Active Extrinsic Contact Sensing: Application to General Peg-in-Hole Insertion

We propose a method that actively estimates the location of contact between a grasped rigid object and its environment, and uses this as input to a peg-in-hole insertion policy. An estimation model and an active tactile feedback controller work collaboratively to get an accurate estimate of the external contacts. The controller helps the estimation model get a better estimate by regulating a consistent contact mode. The better estimation makes it easier for the controller to regulate the contact. To utilize this contact estimate, we train an object-agnostic insertion policy that learns to make use of the series of contact estimates to guide the insertion. In contrast with previous works that learn a policy directly from tactile signals, since this policy is in contact configuration space, can be learned directly in simulation. Lastly, we demonstrate and evaluate the active extrinsic contact line estimation and the trained insertion policy together in a real experiment. We show that the proposed method inserts various-shaped test objects with higher success rates and fewer insertion attempts than previous work with end-to-end approaches. See supplementary video and results at this https URL