TAVIS benchmark advances robotics imitation learning with active vision

Researchers have introduced TAVIS, a new benchmark designed to evaluate active vision in imitation learning for robotics. The benchmark includes two task suites, TAVIS-Head and TAVIS-Hands, built on humanoid embodiments and utilizing IsaacLab. TAVIS offers a paired headcam-vs-fixedcam protocol, a novel Gaze-Action Lead Time (GALT) metric for anticipatory gaze, and procedural in-distribution/out-of-distribution splits. Initial experiments with Diffusion Policy and $\pi_0$ indicate that active vision generally improves performance but is task-dependent, and multi-task policies struggle with distribution shifts. AI

影响 Establishes a standardized evaluation framework for active vision in robotics, potentially accelerating progress in imitation learning for complex manipulation tasks.

排序理由 The cluster describes a new academic benchmark and evaluation infrastructure for robotics research. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Active Vision
• Diffusion Policy
• Gaze-Action Lead Time
• GR1T2
• Imitation Learning
• IsaacLab
• \pi_0
• Reachy2
• Robotics
• TAVIS

• 论文
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →