In this paper, we propose a novel planning framework that can greatly improve the level of intelligence and driving quality of autonomous vehicles. A reference planning layer first generates kinematically and dynamically feasible paths assuming no obstacles on the road, then a behavioral planning layer takes static and dynamic obstacles into account. Instead of directly commanding a desired trajectory, it searches for the best directives for the controller, such as lateral bias and distance keeping aggressiveness. It also considers the social cooperation between the autonomous vehicle and surrounding cars. Based on experimental results from both simulation and a real autonomous vehicle platform, the proposed behavioral planning architecture improves the driving quality considerably, with a 90.3% reduction of required computation time in representative scenarios.
A behavioral planning framework for autonomous driving
2014-06-01
824221 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A BEHAVIORAL PLANNING FRAMEWORK FOR AUTONOMOUS DRIVING
British Library Conference Proceedings | 2014
|Perception and planning collaboration framework for autonomous driving
Europäisches Patentamt | 2022
|MULTIMODAL MOTION PLANNING FRAMEWORK FOR AUTONOMOUS DRIVING VEHICLES
Europäisches Patentamt | 2022
|PERCEPTION AND PLANNING COLLABORATION FRAMEWORK FOR AUTONOMOUS DRIVING
Europäisches Patentamt | 2019
|Europäisches Patentamt | 2021
|