Relative velocity-based reward functions for crowd navigation of robots

How to navigate effectively in crowd environments with socially acceptable standards remains the key problem to be solved for the development of mobile robots. Recent work has shown the effectiveness of deep reinforcement learning in addressing crowd navigation, but the learning becomes progressively less effective as the speed of pedestrians increases. To improve the effectiveness of deep reinforcement learning, we redesigned the reward function by introducing the penalty term of relative speed in the reward function. The newly designed reward function is tested on three mainstream deep reinforcement learning algorithms: deep reinforcement learning collision avoidance (CADRL), deep learning based long and short-term memory (LSTM RL), and reinforcement learning based on socialist riselection (SARL). The results of the experiments show that our model navigates in a safer way, outperforming the current model in key metrics such as success rate, collision rate, and hazard frequency.