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

2025-05-07

AI Summary

To address the challenges of force–position coordination, simulation-to-reality discrepancies, and poor execution robustness in multi-step contact-rich manipulation tasks, this paper proposes an unsupervised hierarchical learning framework tailored for real robotic systems. Methodologically: (1) it introduces an unsupervised task segmentation algorithm based on intent recognition and temporal feature clustering; (2) it constructs a haptics-driven skill representation space enabling unsupervised anomaly detection and online error recovery; and (3) it supports incremental behavior learning and real-time monitoring. The key contributions are: (i) the first joint learning of high- and low-level task representations without human annotations or simulation priors; and (ii) significantly reduced data and computational requirements—achieving state-of-the-art performance in both task segmentation and anomaly detection on two physical robot platforms.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Unsupervised & Self-Supervised Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• Learning robot task coordination and error recovery from demonstrations
• Unsupervised task segmentation for skill inference in manipulation tasks
• Anomaly detection to identify deviations in task execution

Innovation

• Unsupervised task segmentation combining intention recognition
• Novel unsupervised anomaly detection for skill deviations
• Incremental learning framework for task decisions and behaviors