Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard

2020/08/06 by Alex Church, John Lloyd, Church, Alex +6 · 2 citations
Computer Science · Engineering · Neuroscience · #Advanced Sensor and Energy Harvesting Materials #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotics (cs.RO) #Tactile and Sensory Interactions #cs.AI #cs.RO

paper · pdf · doi:10.48550/arxiv.2008.02646

Accepted in RAL and IROS 2020

arxiv created 2020/08/06 · openalex publication_date 2020/08/06 · arxiv updated 2020/08/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Artificial touch would seem well-suited for Reinforcement Learning (RL), since both paradigms rely on interaction with an environment. Here we propose a new environment and set of tasks to encourage development of tactile reinforcement learning: learning to type on a braille keyboard. Four tasks are proposed, progressing in difficulty from arrow to alphabet keys and from discrete to continuous actions. A simulated counterpart is also constructed by sampling tactile data from the physical environment. Using state-of-the-art deep RL algorithms, we show that all of these tasks can be successfully learnt in simulation, and 3 out of 4 tasks can be learned on the real robot. A lack of sample efficiency currently makes the continuous alphabet task impractical on the robot. To the best of our knowledge, this work presents the first demonstration of successfully training deep RL agents in the real world using observations that exclusively consist of tactile images. To aid future research utilising this environment, the code for this project has been released along with designs of the braille keycaps for 3D printing and a guide for recreating the experiments. A brief video summary is also available at https://youtu.be/eNylCA2uE_E.

Citations

• Playing Atari with Deep Reinforcement Learning
• Dueling Network Architectures for Deep Reinforcement Learning
• DeepMind Control Suite
• Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
• Benchmarking Reinforcement Learning Algorithms on Real-World Robots
• Soft Actor-Critic Algorithms and Applications
• Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Solving Rubik's Cube with a Robot Hand
• Learning dexterous in-hand manipulation

Cited by

• FlexiCup: Wireless Multimodal Suction Cup with Dual-Zone Vision-Tactile Sensing
• NeuralTouch: Neural Descriptors for Precise Sim-to-Real Tactile Robot Control

Related

• Enhancing Tactile-based Reinforcement Learning for Robotic Control
• Tactile Gym 2.0: Sim-to-real Deep Reinforcement Learning for Comparing Low-cost High-Resolution Robot Touch
• Learning Tactile Insertion in the Real World
• Learning In-Hand Translation Using Tactile Skin With Shear and Normal Force Sensing
• MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning