Robot Learning from Randomized Simulations: A Review
It addresses the problem of expensive real-world data collection for robot learning by summarizing methods to improve simulation-based training, though it is an incremental review paper.
This paper reviews sim-to-real research in robotics, focusing on domain randomization as a technique to overcome the reality gap between simulation and reality when learning robot control policies.
The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the 'reality gap'. We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named 'domain randomization' which is a method for learning from randomized simulations.