发表机构
Deakin University（迪肯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种执行感知的预执行排序方法，通过结合点云和姿态描述符预测规划与执行成功，在机器人放置任务中显著提升端到端成功率。
AI 中文摘要
一个几何上有效的放置仍然可能难以执行，因为所选抓取会改变所需的末端执行器姿态、碰撞几何和运输运动。本文将放置问题表述为一个预执行排序问题，在规划之前对提供的抓取-放置候选进行评分。该模型结合了一个带类型的、以目标为条件的点云，以及三个姿态描述符和用于规划成功和以规划为条件的执行成功的分层头。在一个包含30个物体、1,235个场景且采用场景组留出法划分的数据集上，三个随机种子的覆盖测试组的前1名成功率在联合选择上达到85.63±1.08%，在固定目标排序上达到79.84±0.16%。对于指定的冻结种子42检查点，前1名成功率在联合排序上从全池cuMotion的72.84%提高到85.78%，在固定目标排序上从59.65%提高到79.67%。冻结迁移到xArm7/MoveIt无需针对xArm的重新训练。在27个锁定案例中，13个完整端到端完成（48.15%）。在通过Top-5预检并开始执行的16个案例中，13个成功（81.25%）。候选级别的部署可行性预测达到81.25%的召回率、85.20%的特异性和83.23%的平衡准确率。
英文摘要
A geometrically valid placement can still be difficult to execute because the selected grasp changes the required end-effector pose, collision geometry, and transport motion. Placement is formulated as a pre-execution ranking problem in which supplied grasp-placement candidates are scored before planning. The model combines a typed target-conditioned point cloud with three pose descriptors and hierarchical heads for planning success and execution success conditioned on planning. On a 30-object, 1,235-scene dataset with scene-group-held-out splits, three-seed top-1 success on covered test groups reaches 85.63 +/- 1.08% for joint selection and 79.84 +/- 0.16% for fixed-target ranking. For the designated frozen seed-42 checkpoint, top-1 success improves from 72.84% to 85.78% over full-pool cuMotion for joint ranking and from 59.65% to 79.67% for fixed-target ranking. Frozen transfer to xArm7/MoveIt requires no xArm-specific retraining. Across 27 locked cases, 13 complete end to end (48.15%). Of the 16 cases that pass Top-5 preflight and begin execution, 13 succeed (81.25%). Candidate-level deployment-feasibility prediction reaches 81.25% recall, 85.20% specificity, and 83.23% balanced accuracy.
Comments8pages, 6figures
