Tactile sensing improves robot learning for precise manipulation tasks
TaRL: Learning General and Physical Rewards from Tactile Demonstrations
Robotics
Summary
Robots often struggle to learn tasks that involve careful contact and gripping because it's hard to design clear goals for them to follow. The authors developed a method that teaches robots by learning rewards from touch-based demonstrations instead of just visuals. This approach helps robots understand how well they are gripping or applying force, improving learning speed and success. Tests show that combining touch and vision helps robots perform better on tasks like threading nuts and picking up objects.
What this means in practice
- •For robot control engineers: Improve robot grasping and force control by using tactile-based rewards derived from successful and failed demonstrations.
- •For industrial automation teams: Enhance robot assembly line tasks by integrating tactile reward learning to raise success rates on contact-sensitive manipulation.
Authors
Po-Yi Wu, Dao-Jan Chang, Shang-Ya Hsiao, Hong-Ming Chen, Yu-Cheng Su, Tsung-Wei Ke
Abstract
Contact-rich manipulation requires robots to sequence precise contacts, maintain stable grasps, and apply directed forces. Reinforcement learning (RL) can acquire such behaviors automatically, but its performance hinges on reward design: sparse rewards reduce the learning efficiency, while dense rewards are hard to specify. Visual reward learning addresses this by inferring rewards from action-free demonstrations. Because it conditions only on visual observations, it fails to capture rewards beyond visual goals. We propose Tactile Reward Learning (TaRL), a framework that learns rewards from tactile demonstrations. TaRL takes a sequence of tactile deformation maps as input, and regresses task-completion progress from both successful and failed demonstrations. Because TaRL captures local robot-object interaction, it provides informative feedback to learn firm grasps and correctly directed forces; meanwhile, it is robust to changes in scene layout such as object position. We evaluate TaRL on four manipulation tasks in simulation and two in the real world. Used as a shaping reward, it substantially improves both sample efficiency and final success rate, raising success on Nut threading from 34% to 56% in simulation and on cube pickup from 37% to 97% in the real world. Combining tactile with visual rewards improves performance further. TaRL also generalizes across object instances: trained on box placement and directly deployed to can placement, it significantly improves policy learning on the new task. Project page is available at https://embodiedai-ntu.github.io/tarl.