Sym2Real: Symbolic Dynamics with Residual Learning for Data-Efficient Adaptive Control

Abstract-- We present Sym2Real, a fully data-driven framework that provides a principled way to train low-level adaptive controllers in a highly data-efficient manner . Using only about 10 trajectories, we achieve robust control of both a quadrotor and a racecar in the real world, without expert knowledge or simulation tuning. Our approach achieves this data efficiency by bringing symbolic regression to real-world robotics by addressing key challenges that prevent its direct application, including noise sensitivity and model degradation that lead to unsafe control. Our key observation is that the underlying physics is often shared for a system no matter the internal or external changes. Hence, we strategically combine low-fidelity simulation data with targeted real-world residual learning. Through experimental validation on quadrotor and racecar platforms, we demonstrate consistent data-efficient adaptation across 6 out-of-distribution sim2sim scenarios and successful sim2real transfer across 5 real-world conditions. More information and videos can be found at http://generalroboticslab. com/Sym2Real. Once assembled, a robot must rapidly learn the low-level skills needed to move and act.