外观
论文arXiv 2610.0930921 天前
预测的未来还不够：为机器人操作学习可执行目标
该文针对世界模型预测难以直接用于控制的问题，提出Entity-Level Goal Readout，并在五个操作任务和Franka真机上验证。
Franka FR3原文链接：Predicted Futures Are Not Enough: Learning Executable Goals for Robot Manipulation（arXiv 2610.09309 · 发布日期：2026-10-07）
Predicted Futures Are Not Enough: Learning Executable Goals for Robot Manipulation
该文针对世界模型预测难以直接用于控制的问题，提出Entity-Level Goal Readout，并在五个操作任务和Franka真机上验证。
核心要点
- 问题：生成式世界模型能预测场景演化，但未来预测不直接给出控制所需紧凑任务变量。
- 方法：Entity-Level Goal Readout将3D轨迹世界模型输出转为SE(3)终端目标。
- 执行：共享Pose-Native Executor利用固定目标与在线物体位姿反馈进行闭环控制。
- 结果：五项任务平均成功率79.69%，Franka零样本部署最高达到75.00%。
验证范围与局限：验证范围包括五个操作任务，以及Franka机械臂在StackCube、带干扰物StackCube和PickPlate上的零样本部署。
英文摘要 (Abstract)
Generative world models provide rich predictions of how manipulation scenes may evolve toward task objectives, yet those futures do not directly expose the compact task variables required by control. When training supervises future prediction alone, terminal goal accuracy is not an explicit learning objective, even when geometric recovery is available. We present Entity-Level Goal Readout, a learned prediction-to-execution interface that makes the executable terminal goal an explicit output of a 3D trace world model. It combines object-centric pose prediction with translation grounded in observed depth to produce a compact goal in SE(3). A shared Pose-Native Executor consumes this fixed goal with online object-pose feedback for closed-loop control without rerunning the world model. Across five manipulation tasks, the pipeline achieves a mean success rate of 79.69%. Goal diagnostics directly measure terminal goal accuracy, while controlled translation perturbations characterize how execution degrades under goal error. Zero-shot deployment on a Franka arm achieves 73.33% success on nominal StackCube, 66.67% with distractors, and 75.00% on PickPlate with a target unseen during policy training. These results support treating the prediction-to-execution interface as an explicit learned component of world-model planning rather than incidental post-processing in the control pipeline itself. Project page: https://claire0730.github.io/executable-goals/
作者：Tzu-Yu Chuang, Ching-Hsiang Chang, Yi-Hsiu Lee, Yi-Ting Chen, Min Sun, YuanFu Yang
来源
本页事实对应的公开页面，以原文为准。