Learning-Based Real-Time Detection of Robot Collisions Without Joint Torque Sensors

• Published in: IEEE robotics and automation letters Vol. 6; no. 1; p. 1
• Main Authors: Park, Kyu Min, Kim, Jihwan, Park, Jinhyuk, Park, Frank C.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Actuators; AI-Based Methods; Algorithms; Artificial neural networks; Collision avoidance; Friction; Learning; Physical Human-Robot Interaction; Robot dynamics; Robot kinematics; Robot sensing systems; Robots; Support vector machines; Torque; Torque sensors (robotics)
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2020.3033269

Robots operating in close proximity to humans require fast and reliable detection of collisions, which can range from sharp impacts (hard collisions) to pulling-pushing-catching motions (soft collisions). Because joint torque sensors can be costly, the external joint torques caused by collisions are typically estimated from motor current measurements at the joint actuators. For reliable detection, however, these methods require accurate models of dissipative friction at the joints. In this paper we design two learning-based detection methods - a support vector machine, and a convolutional neural network - that require only motor current measurements together with a robot dynamics model and a momentum observer; no friction model is needed, and manual tuning of collision detection thresholds for each of the joints can be avoided. Extensive experiments with a six-dof industrial collaborative robot trained with stacks of four- and six-dimensional time series data validate our algorithms for a wide range of hard and soft collisions.