arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.06267cs.HCcs.AI
收藏

FARPLS:一种辅助标注人员偏好提取的特征增强机器人轨迹偏好标注系统

FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitation

Hong Kong University of Science and Technology(香港科技大学);Carnegie Mellon University(卡内基梅隆大学);Tongji University(同济大学);Southeast University(东南大学);Hong Kong Productivity Council(香港生产力促进局);Hong Kong Industrial Artificial Intelligence and Robotics Centre (FLAIR)(香港工业人工智能及机器人中心(FLAIR));University of Manchester(曼彻斯特大学)

Hanfang Lyu, Yuanchen Bai, Xin Liang, Ujaan Das, Chuhan Shi, Leiliang Gong, Yingchi Li, Mingfei Sun, Ming Ge, Xiaojuan Ma

AI总结:

针对传统机器人轨迹偏好标注中存在的特征易忽略、标注易疲劳、质量下降等问题,提出特征增强的FARPLS系统,通过高亮特征、动态调序等方式,提升标注一致性与参与度且不显著增加认知负荷。

摘要:

基于偏好的学习旨在让机器人任务目标与人类价值观对齐。推断人类偏好的最常见方法之一是对机器人任务轨迹进行成对比较。传统的基于比较的偏好标注系统很少能支持标注人员理解并识别视频中记录的复杂轨迹之间的关键差异。我们的形成性研究(N=12)表明,由于观察不全面,个体可能会忽略不显著的任务特征,并在偏好提取过程中建立有偏差的偏好标准。此外,当需要比较多对轨迹时,他们可能会出现精神疲劳,导致标注质量下降。为缓解这些问题,我们提出了FARPLS——一种特征增强机器人轨迹偏好标注系统。FARPLS会高亮显示各类对人类重要的任务特征中的潜在异常值,并提取对应的视频关键帧,方便标注人员查看和比较。它还会根据用户的熟悉程度、轨迹对的难度以及分歧程度动态调整标注顺序。同时,系统会监控标注人员的一致性,并提供标注进度反馈,以保持标注人员的参与度。一项被试间研究(N=42,每人需标注105对机器人抓取-放置轨迹)表明,与传统界面相比,FARPLS能帮助用户更轻松地建立偏好标准,并注意到所呈现轨迹中更多的相关细节。FARPLS还提升了标注一致性和参与度,在不显著增加认知负荷的情况下缓解了偏好提取中的挑战。

英文摘要:

Preference-based learning aims to align robot task objectives with human values. One of the most common methods to infer human preferences is by pairwise comparisons of robot task trajectories. Traditional comparison-based preference labeling systems seldom support labelers to digest and identify critical differences between complex trajectories recorded in videos. Our formative study (N = 12) suggests that individuals may overlook non-salient task features and establish biased preference criteria during their preference elicitation process because of partial observations. In addition, they may experience mental fatigue when given many pairs to compare, causing their label quality to deteriorate. To mitigate these issues, we propose FARPLS, a Feature-Augmented Robot trajectory Preference Labeling System. FARPLS highlights potential outliers in a wide variety of task features that matter to humans and extracts the corresponding video keyframes for easy review and comparison. It also dynamically adjusts the labeling order according to users' familiarities, difficulties of the trajectory pair, and level of disagreements. At the same time, the system monitors labelers' consistency and provides feedback on labeling progress to keep labelers engaged. A between-subjects study (N = 42, 105 pairs of robot pick-and-place trajectories per person) shows that FARPLS can help users establish preference criteria more easily and notice more relevant details in the presented trajectories than the conventional interface. FARPLS also improves labeling consistency and engagement, mitigating challenges in preference elicitation without raising cognitive loads significantly

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。

↑