Trajectory-based actuator identification via differentiable simulation

TL;DR

This paper introduces a differentiable simulation-based method for identifying accurate actuator models from encoder data alone, improving robot trajectory prediction and control.

Contribution

It presents a novel trajectory-matching approach that optimizes actuator parameters without torque sensors, supporting various model classes within a unified framework.

Findings

Achieves tighter trajectory alignment than baseline, reducing mean absolute position error from 14.20 mrad to 7.54 mrad.

Improves robot locomotion performance, increasing travel distance by 46%.

Reduces rotational deviation by 75% in real-robot experiments.

Abstract

Accurate actuation models are critical for bridging the gap between simulation and real robot behavior, yet obtaining high-fidelity actuator dynamics typically requires dedicated test stands and torque sensing. We present a trajectory-based actuator identification method that uses differentiable simulation to fit system-level actuator models from encoder motion alone. Identification is posed as a trajectory-matching problem: given commanded joint positions and measured joint angles and velocities, we optimize actuator and simulator parameters by backpropagating through the simulator, without torque sensors, current/voltage measurements, or access to embedded motor-control internals. The framework supports multiple model classes, ranging from compact structured parameterizations to neural actuator mappings, within a unified optimization pipeline. On held-out real-robot trajectories for a high-gear-ratio actuator with an embedded PD controller, the proposed torque-sensor-free identification achieves much tighter trajectory alignment than a supervised stand-trained baseline dominated by steady-state data, reducing mean absolute position error from 14.20 mrad to as low as 7.54 mrad (1.88 times). Finally, we demonstrate downstream impact for the same actuator class in a real-robot locomotion study: training policies with the refined actuator model increases travel distance by 46% and reduces rotational deviation by 75% relative to the baseline.