Journal
IEEE ROBOTICS AND AUTOMATION LETTERS
Volume 4, Issue 2, Pages 1148-1155Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2019.2894216
Keywords
Deep learning in robotics and automation; visual-based navigation; model learning for control
Categories
Funding
- Shenzhen Science, Technology and Innovation Commission [JCYJ20160428154842603]
- BrainLinks-BrainTools cluster of excellence - DFG (German Research Foundation) [EXC 1086]
- Research Grant Council of Hong Kong SAR Government, China [11210017, 16212815, 21202816]
- National Natural Science Foundation of China [U1713211]
Ask authors/readers for more resources
In this letter, we deal with the reality gap from a novel perspective, targeting transferring deep reinforcement learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks. Instead of adopting the common solutions to the problem by increasing the visual fidelity of synthetic images output from simulators during the training phase, we seek to tackle the problem by translating the real-world image streams back to the synthetic domain during the deployment phase, to make the robot feel at home. We propose this as a lightweight, flexible, and efficient solution for visual control, as first, no extra transfer steps are required during the expensive training of DRL agents in simulation; second, the trained DRL agents will not be constrained to being deployable in only one specific real-world environment; and third, the policy training and the transfer operations are decoupled, and can be conducted in parallel. Besides this, we propose a simple yet effective shift loss that is agnostic to the downstream task, to constrain the consistency between subsequent frames which is important for consistent policy outputs. We validate the shift loss for artistic style transfer for videos and domain adaptation, and validate our visual control approach in indoor and outdoor robotics experiments.
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