TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models

2026-09-22

AI Summary

为了解决多视角一致性问题，本文提出TriWorldBench，通过同步头、左腕和右腕视频评估机器人具身世界模型，使用19个指标衡量任务对齐等性能。

Abstract

Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary views: the head view captures the overall task, while wrist views reveal local gripper-object interactions. However, evaluating these views independently cannot determine whether they describe the same action and object state. We introduce TRIWORLDBENCH, a benchmark for evaluating embodied world models through synchronized head, left-wrist, and right-wrist videos. It contains 500 episodes across 50 bimanual manipulation tasks and uses 19 metrics to assess tri-view consistency, task alignment, physical and 3D coherence, motion quality, temporal consistency, and visual quality. By combining cross-view checks with measurements tailored to each camera, the benchmark evaluates whether plausible individual videos also form a consistent prediction of the intended task. We summarize overall performance with TWB-Score and retain per-view results to identify where predictions fail. This extends world-model evaluation beyond single-view visual quality. Code, data, and metric definitions are available at https://github.com/TriWorldBench/TriWorldBench.

Problem

• Embodied World Models
• Tri-View Consistency
• Bimanual Manipulation
• Cross-View Checks
• Task Alignment

Innovation

• tri-view consistency
• embodied world models
• benchmark
• bimanual manipulation
• TWB-Score