Hierarchical Task Decomposition for Execution Monitoring and Error Recovery: Understanding the Rationale Behind Task Demonstrations

TL;DR

This paper introduces an unsupervised learning framework for robotic task segmentation and anomaly detection, enabling robots to learn, monitor, and recover from errors in complex multi-step manipulation tasks with minimal training data.

Contribution

It presents a novel unsupervised approach combining intention recognition, feature clustering, and anomaly detection for improved task understanding and error recovery in robotics.

Findings

Outperforms state-of-the-art methods in force-based tasks

Reduces training data and computational requirements

Successfully learns complex in-contact behaviors

Abstract

Multi-step manipulation tasks where robots interact with their environment and must apply process forces based on the perceived situation remain challenging to learn and prone to execution errors. Accurately simulating these tasks is also difficult. Hence, it is crucial for robust task performance to learn how to coordinate end-effector pose and applied force, monitor execution, and react to deviations. To address these challenges, we propose a learning approach that directly infers both low- and high-level task representations from user demonstrations on the real system. We developed an unsupervised task segmentation algorithm that combines intention recognition and feature clustering to infer the skills of a task. We leverage the inferred characteristic features of each skill in a novel unsupervised anomaly detection approach to identify deviations from the intended task execution. Together, these components form a comprehensive framework capable of incrementally learning task decisions and new behaviors as new situations arise. Compared to state-of-the-art learning techniques, our approach significantly reduces the required amount of training data and computational complexity while efficiently learning complex in-contact behaviors and recovery strategies. Our proposed task segmentation and anomaly detection approaches outperform state-of-the-art methods on force-based tasks evaluated on two different robotic systems.