Kilohertz-Safe: A Scalable Framework for Constrained Dexterous Retargeting

2026-03-30

AI Summary

This work addresses the challenge of achieving kilohertz-rate real-time teleoperation for dexterous hands while respecting heterogeneous kinematic constraints and formal safety guarantees. The authors reformulate the nonlinear retargeting problem as a convex quadratic program in joint differential space, embedding linearized kinematic and obstacle-avoidance constraints directly into the system dynamics. By integrating control barrier functions, the approach provides rigorous safety assurances against self-collisions and interpenetration. For the first time, the method enables real-time retargeting at a 1 kHz control frequency with high computational efficiency and strict safety compliance, significantly improving numerical stability and scalability. Evaluated on the Wuji Hand platform, it achieves an average latency of 9.05 ms, with over 95% of frames satisfying safety criteria, outperforming state-of-the-art methods such as Dex-Retargeting and GeoRT.

Abstract

Dexterous hand teleoperation requires motion re-targeting methods that simultaneously achieve high-frequency real-time performance and enforcement of heterogeneous kinematic and safety constraints. Existing nonlinear optimization-based approaches often incur prohibitive computational cost, limiting their applicability to kilohertz-level control, while learning-based methods typically lack formal safety guarantees. This paper proposes a scalable motion retargeting framework that reformulates the nonlinear retargeting problem into a convex quadratic program in joint differential space. Heterogeneous constraints, including kinematic limits and collision avoidance, are incorporated through systematic linearization, resulting in improved computational efficiency and numerical stability. Control barrier functions are further integrated to provide formal safety guarantees during the retargeting process. The proposed framework is validated through simulations and hardware experiments on the Wuji Hand platform, outperforming state-of-the-art methods such as Dex-Retargeting and GeoRT. The framework achieves high-frequency operation with an average latency of 9.05 ms, while over 95% of retargeted frames satisfy the safety criteria, effectively mitigating self-collision and penetration during complex manipulation tasks.

Problem

• dexterous teleoperation
• motion retargeting
• safety constraints
• real-time control
• kinematic constraints

Innovation

• convex quadratic programming
• control barrier functions
• dexterous hand retargeting
• real-time teleoperation
• constraint linearization