REACH: Reducing False Negatives in Robot Grasp Planning with a Robust Efficient Area Contact Hypothesis Model
REACH: Reducing False Negatives in Robot Grasp Planning with a Robust Efficient Area Contact Hypothesis Model
复制标题
DOI：
10.1007/978-3-030-95459-8_46
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Michael Danielczuk;Jingyi Xu;Jeffrey Mahler;Matthew Matl;N. Chentanez;Ken Goldberg
中科院分区：
文献类型：
--
作者：
Michael Danielczuk;Jingyi Xu;Jeffrey Mahler;Matthew Matl;N. Chentanez;Ken Goldberg
虽然点接触模型是无处不在的机器人把握规划，他们不建模的扳手，有限面积的软接触提供的范围。这种近似导致许多假阴性。为了减少这些，我们提出了REACH，一个强大的有效区域接触假设模型。我们考虑了它的潜在好处并调查了两个潜在缺点：计算复杂性增加和误报增加。REACH模型使用构造性立体几何相交和重心积分来计算接触轮廓，并估计接触抵抗外部扳手的能力（例如，重力）在物体姿态和材料性质的扰动下。我们使用ABB YuMi机器人对21种不同物体进行了2，625次物理抓取，以评估REACH的性能。我们使用NVIDIA Flex比较了软点接触模型、椭圆区域接触模型和刚体动态仿真模型的性能。与点接触模型相比，REACH模型将假阴性减少了17%，平均召回率达到72%。REACH模型与Flex中的全动态仿真相比也毫不逊色，并且速度快两个数量级，平均计算时间为50 ms。实验数据和补充材料可在https://sites.google.com/berkeley.edu/reach上获得。
Although point contact models are ubiquitous for robot grasp planning, they do not model the range of wrenches that finite-area soft contacts provide. This approximation leads to many false negatives. To reduce these, we propose REACH, a Robust Efficient Area Contact Hypothesis model. We consider its potential benefits and investigate two potential drawbacks: increased computational complexity and increased false positives. The REACH model computes the contact profile using constructive solid geometry intersection and barycentric integration and estimates the contact’s ability to resist external wrenches (e.g., gravity) under perturbations in object pose and material properties. We evaluate the performance of REACH with 2,625 physical grasps of 21 diverse objects with an ABB YuMi robot. We compare performance of a soft point contact model, an elliptical area contact model, and a rigid-body dynamic simulation model using NVIDIA Flex. The REACH model reduces false negatives by 17% compared to the point contact model, achieving 72% average recall. The REACH model also compares favorably to full dynamic simulation in Flex and is two orders of magnitude faster, with 50 ms average computation time. Experimental data and supplementary material are available at https://sites.google.com/berkeley.edu/reach.