SafeCrowdNav: safety evaluation of robot crowd navigation in complex scenes
Authors:
Open Access
- 12 October 2023
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 17, 1276519
Abstract
Navigating safely and efficiently in dense crowds remains a challenging problem for mobile robots. The interaction mechanisms involved in collision avoidance require robots to exhibit active and foresighted behaviors while understanding the crowd dynamics. Deep reinforcement learning methods have shown superior performance compared to model-based approaches. However, existing methods lack an intuitive and quantitative safety evaluation for agents, and they may potentially trap agents in local optima during training, hindering their ability to learn optimal strategies. In addition, sparse reward problems further compound these limitations. To address these challenges, we propose SafeCrowdNav, a comprehensive crowd navigation algorithm that emphasizes obstacle avoidance in complex environments. Our approach incorporates a safety evaluation function to quantitatively assess the current safety score and an intrinsic exploration reward to balance exploration and exploitation based on scene constraints. By combining prioritized experience replay and hindsight experience replay techniques, our model effectively learns the optimal navigation policy in crowded environments. Experimental outcomes reveal that our approach enables robots to improve crowd comprehension during navigation, resulting in reduced collision probabilities and shorter navigation times compared to state-of-the-art algorithms. Our code is available at https://github.com/Janet-xujing-1216/SafeCrowdNav.Keywords
This publication has 23 references indexed in Scilit:
- Crowd-Robot Interaction: Crowd-Aware Robot Navigation With Attention-Based Deep Reinforcement Learning2019
- Curiosity-Driven Exploration by Self-Supervised Prediction2017
- Mobile Robot Navigation and Obstacle Avoidance Techniques: A ReviewInternational Robotics & Automation Journal, 2017
- Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning2017
- Neural networks based reinforcement learning for mobile robots obstacle avoidanceExpert Systems with Applications, 2016
- Social LSTM: Human Trajectory Prediction in Crowded Spaces2016
- Reciprocal n-Body Collision Avoidance2011
- Unfreezing the robot: Navigation in dense, interacting crowds2010
- Reciprocal Velocity Obstacles for real-time multi-agent navigation2008
- Social force model for pedestrian dynamicsPhysical Review E, 1995