Browse Topic: Navigation and guidance systems

Items (1,125)
Technological innovations in military vehicles are essential for enhancing efficiency, safety, and operational capability in complex scenarios. Advances such as navigation system automation and the introduction of autonomous vehicles have transformed military mobility. State estimators enable the precise monitoring of critical variables that are not directly accessible by sensors, providing real-time information to controllers and improving dynamic response under variable conditions. Their integration is crucial for the development of advanced control systems. This study aims to develop and compare parameter and states estimators for military heavy vehicles using three methodologies: particle filter, extended Kalman filter, and moving horizon state estimation. Computational simulations employ Pacejka’s magic formula to model tire behavior, and the vehicle modeling is based on a simplified quarter-car model, with an emphasis on longitudinal dynamics. In the end, the estimators are
Barros, Leandro SilvaSousa, Daniel Henrique BrazRodrigues, Gustavo SimãoLopes, Elias Dias Rossi
Intelligent ships represent a crucial trend in the development of the maritime industry and will become the predominant vessel form in the future. Intelligent ships must have efficient perception and situational analysis capabilities in complex navigation environments to achieve intelligent decision-making and safe navigation. Maritime traffic safety is a critical issue for the global shipping industry, and maritime situational awareness is essential for ensuring safe navigation in waterways. This paper addresses the problem of intelligent identification of potential navigational risks in ship navigation environments and proposes a Transformer-based approach for ship encounter situation recognition. This method utilizes Automatic Identification System (AIS) data to extract encounter features. Contextual Position Encoding and Coordinate Attention mechanisms are introduced into the model to capture spatial correlation and directional features, enhancing the accuracy of determining
Ma, TongyuePan, MingyangLi, ShaoxiHu, JingfengLi, Chao
Although the number of trucks is low, their accident rate is high, and the consequences of accidents are severe. This paper is based on GPS data from 100 trucks, with each trip chain defined by a vehicle’s stay time greater than 20 minutes. The kinematic parameters for each trip chain are then extracted, and the entropy weight method is used to calculate the weights of various parameters. A random forest model is applied to select 11 key indicators, including speed and acceleration. The entropy weight-TOPSIS algorithm is used to assess the risk of each trip chain for the trucks. Different combinations of continuous and discontinuous trip chain scenarios are constructed. Finally, support vector machines (SVM) and decision tree methods are used for risk prediction under different trip chain combinations. The results show that the 11 selected key indicators provide an accuracy of 95.74% for describing the sample. In general, the SVM model shows better prediction accuracy than the decision
Huang, YunheXiong, ZhihuaLi, Jiayu
Dangling from a weather balloon 80,000 feet above New Mexico, a pair of antennas sticks out from a Styrofoam cooler. From that height, the blackness of space presses against Earth’s blue skies. But the antennas are not captivated by the breathtaking view. Instead, they listen for signals that could make air travel safer.
Planetary and lunar rover exploration missions can encounter environments that do not allow for navigation by typical, stereo camera-based systems. Stereo cameras meet difficulties in areas with low ambient light (even when lit by floodlights), direct sunlight, or washed-out environments. Improved sensors are required for safe and successful rover mobility in harsh conditions. NASA Goddard Space Flight Center has developed a Space Qualified Rover LiDAR (SQRLi) system that will improve rover sensing capabilities in a small, lightweight package. The new SQRLi package is developed to survive the hazardous space environment and provide valuable image data during planetary and lunar rover exploration.
(TC)The paper presents a designed and evaluated optimal traction control (TC) strategy for unmanned agriculture vehicle, where onboard sensors acquire various real-time information about wheel speed, load sharing, and terrain characteristics to achieve the precise control of the powertrain by establishing an optimal control command; moreover, the developed AMT-adaptive SMC combines the AMT adaptive control algorithm and the SMC to implement the dynamic gear shifting, torque output, and driving mode switching to obtain an optimal power distribution according to different speed demand and harvest load. Based on the establishment of models of the autonomous agriculture vehicle and corresponding tire model, a MATLAB/Simulink method based on dynamic simulation is adopted to simulate the unmanned agricultural vehicle traversing different terrains conditions. The results from comparison show that the energy saving reaches 19.0%, rising from 2. 1 kWh/km to 1. 7 kWh/km, an increase in
Feng, ZhenghaoLu, YunfanGao, DuanAn, YiZhou, Chuanbo
In contemporary society, where Global Navigation Satellite Systems (GNSS) are utilised extensively, their inherent fragility gives rise to potential hazards with respect to the safety of ship navigation. In order to address this issue, the present study focuses on an ASM signal delay measurement system based on software defined radio peripherals. The system comprises two distinct components: a transmitting end and a receiving end. At the transmitting end, a signal generator, a first time-frequency synchronisation device, and a VHF transmitting antenna are employed to transmit ASM signals comprising dual Barker 13 code training sequences. At the receiving end, signals are received via software-defined radio equipment, a second time-frequency synchronisation device, a computing host, and a VHF receiving antenna. Utilising sliding correlation algorithms enables accurate time delay estimation. The present study leverages the high performance and low cost advantages of the universal
Li, HaoSun, XiaowenWang, TianqiZhou, ZeliangWang, Xiaoye
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
Modern automotive systems generate a wide range of audio-based signals, such as indicator chimes, turn signals, infotainment system audio, navigation prompts, and warning alerts, to facilitate communication between the vehicle and its occupants. Accurate Classification and transcription of this audio is important for refining driver aid systems, safety features, and infotainment automation. This paper introduces an AI/ML-powered technique for audio classification and transcription in automotive environments. The proposed solution employs a hybrid deep learning architecture that leverages convolutional neural networks (CNNs) and recurrent neural networks (RNNs), trained using labeled audio samples. Moreover, an Automatic Speech Recognition (ASR) model is integrated for transcribing spoken navigation prompts and commands from infotainment systems. The proposed system delivers reliable results in real-time audio classification and transcription, facilitating better automation and
Singh, ShwethaKamble, AmitMohanty, AnantaKalidas, Sateesh
Identification of different types of turns during field operation of off-road vehicles is critical in the overall vehicle development as it is helpful in identifying & optimizing machine performance, correct duty cycle, fuel economy, stability analysis, accurate path planning, customer usage pattern & designing the critical components, etc. In this study, a machine learning (ML) based methodology has been developed to detect the off-road vehicle turns using vehicle & GPS parameters. Three most common types of off-road vehicles turn conditions e.g., Straight line, Bulb turn, and Three-Point turn have been considered. Different vehicle parameters (like latitude & longitude, compass bearing, yaw rate, vehicle speed, swash plate angle, engine speed, percent load at vehicle speed, raise lower front & PTO channels) generated during field test have been used here. These vehicle parameters are further processed, analysed and used in ML learning model building. Four ML models e.g., SVM, K-NN
Rai, RohitGangsar, Purushottam
In motorcycle racing and other competitions, there is a technique to intentionally slide the rear wheel to make turns more quickly. While this technique is effective for high-speed riding, it is difficult to execute and carries risks such as falling. Therefore, an anti-sideslip control system that suppresses unintended or excessive sideslip is needed to ensure safe, natural, and smooth turning. In anti-sideslip control, the slip angle is usually used as a control parameter. However, for motorcycles, it is necessary to know the absolute direction of the vehicle's movement. To determine this, GPS or optical sensors are required, but using such sensors for driving is costly and may not provide accurate measurements due to contamination or other environmental factors, making it impractical. Therefore, an anti-sideslip control system was developed by calculating another parameter that indicates the characteristics of the slip angle, without measuring the slip angle itself, thus eliminating
Nakano, KyosukeKawai, KazunoriTakeuchi, Michinori
With the continuous advancement of economic globalization, international trade has been developing rapidly, and Marine transportation is an important part of international trade. Shipping and port are facing greater opportunities for development, the shipping industry gradually to the modernization, specialization, large-scale rapid development. The rapid increase of the number of ships, the tonnage of ships, the flow of ships, the density of ships, and the busier of the channel traffic, these changes make the navigable conditions of navigable waters. Under the limited port water conditions, the ship traffic density increases, the ship distress probability increases, and the navigation environment becomes more complex, which make the water transportation safety face greater challenges and threats. The waters of dense traffic flow, danger, accidents, the importance of its navigation safety assessment is self-evident. Preventing some accident risk in the process of ship navigation has
You, HaoweiZheng, Zhongyi
This study establishes models of airport vertical navigation lights and aircraft vulnerable components (wings and landing gear) using SOLIDWORKS. Based on the frangibility standards for airport navigation facilities, the control dimensions of the circular tube model for navigation lights are determined. Numerical simulations are conducted in ANSYS Workbench to analyze collisions between aircraft wings/landing gear and navigation lights under three different velocity conditions. Internal energy analysis, bidirectional force response, and stress nephograms during the impact process are evaluated. The results indicate that current standards ensure that collisions with vertical navigation lights during takeoff and landing do not cause deformation or damage to aircraft vulnerable components, thereby guaranteeing the safety of aircraft and pilots.
Wang, JianwuSong, XiaoboWei, YanLiu, HongweiYou, ShengnanSun, Jinkun
River regulation engineering is pivotal for harmonizing flood resilience, ecological integrity, and navigation efficiency in large alluvial systems, particularly under intensified hydrological stressors. The Yangtze River, Asia’s largest fluvial network, has experienced altered hydro-sedimentary regimes and exacerbated channel instability due to cascade reservoir operations, demanding adaptive strategies to stabilize dynamic reaches. This study investigates hydrodynamic and flow distribution responses to integrated regulation measures in the Chizhou Reach—a vulnerable alluvial segment characterized by severe bank erosion, sedimentation-induced flow imbalances, and constrained floodplains. Using a 1:500/1:100 scaled hydraulic model validated under flood and low-flow conditions, we assess synergistic effects of dredging, submerged dams, and flow-regulating groynes. Here we show that dredging the Wanchuanzhou right branch increases its flow diversion ratio by 1.71% (annual average flow
Gao, JinFeng, LileiRuan, JunshengLu, LixinYan, Jun
How to realize the intelligent collision avoidance of inland waterway ships has become a hot issue in the field of transportation. The navigation status, position information and speed of inland vessels can be obtained by using the shipborne Beidou terminal and AIS, so as to realize the real-time monitoring of the ship’s operation status and the real-time optimization of collision avoidance path planning. In the process of track classification and prediction, it is necessary to use deep learning algorithms to train and learn historical track data, so as to generate a model that can accurately predict future tracks, and make collision avoidance path planning decisions on this basis, so as to realize the intelligence of water traffic organization and ship collision avoidance.
Liu, XingchenCui, JianzhangKong, Lingqi
In the intelligent traffic system (ITS), roadside sensing can obtain the movement status of various objects in the traffic scene in real time with a globalized perspective, which is of great significance for traffic flow optimization, accident early warning, and rescue afterwards. Accurate target positioning is one of the key links to realize these functions, which can not only help the traffic management department to grasp the traffic condition in time, but also provide the basis for rescue personnel to respond quickly when an accident occurs, so as to minimize the damage caused by the accident. Therefore, a method for acquiring the Global Positioning System (GPS) coordinates of objects relying on monocular surveillance installed on the roadside is proposed in this paper. By combining the target detection algorithm and the coordinate transformation method, and considering the information such as the installation status and internal parameters of the camera, the pixel positions of
Zhang, NijiaLu, MingfengChen, ZiyiZhang, FengTao, RanHu, WeidongFu, Xiongjun
NASA has developed an innovative combination of a Magnetometer, low-powered ElectroMagnets, and Resonant Inductive Coupling (MEMRIC) to create and control relative positioning of nano satellites within a cluster. This is a game-changing approach to enable distributed nanosatellite (nanosat) clusters. The focus is on low-cost propulsion, navigation, and power sharing. Each of these functions can share the same basic technology.
Animals like bats, whales, and insects have long used acoustic signals for communication and navigation. Now, an international team of scientists have taken a page from nature’s playbook to model micro-sized robots that use sound waves to coordinate into large swarms that exhibit intelligent-like behavior. The robot groups could one day carry out complex tasks like exploring disaster zones, cleaning up pollution, or performing medical treatments from inside the body, according to team lead Igor Aronson, Huck Chair Professor of Biomedical Engineering, Chemistry, and Mathematics at Penn State.
Navigation in off-road terrains is a well-studied problem for self-driving and autonomous vehicles. Frequently cited concerns include features like soft soil, rough terrain, and steep slopes. In this paper, we present the important but less studied aspect of negotiating vegetation in off-road terrain. Using recent field measurements, we develop a fast running model for the resistance on a ground vehicle overriding both small vegetation like grass and larger vegetation like bamboo and trees. We implement of our override model into a 3D simulation environment, the MSU Autonomous Vehicle Simulator (MAVS), and demonstrate how this model can be incorporated into real-time simulation of autonomous ground vehicles (AGV) operating in off-road terrain. Finally, we show how this model can be used to simulate autonomous navigation through a variety of vegetation with a PID speed controller and measuring the effect of navigation through vegetation on the vehicle speed.
Goodin, ChristopherMoore, Marc N.Hudson, Christopher R.Carruth, Daniel W.Salmon, EthanCole, Michael P.Jayakumar, ParamsothyEnglish, Brittney
Navigation in off-road terrains is a well-studied problem for self-driving and autonomous vehicles. Frequently cited concerns include features like soft soil, rough terrain, and steep slopes. In this paper, we present the important but less studied aspect of negotiating vegetation in off-road terrain. Using recent field measurements, we develop a fast running model for the resistance on a ground vehicle overriding both small vegetation like grass and larger vegetation like bamboo and trees. We implement of our override model into a 3D simulation environment, the MSU Autonomous Vehicle Simulator (MAVS), and demonstrate how this model can be incorporated into real-time simulation of autonomous ground vehicles (AGV) operating in off-road terrain. Finally, we show how this model can be used to simulate autonomous navigation through a variety of vegetation with a PID speed controller and measuring the effect of navigation through vegetation on the vehicle speed.
Goodin, ChristopherMoore, Marc N.Hudson, Christopher R.Carruth, Daniel W.Salmon, EthanCole, Michael P.Jayakumar, ParamsothyEnglish, Brittney
The Vision for Off-road Autonomy (VORA) project used passive, vision-only sensors to generate a dense, robust world model for use in off-road navigation. The research resulted in vision-based algorithms applicable to defense and surveillance autonomy, intelligent agricultural applications, and planetary exploration. Passive perception for world modeling enables stealth operation (since lidars can alert observers) and does not require more expensive or specialized sensors (e.g., radar or lidar). Over the course of this three-phase program, SwRI built components of a vision-only navigation pipeline and tested the result on a vehicle platform in an off-road environment.
Towler, Meera DayGarza, Harold A.Chambers, David R.
Despite all the technological evolution in navigation, waters just off coastal shores around the globe have remained a black box. That is, until researchers from The University of Texas at Austin and Oregon State University developed a new technology that uses satellites in space to map out these tricky areas.
As NASA’s Artemis missions build out infrastructure on and around the Moon in the coming years, CubeSats and other small satellites will likely play an important role in a communications network that will enable not only conversation with mission control but also navigation, direct scientific observations, and more, all enabled by an internet-like “LunaNet.” These little satellites are cheap to launch and can form constellations for relaying signals reliably. But their small size makes it hard for them to carry antennas large enough to communicate across vast distances.
This article introduces a comprehensive cooperative navigation algorithm to improve vehicular system safety and efficiency. The algorithm employs surrogate optimization to prevent collisions with cooperative cruise control and lane-keeping functionalities. These strategies address real-world traffic challenges. The dynamic model supports precise prediction and optimization within the MPC framework, enabling effective real-time decision-making for collision avoidance. The critical component of the algorithm incorporates multiple parameters such as relative vehicle positions, velocities, and safety margins to ensure optimal and safe navigation. In the cybersecurity evaluation, the four scenarios explore the system’s response to different types of cyberattacks, including data manipulation, signal interference, and spoofing. These scenarios test the algorithm’s ability to detect and mitigate the effects of malicious disruptions. Evaluate how well the system can maintain stability and avoid
Khan, Rahan RasheedHanif, AtharAhmed, Qadeer
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
With 2D cameras and space robotics algorithms, astronautics engineers at Stanford have created a navigation system able to manage multiple satellites using visual data only. They recently tested it in space for the first time. Stanford University, Stanford, CA Someday, instead of large, expensive individual space satellites, teams of smaller satellites - known by scientists as a “swarm” - will work in collaboration, enabling greater accuracy, agility, and autonomy. Among the scientists working to make these teams a reality are researchers at Stanford University's Space Rendezvous Lab, who recently completed the first-ever in-orbit test of a prototype system able to navigate a swarm of satellites using only visual information shared through a wireless network. “It's a milestone paper and the culmination of 11 years of effort by my lab, which was founded with this goal of surpassing the current state of the art and practice in distributed autonomy in space,” said Simone D'Amico
Today, our mobile phones, computers, and GPS systems can give us very accurate time indications and positioning thanks to the over 400 atomic clocks worldwide. All sorts of clocks - be it mechanical, atomic or a smartwatch - are made of two parts: an oscillator and a counter. The oscillator provides a periodic variation of some known frequency over time while the counter counts the number of cycles of the oscillator. Atomic clocks count the oscillations of vibrating atoms that switch between two energy states with very precise frequency.
Wheel Force Transducers (WFT) are precise and accurate measurement devices that seamlessly integrate into any vehicle. They can be applied in numerous vehicle applications for both on-road and in laboratory settings. The instrumentation requires replacing an original equipment manufacturer (OEM) wheel with a custom WFT system which is specific to the wheel hub design. An ideal design will minimally impact a vehicle's dynamics, but the vehicle system is inherently modified from the mass of the measurement device. Research and technical documentation have been published which provide conclusions explaining reduction in the unsprung mass reduces dynamic wheel load. However, there doesn’t appear to be clear compensation techniques for how a modified unsprung mass can be related to the original system, thus allowing the WFT signals to be more accurate to the OEM wheel forces. An experimental study was performed on a prototype motorcycle to better understand these differences. An
Frisco, JacobLarsen, WilliamRhudy, ScottOosting, NicholasLaurent, Matthew
Energy management strategy is essential for HEV’s to achieve an optimum of energy consumption. With predictive energy management, taking future vehicle speed predicted from ADAS map information, in-vehicle navigation traffic flow status information, and current speed into account, one could anticipate a considerable improvement in energy-saving. The major validating approach widely adopted for energy management algorithms nowadays is real-world vehicle testing, of which the economic and time costs are relatively high. Moreover, with advanced algorithms featuring AI coming into light, putting forward higher requirement in the richness of test cases, the drawback in coverage of vehicle testing is revealed. This paper proposed a MIL/SIL testing approach for predictive energy management algorithms, providing a partial replacement to, and overcome the limitations of, vehicle testing. In the testing setup, random traffic generated by MATLAB® based on real-time traffic condition will be taken
Yan, YueMa, XiudanWei, XinliXiong, JieDeng, YunfeiBradfield, Donald Edward
The recent advancements in fields such as sensors, AI, and IoT are majorly impacting the automotive industry. Automated Driving Systems (ADS) are developing rapidly, meaning that SAE J3016 Level 3 and above vehicles are quickly becoming a reality. As a result, maintenance of such systems becomes essential to ensure their safe and efficient operation. Prognostic techniques in particular are crucial to monitor the state of health and predicting the end of life for components. Prognostics engineering is being applied in many industries and for conventional automotive applications, but ADS is new technology, and the prognostics for these systems are still being developed and adapted. In this paper, we first present a review of the most used prognostic techniques across different safety-critical domains such as aerospace, power, and manufacturing. Then, we summarize the main challenges that must be faced to successfully develop novel approaches for prognostics of ADS components and provide
Merola, FrancescoHanif, AtharLami, GiuseppeAhmed, QadeerMonohon, Mark
In cold and snowy areas, low-friction and non-uniform road surfaces make vehicle control complex. Manually driving a car becomes a labor-intensive process with higher risks. To explore the upper limits of vehicle motion on snow and ice, we use an existing aggressive autonomous algorithm as a testing tool. We built our 1:5 scaled test platform and proposed an RGBA-based cost map generation method to generate cost maps from either recorded GPS waypoints or manually designed waypoints. From the test results, the AutoRally software can be used on our test platform, which has the same wheelbase but different weights and actuators. Due to the different platforms, the maximum speed that the vehicle can reach is reduced by 1.38% and 2.26% at 6.0 m/s and 8.5 m/s target speeds. When tested on snow and ice surfaces, compared to the max speed on dirt (7.51 m/s), the maximum speed decreased by 48% and 53.9%, respectively. In addition to the significant performance degradation on snow and ice, the
Yang, YimingBos, Jeremy P.
Autonomous ground navigation has advanced significantly in urban and structured environments, supported by the availability of comprehensive datasets. However, navigating complex and off-road terrains remains challenging due to limited datasets, diverse terrain types, adverse environmental conditions, and sensor limitations affecting vehicle perception. This study presents a comprehensive review of off-road datasets, integrating their applications with sensor technologies and terrain traversability analysis methods. It identifies critical gaps, including class imbalances, sensor performance under adverse conditions, and limitations in existing traversability estimation approaches. Key contributions include a novel classification of off-road datasets based on annotation methods, providing insights into scalability and applicability across diverse terrains. The study also evaluates sensor technologies under adverse conditions and proposes strategies for incorporating event-based and
Musau, HannahRuganuza, DenisIndah, DebbieMukwaya, ArthurGyimah, Nana KankamPatil, AshishBhosale, MayureshGupta, PrakharMwakalonge, JudithJia, YunyiMikulski, DariuszGrabowsky, DavidHong, Jae DongSiuhi, Saidi
Bicycle computers record and store kinematic and physiologic data that can be useful for forensic investigations of crashes. The utility of speed data from bicycle computers depends on the accurate synchronization of the speed data with either the recorded time or position, and the accuracy of the reported speed. The primary goals of this study were to quantify the temporal asynchrony and the error amplitudes in speed measurements recorded by a common bicycle computer over a wide area and over a long period. We acquired 96 hours of data at 1-second intervals simultaneously from three Garmin Edge 530 computers mounted to the same bicycle during road cycling in rural and urban environments. Each computer recorded speed data using a different method: two units were paired to two different external speed sensors and a third unit was not paired to any remote sensors and calculated its speed based on GPS data. We synchronized the units based on the speed signals and used one of the paired
Booth, Gabrielle R.Siegmund, Gunter P.
Accurate reconstruction of vehicle collisions is essential for understanding incident dynamics and informing safety improvements. Traditionally, vehicle speed from dashcam footage has been approximated by estimating the time duration and distance traveled as the vehicle passes between reference objects. This method limits the resolution of the speed profile to an average speed over given intervals and reduces the ability to determine moments of acceleration or deceleration. A more detailed speed profile can be calculated by solving for the vehicle’s position in each video frame; however, this method is time-consuming and can introduce spatial and temporal error and is often constrained by the availability of external trackable features in the surrounding environment. Motion tracking software, widely used in the visual effects industry to track camera positions, has been adopted by some collision reconstructionists for determining vehicle speed from video. This study examines the
Perera, NishanGriffiths, HarrisonPrentice, Greg
Predictive performance simulation of a high-efficiency lightweight vehicle is performed through development of a multi-physics MATLAB Simulink model including advanced vehicle dynamics. The vehicle is put into a three-dimensional representation of the racetrack, including its dimensions, slope, banking, and adhesion coefficient along the model space, elaborated from the track GPS data points. The vehicle’s reference trajectory is not priorly provided to the model at the simulation start as, during run-time, a predictive Steering Angle Generation (SAG) algorithm based on Nonlinear Model Predictive Control (NMPC) computes the optimal steering angle input needed to drive the vehicle on the track within its limits. Computation is based on fast predictive simulations of a simplified version of dynamics modelling of the vehicle. Each single simulation exploits a different possible steering angle to be applied by the virtual driver, starting from the initial conditions given by the actual
De Carlo, MatteoManzone, Simonede Carvalho Pinheiro, HenriqueCarello, Massimiliana
In this study, we introduce RGB2BEV-Net, an end-to-end pipeline that extends traditional BEV segmentation models by utilizing raw RGB images with Bird’s Eye View (BEV) generation. While previous work primarily focused on pre-segmented images to generate corresponding BEV maps, our approach expands this by collecting RGB images alongside their affiliated segmentation masks and BEV representations. This enables direct input of RGB camera sensors into the pipeline, reflecting real-world autonomous driving scenarios where RGB cameras are commonly used as sensors, rather than relying on pre-segmented images. Our model processes four RGB images through a segmentation layer before converting them into a segmented BEV, implemented in the PyTorch framework after being adapted from an original implementation that utilized a different framework. This adaptation was necessary to improve compatibility and ensure better integration of the entire system within autonomous vehicle applications. We
Hossain, SabirLin, Xianke
With the growing diversification of modern urban transportation options, such as delivery robots, patrol robots, service robots, E-bikes, and E-scooters, sidewalks have gained newfound importance as critical features of High-Definition (HD) Maps. Since these emerging modes of transportation are designed to operate on sidewalks to ensure public safety, there is an urgent need for efficient and optimal sidewalk routing plans for autonomous driving systems. This paper proposed a sidewalk route planning method using a cost-based A* algorithm and a mini-max-based objective function for optimal routes. The proposed cost-based A* route planning algorithm can generate different routes based on the costs of different terrains (sidewalks and crosswalks), and the objective function can produce an efficient route for different routing scenarios or preferences while considering both travelling distance and safety levels. This paper’s work is meant to fill the gap in efficient route planning for
Bao, ZhibinLang, HaoxiangLin, Xianke
Towards the goal of real-time navigation of autonomous robots, the Iterative Closest Point (ICP) based LiDAR odometry methods are a favorable class of Simultaneous Localization and Mapping (SLAM) algorithms for their robustness under any light conditions. However, even with the recent methods, the traditional SLAM challenges persist, where odometry drifts under adversarial conditions such as featureless or dynamic environments, as well as high motion of the robots. In this paper, we present a motion-aware continuous-time LiDAR-inertial SLAM framework. We introduce an efficient EKF-ICP sensor fusion solution by loosely coupling poses from the continuous time ICP and IMU data, designed to improve convergence speed and robustness over existing methods while incorporating a sophisticated motion constraint to maintain accurate localization during rapid motion changes. Our framework is evaluated on the KITTI datasets and artificially motion-induced dataset sequences, demonstrating
Kokenoz, CigdemShaik, ToukheerSharma, AbhishekPisu, PierluigiLi, Bing
Items per page:
1 – 50 of 1125