from service stations and manufacturer advisories, the Service Planner assesses the current health and estimated lifespan of parts based on metrics such as days, engine hours, kilometers, and statistical data. This approach integrates predictive analytics, cost estimation, and service planning to reduce unplanned downtime and improve maintenance budgeting, aligning with SAE expectations for review-ready manuscripts. The user interface displays current part health, replacement due dates, and estimated replacement costs. For example, if air filter replacement is recommended every six months, the solution uses manufacturer advisories to estimate the remaining life of the air filter in terms of days or engine hours. It also suggests replacement dates, suitable part options, replacement costs, and available service slots through an operator guidance mobile app and portal. The solution features a 360-degree view of the machine or vehicle, providing detailed information on each part and allowing operators to interact with and select parts of interest. An integrated cost estimator offers users estimated service costs and availability at authorized service centers, using a centralized part database. This solution empowers customers to monitor machine health, gain a better understanding of their machines, and receive service advisories to prevent breakdowns and downtime. Additionally, the cost estimation feature aids in better planning and budgeting for maintenance.
Chaudhari, Hemant Ashok
Large farms cultivating forage crops for the dairy and livestock sectors require high-quality, dense bales with substantial nutritional value. The storage of hay becomes essential during the colder winter months when grass growth and field conditions are unsuitable for animal grazing. Bale weight serves as a critical parameter for assessing field yields, managing inventory, and facilitating fair trade within the industry. The agricultural sector increasingly demands innovative solutions to enhance efficiency and productivity while minimizing the overhead costs associated with advanced systems. Recent weighing system solutions rely heavily on load cells mounted inside baling machines, adding extra costs, complexity and weight to the equipment. This paper addresses the need to mitigate these issues by implementing an advanced model-based weighing system that operates without the use of load cells, specifically designed for round baler machines. The weighing solution utilizes mathematical models and dynamic torque monitoring techniques to estimate the weight of bales immediately after the bale wrap process, before the bale is dropped onto the field. With the capability to function effectively in off-road conditions and diverse terrains, this system represents a substantial technological advancement that addresses the evolving challenges of modern agriculture. By demonstrating the potential of this design, the paper illustrates how advanced engineering solutions can enhance resource allocation, optimize feed management and distribution, support long-term planning, and contribute to the sustainability of agricultural practices without incurring additional costs. The weight of each bale can be used by farmers to analyze the current harvest based on bale weight variability and to make improvements before the next harvest. It also aids in key decision-making processes such as bale handling, transportation, sales and storage for future seasons. This advancement has significant advantages for scalability and profitability, allowing for optimized decision-making processes in agricultural operations.
Kadam, Pankaj
With the escalating rate of urbanization in China, the urban construction sector is encountering numerous challenges, including issues such as traffic congestion and environmental pollution. To enhance traffic efficiency and offer planning guidance for urban development, this study focuses on the fully or partial opening of community entrances. VISSIM is utilized to examine the community opening and simulate the internal road network, while also employing the SPSS data analysis tool for supplementary analysis. The objective of this method is to compare and analyze the traffic conditions and environmental impact of the community before and after its opening with different automobiles. Through the establishment of a comprehensive evaluation system, the study calculates and analyzes the average vehicle speed, noise levels, energy consumption, and carbon dioxide emissions before and after the opening of the community. Finally, several recommendations are proposed to enhance community engagement in order to effectively address the challenges posed by urbanization.
Li, MengyuanZhuo, ChenxuXiong, SiminXu, Lihao
Cargo Routing Problem or Container Allocation Problem is key decision-making challenge in the maritime industry at operational level. Existing research focus on static environment or planning decisions, ignoring the dynamic arrival property of shipping request in practical world. In this paper, we introduced the Online Cargo Routing problem and formulation the path-based models under a space-time network. We proposed an online algorithm under the online primal-dual scheme: re-solving strategy. We further conducted simulation experiments under different demand distributions to demonstrate the performance of the proposed algorithm over the offline baselines.
Xu, XiaoweiGong, LinXiang, XiLiu, Xin
Accurately predicting passenger flow in urban rail transit is of critical importance for ensuring operational safety, enhancing efficiency, and optimizing costs. To enhance the accuracy of metro passenger flow prediction, this study proposes a passenger flow prediction model based on the Transformer deep learning framework. It is conducted using Automatic Fare Collection (AFC) data from Shanghai Metro Line 5. In addition, clustering algorithms are employed to perform cluster analysis on the stations. Finally, the accuracy and practicality of the Transformer-based model for metro passenger flow prediction are validated through comparative experiments. This model is capable of predicting future passenger flow in rail transit with minute-level precision, thereby assisting subway operators in enhancing train scheduling. It helps in the prevention of resource wastage and facilitates the rational planning of departure frequencies and shifts to accommodate variations in passenger flow during peak and off-peak periods. This ultimately reduces passenger waiting times and improves the overall operational efficiency.
Liu, QichangWan, Heng
The high rate of structural changes to the North American Light Vehicle market demands a new approach by the supply base towards strategic planning. A new Supplier Strategy Playbook is in order. First, some historical perspective. For the last several decades, suppliers grew accustomed to a product cadence of approximately five years between all-new platforms and major revisions. In North America, we were constantly pressed to continue improving vehicle efficiency and reduce emissions. Improved powertrain efficiency, vehicle lightweighting, and the advent of enhanced aerodynamics helped an industry that required constant innovation. Additionally, many programs were global in scope, requiring production and tooling in the major regions to launch in close sequence with global scale in tow. Wash, Rinse, Repeat. The textbook for suppliers was complex, though relatively predictable.
Employment of Robotic and Autonomous Systems requires a different paradigm of mission planning, one which considers not only the tasks to be performed by the RAS themselves but regards the flow of information to support the observability of the RAS by the operator. GTRI has developed an initial capability for mission planning of mixed motive, heterogeneous, autonomous systems for management of macro level metrics that support the decision making of the operator or user during employment. The work is ongoing, extensible to additional capability sets, and modular to support integration of other autonomous capabilities.
Spratley, MichaelSchooley, AndrewDickerhoff, Trey
The early stages of product planning and concepting in advanced engineering domains are often hampered by high uncertainty, fragmented decision-making, and unstructured data. Traditional planning methodologies routinely lead to misalignment, inefficient risk assessments, and suboptimal product strategies. To address these challenges, we propose an AI-agentic decision intelligence (DI) framework that leverages Large Language Models (LLMs) to enhance decision-making in product planning and concept development. The proposed framework uses the transformative natural language processing capabilities and comprehensive knowledge of LLMs to capture and refine stakeholder intent, improve stakeholder engagement, and optimize workflow orchestration. Implementation of the framework is facilitated by state-of-the-art and rapidly evolving open-source tools, ensuring scalability and readiness for corporate environments. By enhancing decision confidence, adaptability, and automation, the framework provides a valuable platform for both defense and commercial product development environments.
Murat, AlperChinnam, Ratna BabuRana, SatyendraRapp, Stephen H.Hansen, KurtRichman, Todd A.Bechtel, James E.
September is unofficially known in the industry as a key forecasting month. It's when several suppliers lock in their revenue forecasts for the next year. As we approach 2026, there are still several balls in the air with respect to the trajectory of the light vehicle market. Looming U.S. tariffs, negative economic and geo-political shifts, and the impact of changes to U.S. vehicle emission legislation have all brought with them a cloud of uncertainty that hovers over the industry. An industry that requires greater planning clarity, not less. Let's start with the tariffs. As of this writing, the major vehicle and parts importers outside of North America have agreed to 15% U.S. tariffs for vehicles and parts. In the case of Japan and the European Union, this is 12.5 percentage points higher than 2024 levels. In the case of South Korea, it's 15 points more, as there was a free trade agreement in force. While these framework agreements drive some level of certainty, the final details still need to be hashed out.
The decoupling of software from hardware in automotive systems, driven by the rising share of software in modern vehicles, has introduced a paradigm shift, enabling various software configurations on identical hardware platforms. Consequently, ensuring the correct functionality and reliability of the electric and electronic hardware components, testing and commissioning processes in the vehicle production have grown in importance and complexity. However, the efficiency of these processes relies on diverse datasets, for example parameterization data that allows tailored testing based on the vehicle’s equipment configuration. Therefore, the availability and accuracy of this data need to be guaranteed. Data for testing and commissioning, influenced by the digitization of production processes and their planning, is not only facing the challenges of greater software volumes and faster update cycles, but also those arising from legacy processes or the integration of various IT systems into production environments. In this context, this research explores methods for evaluating the quality of data that is required for planning as well as executing testing and commissioning processes. Special attention is paid to diagnostic data descriptions, requirement documents for testing and commissioning as well as documentation data of the error elimination process. First, a representative sample of such data is selected and then analyzed in terms of requirements from data consumers. Thereby, criteria for the assessment of data quality are developed aiming to improve process efficiency. The presented set of criteria aims to provide a foundation for original equipment manufacturers (OEMs) to optimize their data management methods. This work offers valuable insights and practical steps towards improving data accessibility and fostering better documentation practices in automotive production.
El Asad, AimanKöhler, KatjaHahn, MichaelReuss, Hans-Christian
The automotive industry faces the challenge of developing vehicles that meet current customer needs while being future-proof. Surveys conducted for this study show that customers are concerned about the financial risks of essential components such as energy storage systems, mainly due to aging and performance degradation, which significantly affect vehicle lifespans. Based on vehicle developer surveys, a clear need for action was identified. Given the rapid technological advancements in electrified drive systems, there is a need for innovative approaches that can easily adapt to changing requirements. Therefore, this paper presents a strategy combining foresight-based planning of system upgrades with product architecture design to create adaptable and sustainable vehicles through modularity. First, dynamic subsystem characteristics are identified to establish future energy storage technology requirements. Subsequently, future energy storage system technologies are examined to determine those that meet the identified dynamic characteristics. Based on this information, the technologies are analyzed technically-functional and geometrically to create flexible design spaces within the product architecture. This enables the future integration of new, more efficient, or higher-performance energy storage technologies into vehicles during their utilization phase. The integrability and functional efficacy of the selected technologies are assessed through a combination of impact and criticality analysis based on virtual modeling, resulting in a ranking of the most suitable energy storage technologies. Implementing upgradable mechatronic systems during the development process already considers future requirements. The result is a product architecture with flexible design spaces and standardized interfaces that facilitate the integration of future performance-adapted technologies. This enhances the sustainability of vehicles, extends their service life, and improves resale value, benefiting both customers and manufacturers.
Fehrenbacher, RüdigerKuebler, MaximilianZeng, YunyingBause, KatharinaAlbers, AlbertNootny, FabioKolbe, LuciaJung, Luca
Trajectory planning is a major challenge in robotics and autonomous vehicles, ensuring both efficient and safe navigation. The primary objective of this work is to generate an optimal trajectory connecting a starting point to a destination while meeting specific requirements, such as minimizing travel distance and adhering to the vehicle’s kinematic and dynamic constraints. The developed algorithms for trajectory design, defined as a sequence of arcs and straight segments, offer a significant advantage due to their low computational complexity, making them well-suited for real-time applications in autonomous navigation. The proposed trajectory model serves as a benchmark for comparing actual vehicle paths in trajectory control studies. Simulation results demonstrate the robustness of the proposed method across various scenarios.
Soundouss, HalimaMsaaf, MohammedBelmajdoub, Fouad
Time-Sensitive Networking (TSN) is an emerging technology that has garnered popularity among the US DoD and others for its deterministic properties while using flexible, ubiquitous Ethernet as its core. However, individual TSN devices will support the TSN features of only some of the vast array of amendments and extensions that make up the full IEEE 802 TSN standards. This functional and modular approach offers great flexibility, but it also increases the complexity of network planning, analysis, verification, etc. as well as potentially leading to unexpected emergent behavior that must be addressed before a TSN network can be truly said to be qualified for use with safety-critical systems. Using industry experience gained certifying other deterministic networks to DO-254 and DO-178C Design Assurance Level A (DAL-A) and applying it to the analysis, testing, and validation of a deterministic TSN Ethernet digital backbone offers a roadmap for overcoming these challenges. Such an approach must seek to satisfy the three basic building-blocks of 1) Device-Level Standards Conformance, 2) System-Level Performance and Interoperability, and 3) Network Composability and Determinism.
Finnegan, DanielZischka, WolframSoares, Alvaro
In single-aisle aircraft, the available storage space for carry-on baggage is inherently limited. When the aircraft is fully booked, it often results in insufficient overhead bin space, necessitating last-minute gate-checking of carry-on items. Such disruptions contribute to delays in the boarding process and reduce operational efficiency. A promising approach to mitigate this issue involves the integration of computer vision technologies with an appropriate data storage system and stochastic simulation to enable accurate and supportive predictions that enhance planning, reduce uncertainty, and improve the overall boarding process. In this work, the YOLOv8 image recognition algorithm is used to identify and classify each passenger’s carry-on baggage into predefined categories, such as handbags, backpacks, and suitcases. This classified data is then linked to passenger information stored in a NoSQL database MongoDB, which includes seat assignments and the number of carry-on items associated with each passenger. Stochastic analysis is applied to predict the occupancy levels of overhead storage bins across different seat rows during the boarding of the passengers. This allows for real-time assessment of whether the remaining storage capacity is sufficient to accommodate additional baggage items. The results of the stochastic analysis reveal potential bottlenecks in baggage storage even before the boarding process is completed. By identifying these critical points in real time, the system can alert gate agents to proactively manage baggage distribution and mitigate overcrowding in aircraft overhead bins. This approach has the potential to streamline the boarding process, thereby reducing aircraft turnaround times and improving overall efficiency within commercial aviation.
Bergmann, JacquelineHub, Maximilian
Industries that require high-accuracy automation in the creation of high-mix/low-volume parts, such as aerospace, often face cost constraints with traditional robotics and machine tools due to the need for many pre-programmed tool paths, dedicated part fixtures, and rigid production flow. This paper presents a new machine learning (ML) based vision mapping and planning technique, created to enhance flexibility and efficiency in robotic operations, while reducing overall costs. The system is capable of mapping discrete process targets in the robot work envelope that the ML algorithms have been trained to identify, without requiring knowledge of the overall assembly. Using a 2D camera, images are taken from multiple robot positions across the work area and are used in the ML algorithm to detect, identify, and predict the 6D pose of each target. The algorithm uses the poses and target identifications to automatically develop a part program with efficient tool paths, including accommodations for the different processes required by each identified target type. For higher-accuracy processes, the initial camera-based location estimates are refined using a 3D structured light scanner. The same sensor can be used to perform post-process inspection, detecting deviations-from-nominal in the scan data to ensure process quality. When implemented on mobile stations with collaborative robots, these techniques enable systems to be transported where they are most needed on the manufacturing floor and to work alongside operators. When used together, these developments give the system significant advantages over traditional methods: increased flexibility in part and robot placement, improved efficiency through reduced setup times, adaptability in the targets being processed, and scalability to accommodate various operations. By eliminating the constraints of rigid pre-programmed setups, this ML-based vision mapping and planning system offers a novel solution that expands robotic capabilities in automated manufacturing.
Langan, DanielHall, MichaelGoldberg, EmilySchrandt, Sasha
Dedicated lanes provide a simpler operating environment for ADS-equipped vehicles than those shared with other roadway users including human drivers, pedestrians, and bicycles. This final report in the Automation and Infrastructure series discusses how and when various types of lanes whether general purpose, managed, or specialty lanes might be temporarily or permanently reserved for ADS-equipped vehicles. Though simulations and economic analysis suggest that widespread use of dedicated lanes will not be warranted until market penetration is much higher, some US states and cities are developing such dedicated lanes now for limited use cases and other countries are planning more extensive deployment of dedicated lanes. Automated Vehicles and Infrastructure: Dedicated Lanes includes a review of practices across the US as well as case studies from the EU and UK, the Near East, Japan, Singapore, and Canada. Click here to access the full SAE EDGETM Research Report portfolio.
Coyner, KelleyBittner, Jason
To ensure the safety and stability of road traffic, autonomous vehicles must proactively avoid collisions with traffic participants when driving on public roads. Collision avoidance refers to the process by which autonomous vehicles detect and avoid static and dynamic obstacles on the road, ensuring safe navigation in complex traffic environments. To achieve effective obstacle avoidance, this paper proposes a CL-infoRRT planning algorithm. CL-infoRRT consists of two parts. The first part is the informed RRT algorithm for structured roads, which is used to plan the reference path for obstacle avoidance. The second part is a closed-loop simulation module that incorporates vehicle kinematics to smooth the planned obstacle avoidance reference path, resulting in an executable obstacle avoidance trajectory. To verify the effectiveness of the proposed method, four static obstacle test scenarios and four RRT comparison algorithms were designed. The implementation results show that all five algorithms can generate obstacle avoidance trajectories in the four scenarios. However, compared with the comparison algorithms, the proposed method uses fewer nodes. In Scenario 1, the proposed method uses 3.82% fewer nodes than RRT-Basic, 0.96% fewer nodes than RRT-Goal, 0.77% fewer nodes than RRT-Star, and 4.77% fewer nodes than RRT-Connect. In Scenario 2, the proposed method uses 3.76% fewer nodes than RRT-Basic, 1.35% fewer nodes than RRT-Goal, 0.12% fewer nodes than RRT-Star, and 13.14% fewer nodes than RRT-Connect. In Scenario 3, the proposed method uses 4.48% fewer nodes than RRT-Basic, 2.01% fewer nodes than RRT-Goal, 0.57% fewer nodes than RRT-Star, and 5.87% fewer nodes than RRT-Connect. In Scenario 4, the proposed method uses 3.59% fewer nodes than RRT-Basic, 1.76% fewer nodes than RRT-Goal, 0.16% fewer nodes than RRT-Star, and 5.77% fewer nodes than RRT-Connect. This indicates that the proposed method can effectively plan optimal and safe obstacle avoidance trajectories.
Wu, WeiLu, JunZeng, DequanYang, JinwenHu, YimingYu, QinWang, Xiaoliang
The slope and curvature of spiral ramps in underground parking garages change continuously, and often lacks of predefined map information. Traditional planning algorithms is difficult to ensure safety and real-time performance for autonomous vehicles entering and exiting underground parking garages. Therefore, this study proposed the Model Predictive Path Integral (MPPI) method, focusing on solving motion planning problems in underground parking garages without predefined map information. This sample-based method to allows simultaneous online autonomous vehicle planning and tracking while not relying on predefined map information,along with adjusting the driving path accordingly. Key path points in the spiral ramp environment were defined by curvature, where reducing the dimensionality of the sampling space and optimizing the computational efficiency of sampled trajectories within the MPPI framework. This ensured the safety and computational speed of the improved MPPI method in motion planning for spiral ramp environments. A co-simulation platform based on Prescan, CarSim, and MATLAB was established for constructing a spiral ramp scenario model with variable slopes and curvatures in an underground garage. Motion planning simulations used the improved MPPI method in this scenario and showed that autonomous vehicles can operate safely and efficiently in the spiral ramp environment.
Liu, ZuyangShen, YanhuaWang, Kaidi
Topology reasoning plays a crucial role in understanding complex driving scenarios and facilitating downstream planning, yet the process of perception is inevitably affected by weather, traffic obstacles and worn lane markings on road surface. Combine pre-produced High-definition maps (HDMaps), and other type of map information to the perception network can effectively enhance perception robustness, but this on-line fused information often requires a real-time connection to website servers. We are exploring the possibility to compress the information of offline maps into a network model and integrate it with the existing perception model. We designed a topology prediction module based on graph attention neural network and an information fusion module based on ensemble learning. The module, which was pre-trained on offline high-precision map data, when used online, inputs the structured road element information output by the existing perception module to output the road topology, and the output road topology is input to the ensemble learner together with the topology output by the existing perception model for information fusion. Our method proposes a paradigm for utilizing offline high-precision map information through offline supervised learning and online ensemble learning. Experimental results show that it achieves varying degrees of algorithm accuracy improvement for multiple topology prediction algorithms on the OpenLane-V2 dataset.
Kuang, QuanyuRui, ZhangZhang, SongYixuan, Gao
Aiming at the problem of insufficient capacity of taxiways in hub airports, which combine the safety interval, conflict resolution and fair principles, a taxiway planning model is established by taking the shortest taxiway as the optimisation goal, considering fuel consumption and exhaust emissions. Dijkstra algorithm is used to transform the taxiing path into an adjacency matrix, and conflict resolution is carried out in a weighted way. Under the premise of ensuring zero conflict of taxiways, the total taxiing distance is reduced. Based on actual operational data from a hub airport in China, the results show that the proposed taxiing path planning method is feasible, shortening the aircraft taxiing distance and improving the surface taxiing efficiency.
Feng, BochengQi, XinyueZhang, Hongbin
The automotive industry is facing unprecedented pressure to reduce costs without compromising on quality and performance, particularly in the design and manufacturing. This paper provides a technical review of the multifaceted challenges involved in achieving cost efficiency while maintaining financial viability, functional integrity, and market competitiveness. Financial viability stands as a primary obstacle in cost reduction projects. The demand for innovative products needs to be balanced with the need for affordable materials while maintaining structural integrity. Suppliers’ cost structures, raw material fluctuations, and production volumes must be considered on the way to obtain optimal costs. Functional aspects lead to another layer of complexity, once changes in design or materials should not compromise safety, durability, or performance. Rigorous testing and simulation tools are indispensable to validate changes in the manufacturing process. Marketing considerations are also significant to the success of cost reduction strategies. Brand reputation and customer perceptions of quality must be safeguarded when changes are implemented. To that end, communication strategies to convey the benefits of cost reduction without compromising perceived value are a key factor to enhance market acceptance. Another crucial element in the execution of cost reduction projects is operational efficiency. Streamlining production processes, optimizing supply chain logistics, and embracing automation technologies require careful planning and implementation to avoid disruptions in production schedules. In conclusion, addressing the challenges of reducing costs in automotive body exterior parts demands a holistic approach that considers financial, functional, and marketing aspects. Striking the right balance between these elements is essential for the success of cost reduction initiatives, ensuring that the automotive industry remains competitive while meeting the demands of a cost-conscious market. A solid technical background for all the parties involved is imperative, and this text provides an overview of the pivotal topics in that context.
Oliveira Neto, Raimundo ArraisSouza, Camila Gomes PeçanhaBrito, Luis Roberto BonfimGuimarães, Georges Louis Nogueira
Items per page:
1 – 50 of 1164