Realtime Collision Avoidance for Mobile Robots in Dense Crowds using Implicit Multi-sensor Fusion and Deep Reinforcement Learning
arXiv:2004.03089
Abstract
We present a novel learning-based collision avoidance algorithm, CrowdSteer, for mobile robots operating in dense and crowded environments. Our approach is end-to-end and uses multiple perception sensors such as a 2-D lidar along with a depth camera to sense surrounding dynamic agents and compute collision-free velocities. Our training approach is based on the sim-to-real paradigm and uses high fidelity 3-D simulations of pedestrians and the environment to train a policy using Proximal Policy Optimization (PPO). We show that our learned navigation model is directly transferable to previously unseen virtual and dense real-world environments. We have integrated our algorithm with differential drive robots and evaluated its performance in narrow scenarios such as dense crowds, narrow corridors, T-junctions, L-junctions, etc. In practice, our approach can perform real-time collision avoidance and generate smooth trajectories in such complex scenarios. We also compare the performance with prior methods based on metrics such as trajectory length, mean time to goal, success rate, and smoothness and observe considerable improvement.
8 pages, 7 figures
References in corpus (7)
- Social Force Model for Pedestrian Dynamics
- From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots
- Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
- Towards Monocular Vision based Obstacle Avoidance through Deep Reinforcement Learning
- Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios
- CrowdMove: Autonomous Mapless Navigation in Crowded Scenarios
- Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning