外观
论文arXiv 2610.1900715 天前
Action Jets：学习动作条件数据流形的局部形状
原文链接：Action Jets: Learning the Local Shape of the Action-conditioned Data Manifold（arXiv 2610.19007 · 发布日期：2026-10-13）
Action Jets: Learning the Local Shape of the Action-conditioned Data Manifold
提出Action Jet，以泰勒多项式近似固定状态下动作可达帧的局部流形，在BridgeData V2和DL3DV场景上验证短时域加速与预测。
核心要点
- 动作条件世界模型高维且计算昂贵，限制规划器可评估的动作候选数。
- Action Jet估计各图像区域相对每个动作轴的单位运动，并用轨迹数据校正到三阶泰勒形状。
- 单次状态提取即可遍历局部流形，16个候选评分比源生成器快300倍以上。
- 在BridgeData V2与DL3DV上对比多种生成器，短时域比IRASim更准且计算少百倍以上。
验证范围与局限：验证范围为短时域，包括BridgeData V2真实7-DoF操作基准和DL3DV新视角场景。
英文摘要 (Abstract)
World models are a powerful means of reasoning and planning, but many of these action-conditioned predictive models are high dimensional and computationally expensive. These challenges limit the number of action candidates that can be evaluated by a planner. We show that this cost is avoidable for planners over short horizons, which only require local information with respect to the current state. For a fixed state, the frames reachable by varying a low-dimensional action (a camera movement or an end-effector command) lie on a low-dimensional manifold. We estimate the local shape of that manifold directly via a network trained to estimate how each image region moves per unit of each action axis supervised by data collected from samples by the generator. A correction head fit to trajectory data estimates the shape of this manifold region up to a third-order Taylor polynomial. We call this network estimating the Taylor polynomial describing the manifold shape an Action Jet and compute its radius of validity in closed form. By traversing this approximation of the local manifold shape, we only have to perform inference once per state for any number of candidate actions. Scoring sixteen candidates from a single extraction is over 300x faster than with either source generator, and this gap widens with the number of candidates a planner evaluates. We measure against state-of-the-art action-conditioned generators, IRASim and WorldGym on BridgeData V2, a real 7-DoF manipulation benchmark, and FrameCrafter on DL3DV scenes, where we chart from the novel-view generators DepthSplat and LagerNVS. Because only the tangent comes from the generator and every other term from the data, the Action Jet also predicts held-out frames more accurately than IRASim, the generator that supplied its tangent, at short horizons and at over 100x less compute.
作者：Anton Arapin, Chahyon Ku, Bernadette Bucher
来源
本页事实对应的公开页面，以原文为准。