SPSD: Semantics and Deep Reinforcement Learning Based Motion Planning for Supermarket Robot.

Robot motion planning is an important part of the un-manned supermarket. The challenges of motion planning in supermarkets lie in the diversity of the supermarket environment, the complexity of ob-stacle movement, the vastness of the search space. This paper proposes an adaptive Search and Path planning method based on the Semantic informa-tion and Deep reinforcement learning (SPSD), which effectively improves the autonomous decision-making ability of supermarket robots. Firstly, based on the backbone of deep reinforcement learning (DRL), supermarket robots process real-time information from multi-modality sensors to real-ize high-speed and collision-free motion planning. Meanwhile, in order to solve the problem caused by the uncertainty of the reward in the deep rein-forcement learning, common spatial semantic relationships between land-marks and target objects are exploited to define reward function. Finally, dynamics randomization is introduced to improve the generalization per-formance of the algorithm in the training. The experimental results show that the SPSD algorithm is excellent in the three indicators of generalization performance, training time and path planning length. Compared with other methods, the training time of SPSD is reduced by 27.42% at most, the path planning length is reduced by 21.08% at most, and the trained network of SPSD can be applied to unfamiliar scenes safely and efficiently. The results are motivating enough to consider the application of the proposed method in practical scenes. We have uploaded the video of the results of the exper-iment to https://www.youtube.com/watch?v=h1wLpm42NZk.