用可微模拟器自动调优机器人控制器，几轮试跑即适配新环境。
DiffCoTune: Differentiable Co-Tuning for Cross-domain Robot Control
- 通过可微模拟器迭代收集数据，联合优化仿真器与控制器参数。
- 在弹跳、四足、双足等任务中实现跨域性能显著提升。
- 适合需要快速适配真实环境的机器人控制研发人员。
机器人控制器部署受限于建模偏差，这通常源于计算可处理性所需的简化或仿真器的数据不准确。此类偏差往往需手动调参以达成目标性能，从而确保成功迁移至目标域。我们提出一种基于梯度的自动化调优框架，利用可微仿真器提升部署域表现。方法通过迭代收集轨迹，协同调优仿真器与控制器参数，仅数次试跑即可系统性完成迁移。具体而言，我们为调优设计多步目标，并采用交替优化有效适应控制器至部署域。框架的可扩展性通过联合调优模型基础与学习型控制器（任意复杂度）得到验证，涵盖从低维倒立摆稳定到高维四足与双足跟踪的任务，在不同部署域均实现性能提升。
原文摘要 · Abstract (English)
The deployment of robot controllers is hindered by modeling discrepancies due to necessary simplifications for computational tractability or inaccuracies in data-generating simulators. Such discrepancies typically require ad-hoc tuning to meet the desired performance, thereby ensuring successful transfer to a target domain. We propose a framework for automated, gradient-based tuning to enhance performance in the deployment domain by leveraging differentiable simulators. Our method collects rollouts in an iterative manner to co-tune the simulator and controller parameters, enabling systematic transfer within a few trials in the deployment domain. Specifically, we formulate multi-step objectives for tuning and employ alternating optimization to effectively adapt the controller to the deployment domain. The scalability of our framework is demonstrated by co-tuning model-based and learning-based controllers of arbitrary complexity for tasks ranging from low-dimensional cart-pole stabilization to high-dimensional quadruped and biped tracking, showing performance improvements across different deployment domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。