Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
Authors:
- 30 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3517-3524
Abstract
Safe and efficient navigation through human crowds is an essential capability for mobile robots. Previous work on robot crowd navigation assumes that the dynamics of all agents are known and well-defined. In addition, the performance of previous methods deteriorates in partially observable environments and environments with dense crowds. To tackle these problems, we propose decentralized structural-Recurrent Neural Network (DS-RNN), a novel network that reasons about spatial and temporal relationships for robot decision making in crowd navigation. We train our network with model-free deep reinforcement learning without any expert supervision. We demonstrate that our model outperforms previous methods in challenging crowd navigation scenarios. We successfully transfer the policy learned in the simulator to a real-world TurtleBot 2i.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Human-level control through deep reinforcement learningNature, 2015
- Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperationThe International Journal of Robotics Research, 2015
- Seeking a path through the crowd: Robot navigation in unknown dynamic environments with moving obstacles based on an integrated environment representationRobotics and Autonomous Systems, 2014
- Algorithms for collision-free navigation of mobile robots in complex cluttered environments: a surveyRobotica, 2014
- Human-aware robot navigation: A surveyRobotics and Autonomous Systems, 2013
- Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patternsAutonomous Robots, 2013
- Robot navigation in dense human crowds: the case for cooperation2013
- Reciprocal n-Body Collision Avoidance2011
- The dynamic window approach to collision avoidanceIEEE Robotics & Automation Magazine, 1997
- Social force model for pedestrian dynamicsPhysical Review E, 1995