CLASH:通过增强的仿真到现实混合化进行碰撞学习以弥合现实差距
CLASH: Collision Learning via Augmented Sim-to-real Hybridization to Bridge the Reality Gap
AI总结:
CLASH通过增强的仿真到现实混合化方法,有效提升碰撞预测精度并减少仿真计算时间,增强机器人策略在现实中的鲁棒性。
摘要:
仿真到现实的差距,尤其是在碰撞等接触丰富的动力学建模不准确方面,仍然是部署在仿真中训练的机器人策略的主要障碍。传统物理引擎往往以计算速度为代价换取准确性,导致差异,从而防止直接的策略转移。为了解决这个问题,我们引入了通过增强的仿真到现实混合化进行碰撞学习(CLASH),这是一种数据高效的框架,它学习了一个参数条件的冲击碰撞替代模型,并将其作为插件模块整合到标准模拟器中。CLASH首先从不完美的模拟器(MuJoCo)中提炼出基础模型,使用大规模的模拟碰撞来捕捉可重用的物理先验知识。在仅有少量现实碰撞(例如10个样本)的情况下,它然后(i)通过基于梯度的方法识别关键接触参数,并(ii)应用小步长、提前停止的微调来纠正残余的仿真到现实的不匹配,同时避免过拟合。所得到的混合模拟器不仅实现了更高的碰撞后预测准确性,而且将碰撞密集的CMA-ES搜索的实时时钟时间比MuJoCo减少了42-48%。我们证明了使用混合模拟器获得的策略在现实世界中转移更加稳健,强化学习在连续推动任务中的成功率翻倍,并且显著提高了基于模型的控制任务性能。
英文摘要:
The sim-to-real gap, particularly in the inaccurate modeling of contact-rich dynamics like collisions, remains a primary obstacle to deploying robot policies trained in simulation. Conventional physics engines often trade accuracy for computational speed, leading to discrepancies that prevent direct policy transfer. To address this, we introduce Collision Learning via Augmented Sim-to-real Hybridization (CLASH), a data-efficient framework that learns a parameter-conditioned impulsive collision surrogate model and integrates it as a plug-in module within a standard simulator. CLASH first distills a base model from an imperfect simulator (MuJoCo) using large-scale simulated collisions to capture reusable physical priors. Given only a handful of real collisions (e.g., 10 samples), it then (i) performs gradient-based identification of key contact parameters and (ii) applies small-step, early-stopped fine-tuning to correct residual sim-to-real mismatches while avoiding overfitting. The resulting hybrid simulator not only achieves higher post-impact prediction accuracy but also reduces the wall-clock time of collision-heavy CMA-ES search by 42-48% compared to MuJoCo. We demonstrate that policies obtained with our hybrid simulator transfer more robustly to the real world, doubling the success rate in sequential pushing tasks with reinforcement learning and significantly increase the task performance with model-based control.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。