arXiv cs.AI· Sinjae Kang, Dong Kyu Shin, Jaehong Kim, Kamin Lee, Hyoeun Kim, Kaixin Wang, Li Zhao, Seonghyeon Ye, Kimin Lee·· 4 小时前AI 评分41
QCP：基于迭代事后重标注的质量可控机器人策略学习方法
Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling
AI 导读
研究者提出质量可控策略 QCP，可在推理时控制执行速度、运动平滑度等质量属性及其组合，并通过迭代事后重标注循环扩充可控质量范围。该方法在 Robomimic 和 RoboEval 上持续提升执行质量与成功率，成功轨迹质量超过初始演示。真实世界验证显示，控制速度可提高传送带作业吞吐量，控制运输稳定性可提升端酒杯的成功率。
正文 · 原文
Abstract:Robot policy evaluation often relies on a binary success signal for task completion. In real-world deployment, however, desired execution behaviors are also defined by quality attributes such as execution speed and motion smoothness, which need to be dynamically controlled according to task requirements. To address this, we introduce Quality-Controllable Policy (QCP), a robot policy that enables inference-time control over both individual quality attributes and their combinations. To extend the controllable quality range beyond initial demonstrations, we further propose an iterative hindsight relabeling loop: QCP collects online rollouts under target quality labels, adds successful trajectories to the dataset, relabels the accumulated trajectories in hindsight according to their measured quality, and fine-tunes the policy. Experiments on Robomimic and RoboEval demonstrate that QCP consistently improves both task execution quality and success rates across iterations, producing successful rollouts that exceed the quality of the initial demonstrations. Finally, we validate QCP on real-world manipulation tasks, where controlling speed increases throughput in conveyor operations and controlling transport stability improves success when carrying wine glasses, demonstrating that quality-controllable policies yield practical gains in physical deployment.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.37393 [cs.RO] |
| (or arXiv:2610.37393v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37393 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sinjae Kang [view email]
[v1]
Tue, 27 Oct 2026 15:15:14 UTC (14,438 KB)
来源：arXiv cs.AI · arxiv.org