DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation

2026-09-09

AI Summary

为解决7-DoF末端执行器控制中细粒度动作预测不准确问题，提出DUET-DINO模型，通过同时从侧视和腕部相机视角学习动作条件预测，提高机器人操作中的潜在规划性能。

Abstract

Action-conditioned latent world models predict future visual representations, enabling zero-shot goal-conditioned robot planning and control. However, their predictions for fine-grained spatial and rotational actions are unreliable for full 7-DoF end-effector control. To address this gap, we introduce DUET-DINO, a simultaneous cross-view latent world model that jointly learns action-conditioned predictions from static side- and wrist-camera observations through cross-view conditioning. By exploiting complementary global scene and gripper-centric information, DUET-DINO enables latent planning over the full 7-DoF action space. Across spatially diverse reach, orientation-intensive angled-reach, and multi-goal grasp-and-lift tasks, DUET-DINO consistently outperforms single-view and independent dual-view baselines, achieving 92% success on reach, 72.5% on angled-reach, and 60.0% on lift tasks. DUET-DINO is trained from scratch on DROID and RoboArena datasets and generalizes robustly under visual distribution shifts. We further show that while V-JEPA 2 wrist-view predictions underestimate visual dynamics induced by fine-grained actions, DINOv3 predictions better capture action-conditioned scene changes, leading to stronger downstream planning. The code and model checkpoints will be open-sourced. Project page: https://utn-air.github.io/DUET-DINO

Problem

• action-conditioned latent world models
• 7-DoF end-effector control
• fine-grained spatial and rotational actions

Innovation

• Cross-View Conditioning
• Latent Planning
• 7-DoF Control
• Action-Conditioned Predictions
• Dual-Camera Setup