Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization
This work addresses the problem of efficient sim-to-real transfer for robotics locomotion, offering a simpler alternative to complex engineering methods, though it is incremental in nature.
The paper tackles the challenge of training robust locomotion policies for sim-to-real transfer by proposing a simple random force injection (RFI) method and its extension ERFI, which includes an episodic actuation offset. The results show that ERFI provides 53% improved performance over RFI and enables successful deployment on quadrupedal robots in outdoor environments.
Training deep reinforcement learning (DRL) locomotion policies often require massive amounts of data to converge to the desired behaviour. In this regard, simulators provide a cheap and abundant source. For successful sim-to-real transfer, exhaustively engineered approaches such as system identification, dynamics randomization, and domain adaptation are generally employed. As an alternative, we investigate a simple strategy of random force injection (RFI) to perturb system dynamics during training. We show that the application of random forces enables us to emulate dynamics randomization. This allows us to obtain locomotion policies that are robust to variations in system dynamics. We further extend RFI, referred to as extended random force injection (ERFI), by introducing an episodic actuation offset. We demonstrate that ERFI provides additional robustness for variations in system mass offering on average a 53% improved performance over RFI. We also show that ERFI is sufficient to perform a successful sim-to-real transfer on two different quadrupedal platforms, ANYmal C and Unitree A1, even for perceptive locomotion over uneven terrain in outdoor environments.