TIAGo RL: Simulated Reinforcement Learning Environments with Tactile Data for Mobile Robots
This work provides a tool for researchers in robotics to study transfer learning of deep reinforcement learning policies with tactile data, but it is incremental as it builds on existing methods for simulation environments.
The authors tackled the challenge of modeling robotic behavior with tactile data by developing open-source reinforcement learning environments for the TIAGo robot, which simulate realistic tactile sensor measurements and show preliminary training results where a learned policy performs comparably to a classical PI controller.
Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes increasingly difficult. Deep Reinforcement Learning (DRL) produced promising results for learning complex behavior in various domains, including tactile-based manipulation in robotics. In this work, we present our open-source reinforcement learning environments for the TIAGo service robot. They produce tactile sensor measurements that resemble those of a real sensorised gripper for TIAGo, encouraging research in transfer learning of DRL policies. Lastly, we show preliminary training results of a learned force control policy and compare it to a classical PI controller.