arXiv cs.AI· Sinjae Kang, Dong Kyu Shin, Jaehong Kim, Kamin Lee, Hyoeun Kim, Kaixin Wang, Li Zhao, Seonghyeon Ye, Kimin Lee·· 2 天前AI 评分31
QCP：用迭代 hindsight relabeling 学习质量可控的机器人策略
Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling
AI 导读
研究者提出 Quality-Controllable Policy（QCP），一种可在推理时控制执行速度、运动平滑度等单项质量属性及其组合的机器人策略。为突破初始演示的质量上限，QCP 采用迭代 hindsight relabeling 循环：按目标质量标签收集在线 rollout、将成功轨迹加入数据集、按实测质量重新打标并微调策略。
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