Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications

Sim-to-real transfer remains a significant challenge in robotics due to the discrepancies between simulated and real-world dynamics. Traditional methods like Domain Randomization often fail to capture fine-grained dynamics, limiting their effectiveness for precise control tasks. In this work, we propose a novel approach that dynamically adjusts simulation environment parameters online using in-context learning. By leveraging past interaction histories as context, our method adapts the simulation environment dynamics to match real-world dynamics without requiring gradient updates, resulting in faster and more accurate alignment between simulated and real-world performance. We validate our approach across two tasks: object scooping and table air hockey. In the sim-to-sim evaluations, our method significantly outperforms the baselines on environment parameter estimation by 80% and 42% in the object scooping and table air hockey setups, respectively. Furthermore, our method achieves at least 70% success rate in sim-to-real transfer on object scooping across three different objects. By incorporating historical interaction data, our approach delivers efficient and smooth system identification, advancing the deployment of robots in dynamic real-world scenarios.

I. Introduction

Learning-based methods like deep Reinforcement Learning (RL) allow robots to tackle complex tasks in areas such as object manipulation [1], [2] and locomotion for quadrupedal robots [3], [4] and humanoids [5]. However, RL's high sample complexity and risks of unsafe exploration [6], [7], [8] make it necessary to train policies in simulations and then deploy in the real world. A key challenge is the sim-to-real gap, caused by discrepancies between simulated and real-world dynamics [9], [10], which can lead to catastrophic failures during deployment.