Browse Topic: Automated driving systems

Items (287)
Vehicles equipped with automated driving systems (ADS) may have non-traditional seating configurations, such as rear-facing for front-row occupants. The objectives of this study are (1) to generate biomechanical corridors from kinematic data obtained from postmortem human subjects (PMHS) sled tests and (2) to assess the biofidelity of the Global Human Body Models Consortium (GHBMC) 50th male (M50-O) v6.0 seated in an upright (25-deg recline) Honda Accord seat with a fixed D-ring (FDR) in a 56 km/h rear-facing frontal impact. A phase optimization technique was applied to mass-normalized PMHS data for generating corridors. After replicating the experimental boundary conditions in the computational finite element (FE) environment, the performance of the rigidized FE seat model obtained was validated using LSTC Hybrid III FE model simulations and comparison with experiments. The most recent National Highway Traffic Safety Administration (NHTSA) Biofidelity Ranking System (BRS) method was
Pradhan, VikramRamachandra, RakshitStammen, JasonKracht, CoreyMoorhouse, KevinBolte, John H.Kang, Yun-Seok
To establish and validate new systems incorporated into next generation vehicles, it is important to understand actual scenarios which the autonomous vehicles will likely encounter. Consequently, to do this, it is important to run Field Operational Tests (FOT). FOT is undertaken with many vehicles and large acquisition areas ensuing the capability and suitability of a continuous function, thus guaranteeing the randomization of test conditions. FOT and Use case(a software testing technique designed to ensure that the system under test meets and exceeds the stakeholders' expectations) scenario recordings capture is very expensive, due to the amount of necessary material (vehicles, measurement equipment/objectives, headcount, data storage capacity/complexity, trained drivers/professionals) and all-time robust working vehicle setup is not always available, moreover mileage is directly proportional to time, along with that it cannot be scaled up due to physical limitations. During the early
Sehgal, VishalSekaran, Nikhil
This study presents a comprehensive survey of the current state-of-the-art techniques in virtual scene generation, particularly within the context of autonomous driving. The integration of deep learning methods such as generative adversarial networks (GANs) and convolutional LSTM (ConvLSTM) is explored in detail. Additionally, the effectiveness and applicability of these techniques in simulating real-world traffic scenarios are analyzed. Our article aims to bridge the gap between theoretical models and practical applications, providing an in-depth understanding of how deep learning and virtual scene generation converge to enhance the efficacy of autonomous driving systems
Ayyildiz, Dilara VefaAlnaser, Ala JamilTaj, ShahramZakaria, MahtaJaimes, Luis Gabriel
ABSTRACT Significant Design for Reliability (DfR) methodology challenges are created with the integration of autonomous vehicle technologies via applique systems in a ground military vehicle domain. Voice of the customer data indicates current passenger vehicle usage cycles are typically 5% or less (approximately 72 minutes of use in a twenty-four hour period) [2]. The time during which vehicles currently lay dormant due to drivers being otherwise occupied could change with autonomous vehicles. Within the context of the fully mature autonomous military vehicle environment, the daily vehicle usage rate could grow to 95% or more. Due to this potential increase in the duty or usage cycle of an autonomous military vehicle by an order of magnitude, several issues which impact reliability are worth exploring. Citation: M. Majcher, J. Wasiloff, “New Design for Reliability (DfR) Needs and Strategies for Emerging Autonomous Ground Vehicles”, In Proceedings of the Ground Vehicle Systems
Majcher, MonicaWasiloff, James
ABSTRACT FEV North America will discuss application of advanced automotive cybersecurity to smart vehicle projects, - software safety - software architecture and how it applies to similar features and capabilities across the fleet of DoD combat and tactical vehicles. The analogous system architectures of automotive and military vehicles with advanced architectures, distributed electronic control units, connectivity to networks, user interfaces and maintenance networks and interface points clearly open an opportunity for DoD to leverage the technology techniques, hardware, software, management and human resources to drive implementation costs down while implementing fleet modifications, infrastructure methodology and many of the features of the automotive cyber security spectrum. Two of the primary automotive and DoD subsystems most relevant to Cyber Security threat and protection are the automotive connected vehicles analogous to the DoD Command, Control, Communications, Computers
Chhawri, SumeetTarnutzer, StephanTasky, ThomasLane, Gerald R.
ABSTRACT The IGVC offers a design experience that is at the very cutting edge of engineering education. It is multidisciplinary, theory-based, hands-on, team implemented, outcome assessed, and based on product realization. It encompasses the very latest technologies impacting industrial development and taps subjects of high interest to students. Design and construction of an Intelligent Vehicle fits well in a two semester senior year design capstone course, or an extracurricular activity earning design credit. The deadline of an end-of-term competition is a real-world constraint that includes the excitement of potential winning recognition and financial gain. Students at all levels of undergraduate and graduate education can contribute to the team effort, and those at the lower levels benefit greatly from the experience and mentoring of those at higher levels. Team organization and leadership are practiced, and there are even roles for team members from business and engineering
Kosinski, AndrewTarakhovsky, JaneIyengar, KiranLane, JerryCheok, KaCTheisen, Bernie
ABSTRACT Semi-autonomous vehicles are intended to give drivers multitasking flexibility and to improve driving safety. Yet, drivers have to trust the vehicle’s autonomy to fully leverage the vehicle’s capability. Prior research on driver’s trust in a vehicle’s autonomy has normally assumed that the autonomy was without error. Unfortunately, this may be at times an unrealistic assumption. To address this shortcoming, we seek to examine the impacts of automation errors on the relationship between drivers’ trust in automation and their performance on a non-driving secondary task. More specifically, we plan to investigate false alarms and misses in both low and high risk conditions. To accomplish this, we plan to utilize a 2 (risk conditions) × 4 (alarm conditions) mixed design. The findings of this study are intended to inform Autonomous Driving Systems (ADS) designers by permitting them to appropriately tune the sensitivity of alert systems by understanding the impacts of error type and
Zhao, HuajingAzevedo-Sa, HebertEsterwood, ConnorYang, X. JessieRobert, LionelTilbury, Dawn
ABSTRACT Today we have autonomous vehicles already on select road-ways and regions of this country operating in and around humans and human operated vehicles. The companies developing and testing these systems have experienced varied degrees of success and failure with regard to safe operations within this public space. There have been safety incidents that have made national headlines (when human fatalities have occurred) and their also exist a litany of other physical incidents, usually with human operated systems, that have not grabbed the headlines. Some of the select communities where these autonomous systems have been operationally tested have revoked access to their roadways (kicked out) some of these companies. As a result of these incidents recent data suggests that the public trust in autonomous vehicles is eroding [1]. This situation is couponed by the fact that there are no established safety standards, measures or technological methods to help local, state or national
Frederick, PhilipRose, Mike DelCheok, KaC
ABSTRACT The automotive and defense industries are going through a period of disruption with the advent of Connected and Automated Vehicles (CAV) driven primarily by innovations in affordable sensor technologies, drive-by-wire systems, and Artificial Intelligence-based decision support systems. One of the primary tools in the testing and validation of these systems is a comparison between virtual and physical-based simulations, which provides a low-cost, systems-approach testing of frequently occurring driving scenarios such as vehicle platooning and edge cases and sensor-spoofing in congested areas. Consequently, the project team developed a robotic vehicle platform—Scaled Testbed for Automated and Robotic Systems (STARS)—to be used for accelerated testing elements of Automated Driving Systems (ADS) including data acquisition through sensor-fusion practices typically observed in the field of robotics. This paper will highlight the implementation of STARS as a scaled testbed for rapid
Lodato, DiegoKamalanathsharma, RajFarber, Maurice
ABSTRACT A Model Predictive Control (MPC) LIDAR-based constant speed local obstacle avoidance algorithm has been implemented on rigid terrain and granular terrain in Chrono to examine the robustness of this control method. Provided LIDAR data as well as a target location, a vehicle can route itself around obstacles as it encounters them and arrive at an end goal via an optimal route. Using Chrono, a multibody physics API, this controller has been tested on a complex multibody physics HMMWV model representing the plant in this study. A penalty-based DEM approach is used to model contacts on both rigid ground and granular terrain. We draw conclusions regarding the MPC algorithm performance based on its ability to navigate the Chrono HMMWV on rigid and granular terrain
Haraus, NicholasSerban, RaduFleischmann, Jonathan
ABSTRACT Multiple optimization controls are associated with autonomous vehicles’ movement. These control systems are employed to enhance the comfort of passengers in commercial vehicles or to avoid enemy areas for unmanned military convoys. However, having multiple objectives for optimization can greatly enhance the perception and applicability of these algorithms. This paper involves demonstrating a multi-layered optimization framework which can achieve both and efficiently navigate autonomous vehicles. Other than the primary objective of reducing the probability of intersection crashes, minimizing individual vehicle delay and additionally minimizing energy consumption are the objectives of this example. Primarily this application consists of two parts: a multi-objective optimization framework and individual mathematical models that define vehicle parameters at intersections including vehicle dynamics model and vehicle energy consumption models. Such optimization framework could
Kamalanathsharma, RajZohdy, Ismail
ABSTRACT The IGVC offers a design experience that is at the very cutting edge of engineering education, with a particular focus in developing engineering control/sensor integration experience for the college student participants. A main challenge area for teams is the proper processing of all the vehicle sensor feeds, optimal integration of the sensor feeds into a world map and the vehicle leveraging that world map to plot a safe course using robust control algorithms. This has been an ongoing challenge throughout the 26 year history of the competition and is a challenge shared with the growing autonomous vehicle industry. High consistency, reliability and redundancy of sensor feeds, accurate sensor fusion and fault-tolerant vehicle controls are critical, as even small misinterpretations can cause catastrophic results, as evidenced by the recent serious vehicle crashes experienced by self-driving companies including Tesla and Uber Optimal control techniques & sensor selection
Kosinski, AndrewIyengar, KiranTarakhovsky, JaneLane, JerryCheok, KaCTheisen, BernieOweis, Sami
ABSTRACT Over time, the National Institute of Standards and Technology (NIST) has refined the 4Dimension / Real-time Control System (4D/RCS) architecture for use in Unmanned Ground Vehicles (UGVs). This architecture, when applied to a fully autonomous vehicle designed for missions in urban environments, can greatly assist in the process of saving time and lives by creating a more intelligent vehicle that acts in a safer and more efficient manner. Southwest Research Institute (SwRI®) has undertaken the Southwest Safe Transport Initiative (SSTI) aimed at investigating the development and commercialization of vehicle autonomy as well as vehicle-based telemetry systems to improve active safety systems and autonomy. This paper will discuss the implementation of the 4D/RCS architecture to the SSTI autonomous vehicle, a 2006 Ford Explorer
McWilliams, GeorgeBrown, Michael
ABSTRACT Autonomous driving systems (ADS) in autonomous and semi-autonomous vehicles have the potential to improve driving safety and enable drivers to perform non-driving tasks concurrently. Drivers sometimes fail to fully leverage a vehicle’s autonomy because of a lack of trust. To address this issue, the present study examined the influence of risk on drivers’ trust. Subject tests were conducted to evaluate the effects of combined internal and external risk, where participants drove a simulated semi-autonomous vehicle and completed a secondary task at the same time. Results of this study are expected to provide new insights into promoting trust and acceptance of autonomy in both military and civilian settings
Petersen, LukeZhao, HuajingTilbury, Dawn M.Yang, X. JessieRobert, Lionel P.
ABSTRACT The NAUS ATO (2004-2009) was a follow-on program to the Robotic Follower ATO (2000- 2004) and built on the concept of semi-autonomous leader follower technology to achieve dynamic robotic movement in tactical formations. The NAUS ATO also developed and tested an Unmanned Ground Vehicle (UGV) Self-Security system capable of detecting, tracking, and predicting the intent of human beings in the vicinity of the vehicle. The ATO concluded its Engineering and Evaluation Testing (EET) with a capstone demonstration in October 2008. This paper will detail the technology developed and utilized under the program as well as report on the EET results to the robotic community
Frederick, PhilipKania, RobertBantz, WadeHagner, DonArfa, JoeLacaze, Alberto
ABSTRACT The IGVC offers a design experience that is at the very cutting edge of engineering education, with a particular focus in developing engineering control/sensor integration experience for the college student participants. A main challenge area for teams is the proper processing of all the vehicle sensor feeds, optimal integration of the sensor feeds into a world map and the vehicle leveraging that world map to plot a safe course using robust control algorithms. This has been an ongoing challenge throughout the 27 year history of the competition and is a challenge shared with the growing autonomous vehicle industry. High consistency, reliability and redundancy of sensor feeds, accurate sensor fusion and fault-tolerant vehicle controls are critical, as even small misinterpretations can cause catastrophic results, as evidenced by the recent serious vehicle crashes experienced by self-driving companies including Tesla and Uber Optimal control techniques & sensor selection
Kosinski, AndrewIyengar, KiranTarakhovsky, JaneLane, JerryCheok, KaCTheisen, BernieOweis, Sami
ABSTRACT Accurate models of operator workload in highly automated ground vehicles could inform interface design decisions, predict performance impacts of new systems, and evaluate existing systems. This paper summarizes an existing methodology for modeling human operator workload, demonstrates its application to automated ground vehicles, and discusses its value in development, certification, and acquisition of autonomous military ground systems
Pop, Vlad L.Michelson, W. Stuart
ABSTRACT This paper describes research into the applicability of anomaly detection algorithms using machine learning and time-magnitude thresholding to determine when an autonomous vehicle sensor network has been subjected to a cyber-attack or sensor error. While the research community has been active in autonomous vehicle vulnerability exploitation, there are often no well-established solutions to address these threats. In order to better address the lag, it is necessary to develop generalizable solutions which can be applied broadly across a variety of vehicle sensors. The current measured results achieved for time-magnitude thresholding during this research shows a promising aptitude for anomaly detection on direct sensor data in autonomous vehicle platforms. The results of this research can lead to a solution that fully addresses concerns of cyber-security and information assurance in autonomous vehicles. Citation: R. McBee, J. Wolford, A. Garza, “Detection and Mitigation of
McBee, RyanWolford, JonathanGarza, Abe
ABSTRACT The concept of Autonomous Vehicles ultimately generating an “order of magnitude” potential increase in the duty or usage cycle of a vehicle needs to be addressed in terms of impact on the reliability domain. Voice of the customer data indicates current passenger vehicle usage cycles are typically very low, 5% or less. Meaning, out of a 24 hour day, perhaps the average vehicle is actually driven only 70 minutes or less. Therefore, approximately 95% of the day, the vehicles lay dormant in an unused state. Within the context of future fully mature Autonomous Vehicle environment involving structured car sharing, the daily vehicle usage rate could grow to 95% or more
Wasiloff, James
ABSTRACT Lockheed Martin Missiles and Fire Control has developed a robotic site shuttle for use in structured areas, such as commercial railroad yards, port operations and storage/distribution industries. The purpose of the site shuttle is to provide an autonomous taxi service for personnel needing to move to various locations around the facilities. Many rail yards, ports and storage area are very large, so “taxi” transportation is vital to maintain efficiency and safety. The shuttle vehicles operate in complete autonomy: they have no steering wheel, accelerator or brake pedal. Personnel using the vehicles have only emergency stop buttons in the front and rear of the vehicles. Once implemented, the robotic shuttles will considerably reduce the costs of operation for the company. This need is consistent throughout the rail, port and storage/distribution industries, as all need to move personnel around their yards
Nimblett, DonMills, Myron
ABSTRACT This paper presents a Mobility Virtual Environment (MoVE) for testing multi-vehicle autonomy scenarios with real and simulated vehicles and pedestrians. MoVE is a network-centric framework designed to represent N real and M virtual vehicles interacting and possibly communicating with each other in the same coordinate frame with a common timestamp. The goal is to provide a spectrum of test options from simulation-only to semi-virtual, to all real vehicles and pedestrians. A multi-vehicle test fidelity metric is defined that captures scenario realism more accurately than traditional hardware-in-the-loop style terminology. MoVE’s simple built-in vehicle models are described that provide positions in both latitude and longitude and Cartesian UTM XYZ coordinates. Live GPS inputs from real people or vehicles allow both virtual and real vehicles to interact through the virtual environment. Test results are presented from three experiments with real and virtual vehicles and
Compere, MarcAdkins, KevinLegon, OttoCurrier, Patrick
Object detection is one of the core tasks in autonomous driving perception systems. Most perception algorithms commonly use cameras and LiDAR sensors, but the robustness is insufficient in harsh environments such as heavy rain and fog. Moreover, velocity of objects is crucial for identifying motion states. The next generation of 4D millimeter-wave radar retains traditional radar advantages in robustness and speed measurement, while also providing height information, higher resolution and density. 4D radar has great potential in the field of 3D object detection. However, existing methods overlook the need for specific feature extraction modules for 4D millimeter-wave radar, which can lead to potential information loss. In this study, we propose RadarPillarDet, a novel approach for extracting features from 4D radar to achieve high-quality object detection. Specifically, our method introduces a dual-stream encoder (DSE) module, which combines traditional multilayer perceptron and
Yang, LongZheng, LianqingMo, JingyueBai, JieZhu, XichanMa, Zhixiong
Ongoing research in simulated vehicle crash environments utilizes postmortem human subjects (PMHS) as the closest approximation to live human response. Lumbar spine injuries are common in vehicle crashes, necessitating accurate assessment methods of lumbar loads. This study evaluates the effectiveness of lumbar intervertebral disc (IVD) pressure sensors in detecting various loading conditions on component PMHS lumbar spines, aiming to develop a reliable insertion method and assess sensor performance under different loading scenarios. The pressure sensor insertion method development involved selecting a suitable sensor, using a customized needle-insertion technique, and precisely placing sensors into the center of lumbar IVDs. Computed tomography (CT) scans were utilized to determine insertion depth and location, ensuring minimal tissue disruption during sensor insertion. Tests were conducted on PMHS lumbar spines using a robotic test system for controlled loading in flexion
Burns, Michael R.Caldwell, A. JamesShin, JeesooSochor, Sara H.Kopp, Kevin P.Shaw, GregGepner, BronislawKerrigan, Jason R.
In this article, a novel tuning approach is proposed to obtain the best weights of the discrete-time adaptive nonlinear model predictive controller (AN-MPC) with consideration of improved path-following performance of a vehicle at different speeds in the NATO double lane change (DLC) maneuvers. The proposed approach combines artificial neural network (ANN) and Big Bang–Big Crunch (BB–BC) algorithm in two stages. Initially, ANN is used to tune all AN-MPC weights online. Vehicle speed, lateral position, and yaw angle outputs from many simulations, performed with different AN-MPC weights, are used to train the ANN structure. In addition, set-point signals are used as inputs to the ANN. Later, the BB–BC algorithm is implemented to enhance the path-tracking performance. ANN outputs are selected as the initial center of mass in the first iteration of the BB–BC algorithm. To prevent control signal fluctuations, control and prediction horizons are kept constant during the simulations. The
Yangin, Volkan BekirYalçın, YaprakAkalin, Ozgen
Southwest Research Institute has developed off-road autonomous driving tools with a focus on stealth for the military and agility for space and agriculture clients. The vision-based system pairs stereo cameras with novel algorithms, eliminating the need for LiDAR and active sensors
Controller area network (CAN) buses, the most common intravehicle network (IVN) standard, have been used for over 30 years despite their simple architecture for connecting electronic control units (ECUs). Weight, maintenance costs, mobility promotion, and wired connection complexity increase with ECU count, especially for autonomous vehicles. This paper aims to enhance wired CAN with wireless features for autonomous vehicles (AVs). The proposed solutions include modifying the traditional ECU architecture to become wireless, implementing a hidden communication environment using a unique complementary code keying (CCK) modulation equation and presenting a strategy for dealing with jamming signals using two channels. The proposed wireless CAN (WCAN) is validated using OPNET analysis for performance and reliability. The results show that the bit error rate (BER) and packet loss of the receiver ECU are stable between different CCK modifications, indicating the robustness of the basic
Ibrahim, QutaibaAli, Zeina
The deployment of autonomous urban buses brings with it the hope of addressing concerns associated with safety and aging drivers. However, issues related autonomous vehicle (AV) positioning and interactions with road users pose challenges to realizing these benefits. This report covers unsettled issues and potential solutions related to the operation of autonomous urban buses, including the crucial need for all-weather localization capabilities to ensure reliable navigation in diverse environmental conditions. Additionally, minimizing the gap between AVs and platforms during designated parking requires precise localization. Next-gen Urban Buses: Autonomy and Connectivity addresses the challenge of predicting the intentions of pedestrians, vehicles, and obstacles for appropriate responses, the detection of traffic police gestures to ensure compliance with traffic signals, and the optimization of traffic performance through urban platooning—including the need for advanced communication
Hsu, Tsung-Ming
Model predictive control (MPC) plays a crucial role in advancing intelligent vehicle technologies. Controllers designed based on various vehicle reference models, including kinematic and dynamic models (both linear and nonlinear), often demonstrate significant differences in control performance. This study contributes by comparing three different MPC control methods and proposing a comprehensive evaluation criterion that considers tracking accuracy, stability, and computational efficiency across various MPC designs. Joint simulations using CarSim and MATLAB/Simulink reveal distinct performance characteristics among the MPC variants. Specifically, kinematic MPC (KMPC) exhibits superior performance at low speeds, linear model predictive control (LMPC) performs best at moderate speeds, and nonlinear MPC (NMPC) achieves optimal performance at high speeds. These findings highlight the adaptive nature of MPC strategies to varying vehicle dynamics and operational conditions, emphasizing the
Lai, FeiXiao, HaoLiu, JunboHuang, Chaoqun
ML approaches to solving some of the key perception and decision challenges in automated vehicle functions are maturing at an incredible rate. However, the setbacks experienced during initial attempts at widespread deployment have highlighted the need for a careful consideration of safety during the development and deployment of these functions. To better control the risk associated with this storm of complex functionality, open operating environments, and cutting-edge technology, there is a need for industry consensus on best practices for achieving an acceptable level of safety. Navigating the Evolving Landscape of Safety Standards for Machine Learning-based Road Vehicle Functions provides an overview of standards relevant to the safety of ML-based vehicle functions and serves as guidance for technology providers—including those new to the automotive sector—on how to interpret the evolving standardization landscape. The report also contains practical guidance, along with an example
Burton, Simon
While weaponizing automated vehicles (AVs) seems unlikely, cybersecurity breaches may disrupt automated driving systems’ navigation, operation, and safety—especially with the proliferation of vehicle-to-everything (V2X) technologies. The design, maintenance, and management of digital infrastructure, including cloud computing, V2X, and communications, can make the difference in whether AVs can operate and gain consumer and regulator confidence more broadly. Effective cybersecurity standards, physical and digital security practices, and well-thought-out design can provide a layered approach to avoiding and mitigating cyber breaches for advanced driver assistance systems and AVs alike. Addressing cybersecurity may be key to unlocking benefits in safety, reduced emissions, operations, and navigation that rely on external communication with the vehicle. Automated Vehicles and Infrastructure Enablers: Cybersecurity focuses on considerations regarding cybersecurity and AVs from the
Coyner, KelleyBittner, Jason
With the influx of artificial intelligence (AI) models aiding the development of autonomous driving (AD), it has become increasingly important to analyze and categorize aspects of their operation. In conjunction with the high predictive power innate to AI solutions, due to the safety requirements inherent to automotive systems and the demands for transparency imposed by legislature, there is a natural demand for explainable and predictable models. In this work, we explore the various strategies that reveal the inner workings of these models at various component levels, focusing on those adapted at the modeling stage. Specifically, we highlight and review the use of explainability in state-of-the-art AI-based scenario understanding and motion prediction methods, which represent an integral part of any AD system. We break the discussion down across three key axes that are inherent to any AI solution: the data, the model architecture, and the loss optimization. For each of the axes, we
Okanovic, IlmaStolz, MichaelHillbrand, Bernhard
Vehicle path tracking and stability management are critical technologies for intelligent driving. However, their controls are mutually constrained. This article proposes a cooperative control strategy for intelligent vehicle path tracking and stability, based on the stable domain. First, using the vehicle’s two-degrees-of-freedom (DOF) model and the Dugoff tire model, a phase plane representation is constructed for the vehicle’s sideslip angle and sideslip angular velocity. An enhanced method utilizing five eigenvalues is employed to partition the vehicle stability domain. Second, by employing the divided vehicle stable domain, the design of a fuzzy controller utilizes the Takagi–Sugeno (TS) methodology to determine the weight matrix gain for path tracking and stability control. Subsequently, a fuzzy model predictive control (TS-MPC) cooperative control strategy is designed, which takes into account both the precision of path tracking and the stability of the vehicle. Finally, a
Jiang, ShuhuaiWu, GuangqiangLi, YihangMao, LiboZhang, Dong
Simulation company rFpro has already mapped over 180 digital locations around the world, including public roads, proving grounds and race circuits. But the company's latest is by far its biggest and most complicated. Matt Daley, technical director at rFpro, announced at AutoSens USA 2024 that its new Los Angeles route is an “absolutely massive, complicated model” of a 36-km (22-mile) loop that can be virtually driven in both directions. Along these digital roads - which were built off survey-grade LIDAR data with a 1 cm by 1 cm (1.1-in by 1.1 in) X-Y grid - rFpro has added over 12,000 buildings, 13,000 pieces of street infrastructure (like signs and lamps), and 40,000 pieces of vegetation. “It's a fantastic location,” Daley said. “It's a huge array of different types of challenging infrastructure for AVs. You can drive this loop with full vehicle dynamic inputs, ready to excite the suspension and, especially with AVs, shake the sensors in the correct way as you would be getting if you
Blanco, Sebastian
The traditional approach to applying safety limits in electromechanical systems across various industries, including automated vehicles, robotics, and aerospace, involves hard-coding control and safety limits into production firmware, which remains fixed throughout the product life cycle. However, with the evolving needs of automated systems such as automated vehicles and robots, this approach falls short in addressing all use cases and scenarios to ensure safe operation. Particularly for data-driven machine learning applications that continuously evolve, there is a need for a more flexible and adaptable safety limits application strategy based on different operational design domains (ODDs) and scenarios. The ITSC conference paper [1] introduced the dynamic control limits application (DCLA) strategy, supporting the flexible application of diverse limits profiles based on dynamic scenario parameters across different layers of the Autonomy software stack. This article extends the DCLA
Garikapati, DivyaLiu, YitingHuo, Zhaoyuan
The rise of AI models across diverse domains includes promising advancements, but also poses critical challenges. In particular, establishing trust in AI-based systems for mission-critical applications is challenging for most domains. For the automotive domain, embedded systems are operating in real-time and undertaking mission-critical tasks. Ensuring dependability attributes, especially safety, of these systems remains a predominant challenge. This article focuses on the application of AI-based systems in safety-critical contexts within automotive domains. Drawing from current standardization methodologies and established patterns for safe application, this work offers a reflective analysis, emphasizing overlaps and potential avenues to put AI-based systems into practice within the automotive landscape. The core focus lies in incorporating pattern concepts, fostering the safe integration of AI in automotive systems, with requirements described in standardization and topics discussed
Blazevic, RomanaVeledar, OmarStolz, MichaelMacher, Georg
Verification and validation (V&V) is the cornerstone of safety in the automotive industry. The V&V process ensures that every component in a vehicle functions according to its specifications. Automated driving functionality poses considerable challenges to the V&V process, especially when data-driven AI components are present in the system. The aim of this work is to outline a methodology for V&V of AI-based systems. The backbone of this methodology is bridging the semantic gap between the symbolic level at which the operational design domain and requirements are typically specified, and the sub-symbolic, statistical level at which data-driven AI components function. This is accomplished by combining a probabilistic model of the operational design domain and an FMEA of AI with a fitness-for-purpose model of the system itself. The fitness-for-purpose model allows for reasoning about the behavior of the system in its environment, which we argue is essential to determine whether the
Paardekooper, Jan-PieterBorth, Michael
Driving safety in the mixed traffic state of autonomous vehicles and conventional vehicles has always been an important research topic, especially on highways where autonomous driving technology is being more widely adopted. The merging scenario at highway ramps poses high risks with frequent vehicle conflicts, often stemming from misperceived intentions [1]. This study focuses on autonomous and conventional vehicles in merging scenarios, where timely recognition of lane-changing intentions can enhance merging efficiency and reduce accidents. First, trajectory data of merging vehicles and their conflicting vehicles were extracted from the NGSIM open-source database in the I-80 section. The segmented cubic polynomial interpolation method and Savitzky–Golay filtering are utilized for data outlier removal and noise reduction. Second, the processed trajectory data were used as input to a hybrid Gaussian hidden Markov (GMM-HMM) model for driving intention classification, specifically lane
Ren, YouWang, XiyaoSong, JiaqiLu, WenyangLi, PenglongLi, Shangke
Understanding driving scenes and communicating automated vehicle decisions are key requirements for trustworthy automated driving. In this article, we introduce the qualitative explainable graph (QXG), which is a unified symbolic and qualitative representation for scene understanding in urban mobility. The QXG enables interpreting an automated vehicle’s environment using sensor data and machine learning models. It utilizes spatiotemporal graphs and qualitative constraints to extract scene semantics from raw sensor inputs, such as LiDAR and camera data, offering an interpretable scene model. A QXG can be incrementally constructed in real-time, making it a versatile tool for in-vehicle explanations across various sensor types. Our research showcases the potential of QXG, particularly in the context of automated driving, where it can rationalize decisions by linking the graph with observed actions. These explanations can serve diverse purposes, from informing passengers and alerting
Belmecheri, NassimGotlieb, ArnaudLazaar, NadjibSpieker, Helge
An essential component in the approval of advanced driver assistance systems (ADAS) and automated driving systems (ADS) is the quantification of residual risk, which demonstrates that hazardous behavior (HB) occurs less frequently than specified by a corresponding acceptance criterion. In the case of HB with high potential impact severity, only very low accepted frequencies of occurrence are tolerated. To avoid uncertainties due to abstractions and simplifications in simulations, the proof of the residual risk in systems such as advanced emergency braking systems (AEBS) is often partially or entirely implemented as system level field test. However, the low rates and high confidence required, common for residual risk demonstrations, result in a significant disadvantage of these field tests: the long driving distance required. In this publication, the prediction divergence principle (PDP) is presented as an approach that has the potential to reduce the testing effort in the future
Betschinske, DanielSchrimpf, MalteLippert, MoritzPeters, Steven
To shape future mobility MAHLE has committed itself to foster wireless charging for electrical vehicles. The standardized wireless power transfer of 11 kW at a voltage level of 800 V significantly improves the end user experience for charging an electric vehicle without the need to handle a connector and cable anymore. Combined with automated parking and autonomous driving systems, the challenge to charge fleets without user interaction is solved. Wireless charging is based on inductive power transfer. In the ground assembly’s (GA) power transfer coil, a magnetic field is generated which induces a voltage in the vehicle assembly (VA) power transfer coil. To transfer the power from grid to battery with a high efficiency up to 92% the power transfer coils are compensated with resonant circuits. In this paper the Differential-Inductive-Positioning-System (DIPS) to align a vehicle on the GA for parking will be presented. This system utilizes five standardized magnetic fields which are
Boettigheimer, MikeGrabherr, Philip
Typically, machine learning techniques are used to realise autonomous driving. Be it as part of environment recognition or ultimately when making driving decisions. Machine learning generally involves the use of stochastic methods to provide statistical inference. Failures and wrong decisions are unavoidable due to the statistical nature of machine learning and are often directly related to root causes that cannot be easily eliminated. The quality of these systems is normally indicated by statistical indicators such as accuracy and precision. Providing evidence that accuracy and precision of these systems are sufficient to guarantee a safe operation is key for the acceptance of autonomous driving. Usually, tests and simulations are extensively used to provide this kind of evidence. However, the basis of all descriptive statistics is a random selection from a probability space. A major challenge in testing or constructing the training and test data set is that this probability space is
Wiesbrock, Hans WernerGrossmann, Jürgen
In the evolving landscape of automated driving systems, the critical role of vehicle localization within the autonomous driving stack is increasingly evident. Traditional reliance on Global Navigation Satellite Systems (GNSS) proves to be inadequate, especially in urban areas where signal obstruction and multipath effects degrade accuracy. Addressing this challenge, this paper details the enhancement of a localization system for autonomous public transport vehicles, focusing on mitigating GNSS errors through the integration of a LiDAR sensor. The approach involves creating a 3D map using the factor graph-based LIO-SAM algorithm, which is further enhanced through the integration of wheel encoder and altitude data. Based on the generated map a LiDAR localization algorithm is used to determine the pose of the vehicle. The FAST-LIO based localization algorithm is enhanced by integrating relative LiDAR Odometry estimates and by using a simple yet effective delay compensation method to
Kramer, MarkusBeierlein, Georg
The conventional process of last-mile delivery logistics often leads to safety problems for road users and a high level of environmental pollution. Delivery drivers must deal with frequent stops, search for a convenient parking spot and sometimes navigate through the narrow streets causing traffic congestion and possibly safety issues for the ego vehicle as well as for other traffic participants. This process is not only time consuming but also environmentally impactful, especially in low-emission zones where prolonged vehicle idling can lead to air pollution and to high operational costs. To overcome these challenges, a reliable system is required that not only ensures the flexible, safe and smooth delivery of goods but also cuts the costs and meets the delivery target. In the dynamic landscape of last-mile delivery, LogiSmile, an EU project, introduced a solution to urban delivery challenges through an innovative cooperation between an Autonomous Hub Vehicle (AHV) and an Autonomous
Aslam, IqraAniculaesei, AdinaBuragohain, AbhishekZhang, MengBamal, DanielRausch, Andreas
Deep learning algorithms are being widely used in autonomous driving (AD) and advanced driver assistance systems (ADAS) due to their impressive capabilities in visual perception of the environment of a car. However, the reliability of these algorithms is known to be challenging due to their data-driven and black-box nature. This holds especially true when it comes to accurate and reliable perception of objects in edge case scenarios. So far, the focus has been on normal driving situations and there is little research on evaluating these systems in a safety-critical context like pre-crash scenarios. This article describes a project that addresses this problem and provides a publicly available dataset along with key performance indicators (KPIs) for evaluating visual perception systems under pre-crash conditions
Bakker, Jörg
What are the differences between the traditional automotive companies and “new mobility” players—and even more importantly, who will win? Those are the questions that this report discusses, taking a particular focus on engineering aspects in the automotive/mobility sector and addressing issues regarding innovation, business, market, and regulation Two Approaches to Mobility Engineering was developed with input from nearly 20 industry experts from new and established companies to gain an overview of the intricacies of newcomers and incumbents, to see where the industry stands, and to provide an outlook on where the sector is headed. It provides recommendations as to what respective players should do to master their future and stay at the forefront of mobility innovation. Click here to access the full SAE EDGETM Research Report portfolio
Beiker, Sven
To enhance the interpretability and coverage of high-risk scenarios in virtual test scenarios for autonomous vehicles, we propose a method for generating virtual test scenarios based on the VI-GAN (vehicle-interactive GAN) game neural network. This method constructs a converging interaction game model by capturing the interaction characteristics of vehicles converging on the ramp and those driving in the main lane. The Nash equilibrium solution of the game strategy and the convergence data are used to obtain the vehicle priority probability, and the game model is embedded in the S-GAN neural network model to propose a game trajectory generation model with the characteristics of a realistic interactive gaming behavior. Meanwhile, in order to obtain high-risk convergence scenarios, CT model is introduced to test the combination of real trajectories of interacting vehicles in the observed area and used in VI-GAN algorithm to generate more high-risk interaction trajectories with realistic
Wang, Jingjing
Eastman, BrittanyDukarski, Jennifer
Artificial intelligence (AI)-based solutions are slowly making their way into mobile devices and other parts of our lives on a daily basis. By integrating AI into vehicles, many manufacturers are looking forward to developing autonomous cars. However, as of today, no existing autonomous vehicles (AVs) that are consumer ready have reached SAE Level 5 automation. To develop a consumer-ready AV, numerous problems need to be addressed. In this chapter we present a few of these unaddressed issues related to human-machine interaction design. They include interface implementation, speech interaction, emotion regulation, emotion detection, and driver trust. For each of these aspects, we present the subject in detail—including the area’s current state of research and development, its current challenges, and proposed solutions worth exploring
Fang, ChenRazdan, rahulBeiker, SvenTaleb-Bendiab, Amine
Items per page:
1 – 50 of 287