Autonomous obstacle avoidance for mobile robots based on deep reinforcement learning and social force model
Li Heng,Liu Qinchen,Ma Qichao
(School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China)
Abstract: Deep reinforcement learning has been widely applied in the field of mobile robot autonomous obstacle avoidance Its basic principle is to simulate continuous trialanderror in the environment and improve the robot’s obstacle avoidance performance by combining reward mechanisms However, the training efficiency of the network varies significantly depending on the task scene, and in crowded scenes, the robot’s behavior may cause interference with humans To address the problems of low training efficiency and robots behaving inappropriately, this paper proposes a selfobstacle avoidance strategy that incorporates the social force model into deep reinforcement learning The strategy firstly considers the future trajectory of humans in the reward function to ensure that the robot understands human intentions and avoids entering the human comfort zone Secondly, during the training process, a priori traditional controller model is introduced and a probabilitybased switching method is designed to randomly switch controller outputs to improve the robot’s exploration efficiency The experimental results show that the proposed method can increase the safety distance between the robot and humans while achieving smooth navigation.
Key words : eep reinforcement learning; social force model; autonomous obstacle avoidance