Journal
IEEE TRANSACTIONS ON ROBOTICS
Volume 36, Issue 3, Pages 582-596Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2019.2959445
Keywords
Task analysis; Haptic interfaces; Visualization; Robot sensing systems; Solid modeling; Reinforcement learning; Deep learning in robotics and automation; perception for grasping and manipulation; sensor fusion; sensor-based control
Categories
Funding
- D.com American Technologies Corporation (JD) under the SAIL-JD AI Research Initiative
- Toyota Research Institute (TRI)
Ask authors/readers for more resources
Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. It is nontrivial to manually design a robot controller that combines these modalities, which have very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to train directly on real robots due to sample complexity. In this article, we use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our policy learning. Evaluating our method on a peg insertion task, we show that it generalizes over varying geometries, configurations, and clearances, while being robust to external perturbations. We also systematically study different self-supervised learning objectives and representation learning architectures. Results are presented in simulation and on a physical robot.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available