HMPO: Human Motion Prediction in Occluded Environments for Safe Motion Planning
Jae Sung Park, Dinesh Manocha · 2020
We present a novel approach to generate collisionfree trajectories for a robot operating in close proximity with a human obstacle in an occluded environment.The self-occlusions of the robot can significantly reduce the accuracy of human motion prediction, and we present a novel deep learningbased prediction algorithm.Our formulation uses CNNs and LSTMs and we augment human-action datasets with synthetically generated occlusion information for training.We also present an occlusion-aware planner that uses our motion prediction algorithm to compute collision-free trajectories.We highlight performance of the overall approach (HMPO) in complex scenarios and observe upto 68% performance improvement in motion prediction accuracy, and 38% improvement in terms of error distance between the ground-truth and the predicted human joint positions.