Sim2Real Manipulation on Unknown Objects with Tactile-based Reinforcement Learning

Using tactile sensors for manipulation remains one of the most challenging problems in robotics. At the heart of these challenges is generalization: How can we train a tactile-based policy that can manipulate unseen and diverse objects? In this paper, we propose to perform Reinforcement Learning with only visual tactile sensing inputs on diverse objects in a physical simulator. By training with diverse objects in simulation, it enables the policy to generalize to unseen objects. However, leveraging simulation introduces the Sim2Real transfer problem. To mitigate this problem, we study different tactile representations and evaluate how each affects real-robot manipulation results after transfer. We conduct our experiments on diverse real-world objects and show significant improvements over baselines. Our project page is available at https://tactilerl.github.io/.

Authors

• Entong Su
• Chengzhe Jia
• Yuzhe Qin
• Wenxuan Zhou 0001
• Annabella Macaluso
• Binghao Huang
• Xiaolong Wang 0004

Keywords

• Training
• Heart
• Visualization
• Tactile sensors
• Reinforcement learning
• Sensors
• Task analysis
• Tactile Sensor
• Variety Of Objects
• Real-world Objects
• Problem In Robotics
• Simulated Object
• Unseen Objects
• Visual Feedback
• Angle Difference
• Elastography
• Low Success Rate
• Reward Function
• Real-world Experiments
• Deep Reinforcement Learning
• Observation Space
• Image Augmentation
• Real Robot
• Tactile Information
• Angle Estimation
• Training Policy
• Object Pose
• Proximal Policy Optimization
• Reinforcement Learning Policy
• Expert Demonstrations
• Tactile Input
• Object Geometry
• RGB Images