Computed torque control with variable gains through Gaussian process regression

Nicolas Torres Alberto, Michael Mistry, Freek Stulp

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In computed torque control, robot dynamics are predicted by dynamic models. This enables more compliant control, as the gains of the feedback term can be lowered, because the task of compensating for robot dynamics is delegated from the feedback to the feedforward term. Previous work has shown that Gaussian process regression is an effective method for learning computed torque control, by setting the feedforward torques to the mean of the Gaussian process. We extend this work by also exploiting the variance predicted by the Gaussian process, by lowering the gains if the variance is low. This enables an automatic adaptation of the gains to the uncertainty in the computed torque model, and leads to more compliant low-gain control as the robot learns more accurate models over time. On a simulated 7-DOF robot manipulator, we demonstrate how accurate tracking is achieved, despite the gains being lowered over time.
Original languageEnglish
Title of host publication14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, November 18-20, 2014
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Electronic)978-1-4799-7174-9
ISBN (Print)978-1-4799-7175-6
Publication statusPublished - 2014


Dive into the research topics of 'Computed torque control with variable gains through Gaussian process regression'. Together they form a unique fingerprint.

Cite this