Adaptive Behavior Generation for Autonomous Driving using Deep Reinforcement Learning with Compact Semantic States
This work addresses the challenge of decision-making in autonomous driving by enabling online behavior adaptation, which is incremental as it builds on existing deep reinforcement learning methods with a novel state representation.
The paper tackles the problem of generating adaptive driving behaviors for autonomous vehicles by using deep reinforcement learning with a compact semantic state representation, resulting in an agent that learns to drive safely and adhere to traffic rules in various scenarios without requiring re-training for behavior changes.
Making the right decision in traffic is a challenging task that is highly dependent on individual preferences as well as the surrounding environment. Therefore it is hard to model solely based on expert knowledge. In this work we use Deep Reinforcement Learning to learn maneuver decisions based on a compact semantic state representation. This ensures a consistent model of the environment across scenarios as well as a behavior adaptation function, enabling on-line changes of desired behaviors without re-training. The input for the neural network is a simulated object list similar to that of Radar or Lidar sensors, superimposed by a relational semantic scene description. The state as well as the reward are extended by a behavior adaptation function and a parameterization respectively. With little expert knowledge and a set of mid-level actions, it can be seen that the agent is capable to adhere to traffic rules and learns to drive safely in a variety of situations.