Autonomous driving paper index
Enhancing Safety and Handling of Autonomous Vehicles in Simulated Traffic: A Co-Simulation Framework Using Multibody Dynamics and CARLA
One-line summary
In recent years, there has been an increased emphasis on autonomous driving technologies to improve vehicle road safety amidst rising traffic congestion and the complexities of intersection jaywalking and diverse road conditions.
Engineering notes
Key topics: autonomous driving, autonomous vehicle, lane change, carla, control. See the paper for implementation details and experimental results.
Chinese explanation / 中文解读
中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。
Original abstract
In recent years, there has been an increased emphasis on autonomous driving technologies to improve vehicle road safety amidst rising traffic congestion and the complexities of intersection jaywalking and diverse road conditions. Therefore, improving the vehicle's handling ability is crucial for safe and efficient traffic navigation, particularly emphasising collision prevention and safety in unforeseen circumstances. Evaluating safety perspectives in such situations, the lane change event serves as an important measure for addressing the matter and forms the focus of this paper. However, for such new-age technology, conducting proving ground tests replicating urban conditions is a costly endeavour. Hence, simulation is a better approach, which can mimic real traffic conditions, develop control systems, and simulate vehicle handling behaviour all working together within a closed-loop system. An autonomous lane change manoeuvre event of a four-wheeled vehicle is created in a simulation environment where the system will initiate the lane change manoeuvre based on the relative distance of the slow-moving preceding vehicle to the ego vehicle. The trajectory of the vehicle will be determined by the type of slow-moving vehicle and the dimensions of the road. A series of lane change events generated by MBD simulation will be converted into a reduced-order model (ROM) and integrated into the system. The control system will be developed using MBSE and co-simulated with CARLA for testing the system in a CARLA environment, replicating urban conditions. This enables the integration of accurate dynamics of the vehicle into CARLA, ensuring a reliable manoeuver. To check the robustness of the system, various traffic scenarios will be simulated.
Links and sources
Need this topic turned into a technical roadmap?
Full Self Driving can prepare a custom autonomous driving literature review, code map, dataset map, and B2B technology assessment.
Request B2B research
Comments