Realtime Collision Avoidance for Mobile Robots in Dense Crowds using Implicit Multi-sensor Fusion and Deep Reinforcement Learning
This addresses the problem of safe and efficient navigation for mobile robots in crowded environments, representing an incremental advance with specific gains.
The authors tackled real-time collision avoidance for mobile robots in dense crowds by developing CrowdSteer, an end-to-end learning-based algorithm using multi-sensor fusion and deep reinforcement learning, which showed considerable improvements in metrics like trajectory length and success rate compared to prior methods.
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.