Unified Learning of Temporal Task Structure and Action Timing for Bimanual Robot Manipulation

TL;DR

This paper introduces a unified approach for learning and integrating symbolic and subsymbolic temporal constraints from human demonstrations to generate precise, executable plans for bimanual robot manipulation.

Contribution

It presents a novel method combining Gaussian Mixture Models, a DPLL-based symbolic reasoning, and an optimization system to learn and plan complex bimanual tasks.

Findings

Generated plans closely match human demonstrations

Outperformed baseline methods in temporal accuracy

Effectively integrated high-level and low-level task constraints

Abstract

Temporal task structure is fundamental for bimanual manipulation: a robot must not only know that one action precedes or overlaps another, but also when each action should occur and how long it should take. While symbolic temporal relations enable high-level reasoning about task structure and alternative execution sequences, concrete timing parameters are equally essential for coordinating two hands at the execution level. Existing approaches address these two levels in isolation, leaving a gap between high-level task planning and low-level movement synchronization. This work presents an approach for learning both symbolic and subsymbolic temporal task constraints from human demonstrations and deriving executable, temporally parametrized plans for bimanual manipulation. Our contributions are (i) a 3-dimensional representation of timings between two actions with methods based on multivariate Gaussian Mixture Models to represent temporal relationships between actions on a subsymbolic level, (ii) a method based on the Davis-Putnam-Logemann-Loveland (DPLL) algorithm that finds and ranks all contradiction-free assignments of Allen relations to action pairs, representing different modes of a task, and (iii) an optimization-based planning system that combines the identified symbolic and subsymbolic temporal task constraints to derive temporally parametrized plans for robot execution. We evaluate our approach on several datasets, demonstrating that our method generates temporally parametrized plans closer to human demonstrations than the most characteristic demonstration baseline.