Collision detection in legged locomotion using supervised learning

Abstract— We propose a fast approach for detecting collisionfree swing-foot trajectories for legged locomotion over extreme terrains. Instead of simulating the swing trajectories and checking for collisions along them, our approach uses machine learning techniques to predict whether a swing trajectory is collision-free. Using a set of local terrain features, we apply supervised learning to train a classifier to predict collisions. Both in simulation and on a real quadruped platform, our results show that our classifiers can improve the accuracy of collision detection compared to a real-time geometric approach without significantly increasing the computation time.

• Type: Conference
• Year: 2007
• Where: IROS
• Authors: Finale Doshi, Emma Brunskill, Alexander C. Shkolnik, Thomas Kollar, Khashayar Rohanimanesh, Russ Tedrake, Nicholas Roy
• Keywords: Approach Uses Machine, Collisionfree Swing-foot Trajectories, IROS 2007, Robotics, Swing Trajectories