Learning for Control of Rolling μbots

Summary

Read the Paper: https://arxiv.org/abs/2212.00188

Download the code: https://github.com/SuhailSama/MR_RL

Micron-scale robots (μbots) have recently shown great promise for emerging medical applications, and accurate control of μbots is a critical next step to deploying them in real systems. In this work, we adapt the idea of an inverse nonlinear mismatch controller to compensate for the mismatch between the classic unicycle model of a rolling μbot and trajectory data collected during an experiment. We exploit the differential flatness property of the rolling $\mu$bot model to generate a mapping from the desired state trajectory to nominal control actions. Due to model mismatch and parameter estimation error, the nominal control actions will not exactly reproduce the desired state trajectory. We employ a Gaussian Process (GP) to learn the model mismatch as a function of the desired control actions, and correct the nominal control actions using a least-squares optimization. We demonstrate the performance of our online learning algorithm in simulation, and propose that the model mismatch makes some desired states unreachable. Finally, we validate our approach in an experiment and show that the error metrics are reduced by up to 40%.

Experiments