Proprioceptive Robot Collision Detection through Gaussian Process Regression
This work addresses collision detection for robots in scenarios with minimal sensing, offering a domain-specific improvement over existing methods.
The paper tackles the problem of detecting robot collisions using only proprioceptive data (currents and joint configurations) by extending Gaussian Process regression with a richer input set and custom kernel. Tests on a UR10 robot demonstrate the algorithm's effectiveness in collision detection.
This paper proposes a proprioceptive collision detection algorithm based on Gaussian Regression. Compared to sensor-based collision detection and other proprioceptive algorithms, the proposed approach has minimal sensing requirements, since only the currents and the joint configurations are needed. The algorithm extends the standard Gaussian Process models adopted in learning the robot inverse dynamics, using a more rich set of input locations and an ad-hoc kernel structure to model the complex and non-linear behaviors due to frictions in quasi-static configurations. Tests performed on a Universal Robots UR10 show the effectiveness of the proposed algorithm to detect when a collision has occurred.