The complexity to handle complex situations in automated driving requires increasing computational resources. In this work, we propose a machine learning approach for motion planning aiming at optimizing the set of path candidates to be evaluated in accordance with the driving context. Thus, the computation cost of the whole motion planning strategy can be reduced while generating safe and comfortable trajectories when required. The proposed strategy has been implemented in a real experimental platform and validated in different operating environments, successfully providing high quality trajectories in a small time frame.
Machine learning based motion planning approach for intelligent vehicles
2020-10-19
2375237 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Machine learning based motion planning approach for intelligent vehicles
BASE | 2020
|MACHINE LEARNING BASED MOTION PLANNING APPROACH FOR INTELLIGENT VEHICLES
British Library Conference Proceedings | 2020
|Motion Planning of Intelligent Vehicles: A Survey
IEEE | 2006
|