Learning driving styles for autonomous vehicles from demonstration
IEEE International Conference on Robotics and Automation(2015)
摘要
It is expected that autonomous vehicles capable of driving without human supervision will be released to market within the next decade. For user acceptance, such vehicles should not only be safe and reliable, they should also provide a comfortable user experience. However, individual perception of comfort may vary considerably among users. Whereas some users might prefer sporty driving with high accelerations, others might prefer a more relaxed style. Typically, a large number of parameters such as acceleration profiles, distances to other cars, speed during lane changes, etc., characterize a human driver's style. Manual tuning of these parameters may be a tedious and error-prone task. Therefore, we propose a learning from demonstration approach that allows the user to simply demonstrate the desired style by driving the car manually. We model the individual style in terms of a cost function and use feature-based inverse reinforcement learning to find the model parameters that fit the observed style best. Once the model has been learned, it can be used to efficiently compute trajectories for the vehicle in autonomous mode. We show that our approach is capable of learning cost functions and reproducing different driving styles using data from real drivers.
更多查看译文
关键词
learning systems,mobile robots,acceleration profiles,autonomous vehicles,cost function,demonstration approach,feature-based inverse reinforcement learning,learning driving styles
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络