用轻量强化学习让机器人动作提速超2.4倍，不改数据也能快而稳。
SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning
- 通过强化学习预测最优动作速度，无需新数据采集。
- 实测执行速度提升超2.4倍，成功率仍高于基线方法。
- 适合需要快速精准操作的机器人场景，如倒水、投掷等。
虽然学习型机器人策略在泛化操作方面具有潜力，但其实际部署常受限于执行速度不足。模仿学习策略受采集时操作者速度和硬件限制，且目前缺乏加速模仿学习策略的有效方法，执行速度与任务成功率之间的关系也未被充分探索。为此，我们提出SpeedTuning，一种专为提升操作策略速度设计的强化学习框架。该框架学习预测动作的最佳执行速度，从而在不改变原始策略或额外收集数据的情况下实现加速。实验表明，SpeedTuning在多种动态与高精度任务（如倒液体、投掷、抓取）中实现了超过2.4倍的速度提升，同时保持了可接受的成功率，优于原始策略及固定速度线性插值等简单提速方法。视频与代码已公开于https://daivdyuan.github.io/speed-tuning/。
原文摘要 · Abstract (English)
While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds. Imitation learning policies are inherently limited by hardware constraints and the speed of the operator during data collection. In addition, there are no established methods for accelerating policies learned via imitation, and the empirical relationship between execution speed and task success remains underexplored. To address these issues, we introduce SpeedTuning, a reinforcement learning framework specifically designed to enhance the speed of manipulation policies. SpeedTuning learns to predict the optimal execution speed for actions, thereby complementing a base policy without necessitating additional data collection. We provide empirical evidence that SpeedTuning achieves substantial improvements in execution speed, exceeding 2.4x speed-up, while preserving an adequate success rate compared to both the original task policy and straightforward speed-up methods such as linear interpolation at a fixed speed. We evaluate our approach across a diverse set of dynamic and precise tasks, including pouring, throwing, and picking, demonstrating its effectiveness and robustness in enhancing real-world robotic manipulation. Videos and code are available at https://daivdyuan.github.io/speed-tuning/
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。