Failure-Aware Bimanual Teleoperation via Conservative Value Guided Assistance
🤖 AI Summary
This work addresses the challenge of task failure prediction in high-precision bimanual teleoperation, where human operators struggle to anticipate failures due to partial observability and complex contact dynamics. The authors propose a conservative value-guided failure-aware shared autonomy framework that leverages offline heterogeneous teleoperation data—comprising both successful and failed demonstrations—to train a task feasibility model. During online execution, the system generates compliant force feedback to assist the operator while preserving their primary control authority. Notably, this is the first application of conservative value learning to teleoperation, enabling a risk-sensitive success scoring mechanism robust to distributional shifts and facilitating continuous failure avoidance without overriding user intent. Experimental results demonstrate that the approach significantly improves task success rates and reduces operator workload in contact-rich manipulation scenarios.
Application Category
📝 Abstract
Teleoperation of high-precision manipulation is con-strained by tight success tolerances and complex contact dy-namics, which make impending failures difficult for human operators to anticipate under partial observability. This paper proposes a value-guided, failure-aware framework for bimanual teleoperation that provides compliant haptic assistance while pre-serving continuous human authority. The framework is trained entirely from heterogeneous offline teleoperation data containing both successful and failed executions. Task feasibility is mod-eled as a conservative success score learned via Conservative Value Learning, yielding a risk-sensitive estimate that remains reliable under distribution shift. During online operation, the learned success score regulates the level of assistance, while a learned actor provides a corrective motion direction. Both are integrated through a joint-space impedance interface on the master side, yielding continuous guidance that steers the operator away from failure-prone actions without overriding intent. Experimental results on contact-rich manipulation tasks demonstrate improved task success rates and reduced operator workload compared to conventional teleoperation and shared-autonomy baselines, indicating that conservative value learning provides an effective mechanism for embedding failure awareness into bilateral teleoperation. Experimental videos are available at https://www.youtube.com/watch?v=XDTsvzEkDRE
Problem
Research questions and friction points this paper is trying to address.
bimanual teleoperation
failure awareness
partial observability
contact-rich manipulation
task success tolerance
Innovation
Methods, ideas, or system contributions that make the work stand out.
Conservative Value Learning
Failure-Aware Teleoperation
Bimanual Manipulation
Shared Autonomy
Haptic Assistance
🔎 Similar Papers
No similar papers found.
