M. Howard, D.J. Braun, and S. Vijayakumar, Transferring human impedance behavior to heterogeneous variable impedance actuators, IEEE Transactions on Robotics, vol. 29, no. 4, pp. 847-862, 2013.
This paper investigates how human impedance modulation strategies can be transferred to robots equipped with variable impedance actuators (VIAs). The study categorizes three approaches—direct transfer, feature-based transfer, and inverse optimal transfer—and evaluates their suitability across different robotic systems. It introduces a constraint-based method and an apprenticeship learning framework to enable generalizable transfer independent of the robot’s mechanical design. The methods are validated through simulations and experiments transferring electromyographic data from humans to robotic devices with passive compliance.
Why it matters: Teaching robots to replicate human impedance behavior is critical for safe and efficient human–robot interaction. This work provides general frameworks for transferring human control strategies to heterogeneous robotic systems, laying the groundwork for adaptable and human-inspired robot control.