Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks
arXiv:2206.06282 · doi:10.1109/IROS47612.2022.9981951
Abstract
Randomization is currently a widely used approach in Sim2Real transfer for data-driven learning algorithms in robotics. Still, most Sim2Real studies report results for a specific randomization technique and often on a highly customized robotic system, making it difficult to evaluate different randomization approaches systematically. To address this problem, we define an easy-to-reproduce experimental setup for a robotic reach-and-balance manipulator task, which can serve as a benchmark for comparison. We compare four randomization strategies with three randomized parameters both in simulation and on a real robot. Our results show that more randomization helps in Sim2Real transfer, yet it can also harm the ability of the algorithm to find a good policy in simulation. Fully randomized simulations and fine-tuning show differentiated results and translate better to the real robot than the other approaches tested.
arXiv commentAccepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022
References in corpus (7)
- Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
- Solving Rubik's Cube with a Robot Hand
- Emergent Tool Use From Multi-Agent Autocurricula
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
- Towards MRI-Based Autonomous Robotic US Acquisitions: A First Feasibility Study
- Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?
- 3D Simulation for Robot Arm Control with Deep Q-Learning