Object extraction tasks often occur in disassembly problems, where bolts, screws, or pins have to be removed from tight, narrow spaces. In such problems, the distance to the environment is often on the millimeter scale. Sampling-based planners can solve such problems and provide completeness guarantees. However, sampling becomes a bottleneck, since almost all motions will result in collisions with the environment. To overcome this problem, we propose a novel scale-invariant sampling strategy which explores the configuration space using a grow-shrink search to find useful, high-entropy sampling scales. Once a useful sampling scale has been found, our framework exploits this scale by using a principal components analysis (PCA) to find useful directions for object extraction. We embed this sampler into a multi-arm bandit rapidly-exploring random tree (MAB-RRT) planner and test it on eight challenging 3D object extraction scenarios, involving bolts, gears, rods, pins, and sockets. To evaluate our framework, we compare it with classical sampling strategies like uniform sampling, obstacle-based sampling, and narrow-passage sampling, and with modern strategies like mate vectors, physics-based planning, and disassembly breadth first search. Our experiments show that scale-invariant sampling improves success rate by one order of magnitude on 7 out of 8 scenarios. This demonstrates that scale-invariant sampling is an important concept for general purpose object extraction in disassembly tasks.

翻译：物体提取任务常见于拆解问题中，需从狭窄空间移除螺栓、螺钉或销钉。此类问题中，与环境的距离往往处于毫米量级。基于采样的规划器可解决这类问题并提供完备性保证，但采样过程成为瓶颈——几乎所有运动都会与环境发生碰撞。为解决该问题，我们提出一种新颖的尺度不变采样策略，通过"生长-收缩"搜索探索构型空间，寻找高熵的有效采样尺度。一旦获得有效尺度，本框架利用主成分分析（PCA）确定物体提取的有利方向，从而充分利用该尺度。我们将该采样器嵌入多臂老虎机快速探索随机树（MAB-RRT）规划器，并在八个涉及螺栓、齿轮、杆件、销钉和插座的复杂三维物体提取场景中开展测试。为评估本框架，我们将其与经典采样策略（均匀采样、基于障碍物的采样、窄通道采样）及现代策略（配对向量法、物理仿真规划、拆解广度优先搜索）进行对比。实验表明，在8个场景中有7个场景的尺度不变采样将成功率提升一个数量级，证明尺度不变采样是拆解任务中通用物体提取的重要概念。