Learning World Transition Model for Socially Aware Robot Navigation
arXiv:2011.03922
Abstract
Moving in dynamic pedestrian environments is one of the important requirements for autonomous mobile robots. We present a model-based reinforcement learning approach for robots to navigate through crowded environments. The navigation policy is trained with both real interaction data from multi-agent simulation and virtual data from a deep transition model that predicts the evolution of surrounding dynamics of mobile robots. The model takes laser scan sequence and robot's own state as input and outputs steering control. The laser sequence is further transformed into stacked local obstacle maps disentangled from robot's ego motion to separate the static and dynamic obstacles, simplifying the model training. We observe that our method can be trained with significantly less real interaction data in simulator but achieve similar level of success rate in social navigation task compared with other methods. Experiments were conducted in multiple social scenarios both in simulation and on real robots, the learned policy can guide the robots to the final targets successfully while avoiding pedestrians in a socially compliant manner. Code is available at https://github.com/YuxiangCui/model-based-social-navigation
References in corpus (8)
- Social Force Model for Pedestrian Dynamics
- Decomposing Motion and Content for Natural Video Sequence Prediction
- Model-Based Reinforcement Learning for Atari
- Learning Latent Dynamics for Planning from Pixels
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
- Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans
- Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios
- A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games