HMPO: Human Motion Prediction in Occluded Environments for Safe Motion\n Planning

2020/05/30 by Jae Sung Park, Dinesh Manocha, Park, Jae Sung +1
Computer Science · Engineering · #Human Pose and Action Recognition #Autonomous Vehicle Technology and Safety #Anomaly Detection Techniques and Applications

paper · pdf · doi:10.48550/arxiv.2006.00424

Abstract

We present a novel approach to generate collision-free trajectories for a\nrobot operating in close proximity with a human obstacle in an occluded\nenvironment. The self-occlusions of the robot can significantly reduce the\naccuracy of human motion prediction, and we present a novel deep learning-based\nprediction algorithm. Our formulation uses CNNs and LSTMs and we augment\nhuman-action datasets with synthetically generated occlusion information for\ntraining. We also present an occlusion-aware planner that uses our motion\nprediction algorithm to compute collision-free trajectories. We highlight\nperformance of the overall approach (HMPO) in complex scenarios and observe\nupto 68% performance improvement in motion prediction accuracy, and 38%\nimprovement in terms of error distance between the ground-truth and the\npredicted human joint positions.\n

Related

• Occlusion aware obstacle prediction using people as sensors
• I-Planner: Intention-Aware Motion Planning Using Learning Based Human Motion Prediction
• Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments
• OA-MPC: Occlusion-Aware MPC for Guaranteed Safe Robot Navigation with Unseen Dynamic Obstacles
• Digital-Twin Evaluation for Proactive Human-Robot Collision Avoidance via Prediction-Guided A-RRT*