arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09408cs.RO
收藏

基于学习分数的几何规划的2D装配鲁棒排序

Robust 2D Assembly Sequencing via Geometric Planning with Learned Scores

Tel-Aviv University(特拉维夫大学);Technion(以色列理工学院);University of California, Berkeley(加州大学伯克利分校)

Tzvika Geft, Aviv Tamar, Ken Goldberg, Dan Halperin

摘要:

为了计算强大的2D装配计划,我们提出了一种方法,结合几何规划与深度神经网络。我们使用Box 2D物理模拟器并添加随机噪声来训练网络,以产生鲁棒性分数--计划装配运动的成功概率。由于对每个装配运动进行仿真是不切实际的,我们训练一个卷积神经网络来映射装配操作,以装配前后的图像对的形式给出,以获得鲁棒性分数。神经网络预测在规划器内用于快速地修剪掉不稳健的运动。我们证明了这种方法双手平面组件,其中的运动是一步平移。结果表明,神经网络可以学习鲁棒性规划鲁棒序列的速度比物理模拟快一个数量级。

英文摘要:

To compute robust 2D assembly plans, we present an approach that combines geometric planning with a deep neural network. We train the network using the Box2D physics simulator with added stochastic noise to yield robustness scores--the success probabilities of planned assembly motions. As running a simulation for every assembly motion is impractical, we train a convolutional neural network to map assembly operations, given as an image pair of the subassemblies before and after they are mated, to a robustness score. The neural network prediction is used within a planner to quickly prune out motions that are not robust. We demonstrate this approach on two-handed planar assemblies, where the motions are one-step translations. Results suggest that the neural network can learn robustness to plan robust sequences an order of magnitude faster than physics simulation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑