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

TL;DR

This paper introduces HMPO, a deep learning-based system that improves human motion prediction and collision-free robot planning in occluded environments, enhancing safety and accuracy in human-robot interaction.

Contribution

The paper presents a novel occlusion-aware prediction algorithm using CNNs and LSTMs, augmented with synthetic occlusion data, and integrates it into a motion planner for safer robot navigation.

Findings

Up to 68% improvement in motion prediction accuracy

38% reduction in error distance between predicted and actual human joints

Effective in complex, occlusion-rich scenarios

Abstract

We present a novel approach to generate collision-free 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 learning-based 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.