Path planning for obstacle avoidance of unmanned vehicles based on Frenet coordinates and B-spline curves
Abstract
With the development of intelligent networking technology and computer information processing technology, the functions of autonomous vehicle are constantly enriched and improved. In order to improve the path planning processing ability of autonomous vehicle when encountering obstacles, the paper makes in-depth analysis and research on the path planning of autonomous vehicles encountering obstacles based on the Frenet coordinate system and quasi uniform B-spline curve. By introducing the central reference line of the road to automatically drive the vehicle, when encountering obstacles, the road ahead is uniformly sampled laterally, and the feasible path for obstacle avoidance is planned according to the vehicle obstacle information and real-time vehicle information. Finally, the optimal path for obstacle avoidance is selected through maximum curvature constraint, target cost function, collision detection, etc. In order to verify the feasibility of the method, First, the basic function of the algorithm is verified in the self-developed automatic driving simulation test tool terminal, and the vehicle obstacle avoidance function is realized under the condition of continuous static obstacles. Finally, the real vehicle experiment proves that this method can run stably and reliably in the aspect of obstacle avoidance.
- Publication:
-
Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series
- Pub Date:
- September 2023
- DOI:
- 10.1117/12.2689707
- Bibcode:
- 2023SPIE12790E..5SC