Robotic arm control improves tracking with stability aware learning
Stability-aware Residual Reinforcement Learning Framework for Robotic Manipulator Disturbance Compensation
Robotics
Summary
Robotic arms often struggle to move precisely when unexpected forces or friction affect them. This paper shows how combining a traditional control method with a smart learning part can help the robot quickly adjust to these disturbances. The learning system focuses only on what the traditional method misses, making the control more reliable. The researchers also made sure the robot's adjustments stay safe and stable. Tests showed the new approach significantly reduces position errors, even when the robot faces new disturbances it hasn't seen before.
What this means in practice
- •For industrial robot operators: Improve robotic arm accuracy during unpredictable disturbances to maintain production quality.
- •For robotics control engineers: Design robotic controllers that adapt to unknown forces while guaranteeing safe, stable operation.
Authors
Jihong Kim, Joonhyuk Kwon, Hwa Soo Kim, TaeWon Seo, Hyung-Tae Seo
Abstract
Although conventional controllers and disturbance observers (DOBs) are the standard for precision tracking in manipulators, they suffer from parameter uncertainty, nonlinear friction, and compound disturbances. This study proposes a residual reinforcement learning DOB framework that pairs an analytical observer with an RL policy. The deterministic baseline operates within a reliable region, whereas the RL policy explicitly targets the residuals that the model cannot capture. To make this compensation disturbance-aware, an estimator network aligns the observation history with a privileged disturbance context, organizing the latent space by disturbance regime and enabling rapid adaptation across disturbance transitions. To guarantee stability, we derived and enforced a state-dependent action bound on the RL policy from an input-to-state stability (ISS) analysis such that the closed loop provably confines the tracking error to a certified envelope for arbitrary policy outputs. Experiments on a 6-DOF manipulator demonstrated consistent improvements in disturbance estimation and tracking, including a 27.8% tracking-error reduction on real hardware under zero-shot sim-to-real transfer and a 38.0% reduction under a base-vibration disturbance that was not observed during training.