RBE Directed Research Presentation
Zhanhong Huang
Motion Planning for LiDAR-based Automated Driving Simulation
Friday, April 28th, 2023
2:00 PM - 3:00 PM
Zoom Link: https://wpi.zoom.us/j/5226320068
Abstract: Real-time motion planning is one of the crucial tasks for autonomous driving. While there are many research works focused on improving the performance of perception and motion planning independently, it is not clear how a perception error may adversely impact the motion planning results. Hereby, we propose a joint simulation framework with LiDAR-based perception and motion planning for real-time automated driving. In this work, we introduce a new collision bound representation that relaxes the communication cost between the perception module and the motion planner. Given the vehicle information from the LiDAR perception system, a novel collision checking algorithm is implemented using line intersection checking, which is more efficient for long-distance range in comparison to the traditional method of occupancy grid. We evaluate the joint simulation framework in CARLA for urban driving scenarios. Experiments show that our proposed automated driving system can execute at 25 Hz, which meets the real-time requirement. The motion planning results show that a consistent safe distance is kept when simulating urban driving scenarios in CARLA.
Advisor:
Professor Xinming Huang, Worcester Polytechnic Institute (WPI)
Committee:
Professor Pradeep Radhakrishnan, Worcester Polytechnic Institute (WPI)