TAVIS：一种用于第一人称主动视觉和预见性注视的模仿学习基准
TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning
AI总结：
TAVIS提出了一种评估主动视觉模仿学习的基础设施，包含两个任务集和两个仿人躯干机器人，通过实验发现主动视觉对任务类型和条件具有任务依赖性，且多任务策略在分布偏移下表现下降，模仿学习能产生与人类参考相当的预见性注视。
摘要：
主动视觉——即策略在操作过程中控制自身注视——已成为模仿学习中的关键能力，但目前缺乏统一的基准来比较方法或量化主动视觉的贡献，特别是在哪些任务类型和条件下。我们引入TAVIS，一种用于主动视觉模仿学习的评估基础设施，包含两个互补的任务集——TAVIS-Head（5个任务，通过俯仰颈部进行全局搜索）和TAVIS-Hands（3个任务，通过腕部相机进行局部遮挡），并在两个仿人躯干机器人（GR1T2、Reachy2）上构建，基于IsaacLab。TAVIS提供三种评估原语：相同演示的头摄像头与固定摄像头配对协议；GALT（注视-动作提前时间），一种基于认知科学和人机交互的新指标，用于量化学习策略中的预见性注视；以及程序性ID/OOD划分。基于Diffusion Policy和π₀的基线实验表明：（i）主动视觉通常有助于提升性能，但其收益取决于具体任务而非普遍适用；（ii）多任务策略在两个任务集上受控分布偏移下表现急剧下降；（iii）模仿学习本身能产生预见性注视，其中位提前时间与人类远程操作参考相当。代码、评估脚本、演示（LeRobot v3.0；约2200集）和训练基线已发布在https://github.com/spiglerg/tavis和https://huggingface.co/tavis-benchmark。
英文摘要：
Active vision -- where a policy controls its own gaze during manipulation -- has emerged as a key capability for imitation learning, with multiple independent systems demonstrating its benefits in the past year. Yet there is no shared benchmark to compare approaches or quantify what active vision contributes, on which task types, and under what conditions. We introduce TAVIS, evaluation infrastructure for active-vision imitation learning, with two complementary task suites -- TAVIS-Head (5 tasks, global search via pan/tilt necks) and TAVIS-Hands (3 tasks, local occlusion via wrist cameras) -- on two humanoid torso embodiments (GR1T2, Reachy2), built on IsaacLab. TAVIS provides three evaluation primitives: a paired headcam-vs-fixedcam protocol on identical demonstrations; GALT (Gaze-Action Lead Time), a novel metric grounded in cognitive science and HRI that quantifies anticipatory gaze in learned policies; and procedural ID/OOD splits. Baseline experiments with Diffusion Policy and $π_0$ reveal that (i) active vision generally helps, consistently across training runs, but benefits are task-conditional rather than uniform; (ii) multi-task policies degrade sharply under controlled distribution shifts on both suites; and (iii) imitation alone yields anticipatory gaze that lands on the task-relevant object, with lead times comparable to those of the human demonstrations, although head motion is less smooth than in the demonstrations, an effect of action chunking that success rate does not reveal. Code and evaluation scripts are released at https://github.com/spiglerg/tavis; demonstrations (LeRobot v3.0; ~2200 episodes) and trained baselines at https://huggingface.co/tavis-benchmark.
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。
