Towards Safe and Efficient Last-Mile Delivery: A Multi-Modal Socially Aware Navigation Framework for Autonomous Robots on Pedestrian-Crowded Sidewalks

Last-mile delivery robot has been attracted increasing attention from industry and comes into our daily life recently. However, how to safely and effectively navigate among crowded pedestrians is still an open problem. It requires the robot capable of analysing where it can traverse, understanding the intentions of surrounding pedestrians, planning the trajectory with social awareness, etc. In this paper, we have successfully completed a systematic implementation for navigation of delivery robot in pedestrian crowded environments. First, we introduced the Nanyang Sidewalk dataset, designed explicitly for class segmentation tasks on sidewalks. Second, a multi-modal 3D detection and motion prediction integrated with the social force model has been introduced to perceive the intention of pedestrians. Then, a socially aware motion planner for the delivery robot is demonstrated by following pedestrian etiquette. Extensive experiments have been conducted to verify and evaluate the performance of the proposed algorithm.