TrAct：用视觉轨迹桥接机器人控制与视觉预测
原标题：TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks
技术动态AI 85
来源：arXiv cs.RO发布时间待核实
arXiv:2608.24101v3 Announce Type: replace Abstract: Robot actions are inherently embodiment-specific and only weakly aligned with image-space visual changes, limiting their effectiveness as conditioning signals for robot world models. In contrast, visual tracks provide an embodiment-agnostic representation of how task-relevant points move through a scene, offering dense image-space guidance for accurate and spatially precise future video prediction. Building on this observation, we propose TrAct…