Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
This addresses safe and efficient robot navigation in crowded environments, but it is incremental as it extends a previous approach with improvements like LSTM for scalability.
The paper tackles the problem of robot navigation among dynamic, decision-making agents by developing a deep reinforcement learning algorithm that avoids collisions without assuming specific behavior rules and handles arbitrary numbers of agents using an LSTM strategy. The result shows it outperforms previous methods as agent count increases and is demonstrated on an autonomous vehicle at human walking speed without 3D Lidar.
Robots that navigate among pedestrians use collision avoidance algorithms to enable safe and efficient operation. Recent works present deep reinforcement learning as a framework to model the complex interactions and cooperation. However, they are implemented using key assumptions about other agents' behavior that deviate from reality as the number of agents in the environment increases. This work extends our previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules. This work also introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size. The proposed algorithm outperforms our previous approach in simulation as the number of agents increases, and the algorithm is demonstrated on a fully autonomous robotic vehicle traveling at human walking speed, without the use of a 3D Lidar.