Deep Reinforcement Learning-Based Mapless Crowd Navigation with Perceived Risk of the Moving Crowd for Mobile Robots
This addresses safe and efficient navigation for mobile robots in dynamic, non-cooperative crowds, with incremental improvements in handling unseen behaviors.
The paper tackled the problem of generalization and scalability in deep reinforcement learning-based crowd navigation for mobile robots by incorporating a Collision Probability in the observation space, achieving a 100% success rate in all test scenarios and outperforming a state-of-the-art method in social safety.
Current state-of-the-art crowd navigation approaches are mainly deep reinforcement learning (DRL)-based. However, DRL-based methods suffer from the issues of generalization and scalability. To overcome these challenges, we propose a method that includes a Collision Probability (CP) in the observation space to give the robot a sense of the level of danger of the moving crowd to help the robot navigate safely through crowds with unseen behaviors. We studied the effects of changing the number of moving obstacles to pay attention during navigation. During training, we generated local waypoints to increase the reward density and improve the learning efficiency of the system. Our approach was developed using deep reinforcement learning (DRL) and trained using the Gazebo simulator in a non-cooperative crowd environment with obstacles moving at randomized speeds and directions. We then evaluated our model on four different crowd-behavior scenarios. The results show that our method achieved a 100% success rate in all test settings. We compared our approach with a current state-of-the-art DRL-based approach, and our approach has performed significantly better, especially in terms of social safety. Importantly, our method can navigate in different crowd behaviors and requires no fine-tuning after being trained once. We further demonstrated the crowd navigation capability of our model in real-world tests.