Hierarchical Human-Motion Prediction and Logic-Geometric Programming for Minimal Interference Human-Robot Tasks

TL;DR

This paper presents a hierarchical human motion prediction integrated with a dynamic logic-geometric programming approach to improve human-robot task coordination, with periodic replanning to adapt to real human behavior.

Contribution

It introduces a novel combination of hierarchical motion prediction with a dynamic TAMP algorithm for better human-robot collaboration.

Findings

Effective human motion prediction using IRL and RNN.

Dynamic LGP improves task planning adaptability.

Validated on MoGaze dataset.

Abstract

In this paper, we tackle the problem of human-robot coordination in sequences of manipulation tasks. Our approach integrates hierarchical human motion prediction with Task and Motion Planning (TAMP). We first devise a hierarchical motion prediction approach by combining Inverse Reinforcement Learning and short-term motion prediction using a Recurrent Neural Network. In a second step, we propose a dynamic version of the TAMP algorithm Logic-Geometric Programming (LGP). Our version of Dynamic LGP, replans periodically to handle the mismatch between the human motion prediction and the actual human behavior. We assess the efficacy of the approach by training the prediction algorithms and testing the framework on the publicly available MoGaze dataset.