Collision detection for cobots: A new effective algorithm

Collaborative robots (Cobots) can interact with humans, simultaneously promoting the advantages of both humans and robots to increase work efficiency. Cobots operate friendly and interact with humans because they are programmed to detect collisions safely. Therefore, the requirement to accurately and quickly detect collisions of cobot arms is a topic that attracts the attention of many researchers. This paper proposes an approach applying a supervised machine learning technique, SVR (Support Vector Regression), to detect collisions with CURA6 robot arms. A real-world experiment (the Intema dataset) was used to validate the proposed method.