Amazon and University of Michigan give robots a sense of touch

Summary

Robotic manipulation in contact-rich settings requires accurate tactile force perception, but existing physics simulators either run too slowly for reinforcement learning or oversimplify shear forces. HydroShear addresses this tactile reality gap by incorporating path-dependent force tracking into hydroelastic contact models. By remembering object motion history across soft elastomer sensors, the GPU-parallelizable simulator computes full 3-D contact deformations, friction, and slipping dynamics. Reinforcement learning policies trained entirely in HydroShear transferred directly to a real Franka robot equipped with GelSight Mini sensors without fine-tuning. Across four challenging manipulation tasks, HydroShear achieved a 93 percent average success rate, outperforming baseline models TacSL and FOTS.

Takeaways

1. 1

   HydroShear enables zero-shot sim-to-real transfer of reinforcement learning policies for contact-rich robotic tasks without real-world fine-tuning.

2. 2

   Across peg insertion, bin packing, book shelving, and drawer pulling, HydroShear achieved a 93% success rate, outperforming TacSL at 34% and FOTS at 58% to 61%.

3. 3

   HydroShear models full 3-D motion and tracks individual surface contact points over time to compute realistic force fields that account for friction and slipping.