ECNNs: Ensemble Learning Methods for Improving Planar Grasp Quality Estimation
ECNNs: Ensemble Learning Methods for Improving Planar Grasp Quality Estimation
复制标题
DOI：
10.1109/icra48506.2021.9561038
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Fadi M. Alladkani;James Akl;B. Çalli
中科院分区：
文献类型：
--
作者：
Fadi M. Alladkani;James Akl;B. Çalli
我们提出了一种集成学习方法，结合了多个现有的机器人把握合成算法，并获得了成功率是显着优于个别算法。该方法将抓取算法视为提供抓取“意见”的“专家”。使用专家混合（莫伊）模型来训练一个嵌入式卷积神经网络（ECNN），该模型集成了这些意见并确定最终的抓取决策。ECNN引入了最小的计算成本开销，并且网络几乎可以像最慢的专家一样快地运行。我们通过采用GQCNN 4.0，GGCNN和GGCNN的自定义变体作为专家，使用文献中的开源算法测试了这种架构，并在Cornell数据集上获得了6%的抓取成功率。该方法的性能也证明了使用弗兰卡Panda手臂。
We present an ensemble learning methodology that combines multiple existing robotic grasp synthesis algorithms and obtain a success rate that is significantly better than the individual algorithms. The methodology treats the grasping algorithms as "experts" providing grasp "opinions". An Ensemble Convolutional Neural Network (ECNN) is trained using a Mixture of Experts (MOE) model that integrates these opinions and determines the final grasping decision. The ECNN introduces minimal computational cost overhead, and the network can virtually run as fast as the slowest expert. We test this architecture using open-source algorithms in the literature by adopting GQCNN 4.0, GGCNN and a custom variation of GGCNN as experts and obtained a 6% increase in the grasp success on the Cornell Dataset compared to the best-performing individual algorithm. The performance of the method is also demonstrated using a Franka Emika Panda arm.