LOPAL: Local Performance-Aware Active Learning from Imperfect Demonstrations

2026-06-15

AI Summary

This work addresses the performance limitations of learning robotic skills from human demonstrations that are inconsistent in quality and locally suboptimal. To overcome this challenge, the authors propose an active learning approach that integrates local performance evaluation with shared autonomy. The method uniquely incorporates local demonstration quality into the learning process by jointly encoding trajectories and their associated local quality scores using a Gaussian Mixture Model (GMM). In regions identified as low-quality, the system proactively requests user corrections, while leveraging high-quality segments to synthesize trajectories that surpass the original demonstrations. Evaluated on a real-world pipe inspection task, the approach achieves up to a 27.31% improvement in task performance and substantially reduces the human effort required for providing demonstrations.

Abstract

Learning from Demonstration (LfD) enables intuitive robot skill acquisition by allowing robots to learn directly from human task demonstrations. However, current methods often fail to address the fact that due to suboptimal and inconsistent human behavior, the quality of the demonstration can vary within each demonstration. Therefore, we introduce LOPAL (LOcal Performance-aware Active Learning), an active learning approach that leverages this local demonstration quality information. Our approach consists of two synergistic components. First, a local performance-driven LfD method uses a Gaussian Mixture Model (GMM) to encode both the demonstrated trajectories and their associated local quality assessments. This enables the generation of trajectories that outperform the imperfect demonstrations by utilizing complementary local data of high performance. Second, active data acquisition allows to improve beyond the imperfect demonstrations by collecting additional informative samples. In areas missing good data, the user is actively requested to provide corrections through a shared autonomy (SA) mechanism, while the robot autonomously executes the learned behavior. The efficacy of LOPAL was validated in both a simulation and a real-world experiment. The results from a real-world pipe inspection task showed that the proposed approach can achieve up to 27.31 % improvement in task performance while also reducing the effort required to collect the demonstrations.

Problem

• Learning from Demonstration
• Imperfect Demonstrations
• Local Performance
• Active Learning
• Robot Skill Acquisition

Innovation

• Local Performance-aware Learning
• Active Learning
• Learning from Demonstration
• Gaussian Mixture Model
• Shared Autonomy