Manipulation by Feel: Touch-Based Control with Deep Predictive Models
arXiv:1903.04128
Abstract
Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to effectively leverage tactile sensing as well as accurate physics models of contacts and forces remain largely elusive, and it is unclear how to even specify a desired behavior in terms of tactile percepts. In this paper, we take a step towards addressing these issues by combining high-resolution tactile sensing with data-driven modeling using deep neural network dynamics models. We propose deep tactile MPC, a framework for learning to perform tactile servoing from raw tactile sensor inputs, without manual supervision. We show that this method enables a robot equipped with a GelSight-style tactile sensor to manipulate a ball, analog stick, and 20-sided die, learning from unsupervised autonomous interaction and then using the learned tactile predictive model to reposition each object to user-specified configurations, indicated by a goal tactile reading. Videos, visualizations and the code are available here: https://sites.google.com/view/deeptactilempc
Accepted to ICRA 2019
References in corpus (3)
Cited by in corpus (8)
- Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
- Learning efficient haptic shape exploration with a rigid tactile sensor array
- RoboNet: Large-Scale Multi-Robot Learning
- Cable Manipulation with a Tactile-Reactive Gripper
- Learning Dense Rewards for Contact-Rich Manipulation Tasks
- Elastic Interaction of Particles for Robotic Tactile Simulation
- Elastic Tactile Simulation Towards Tactile-Visual Perception
- Generation of GelSight Tactile Images for Sim2Real Learning