MetaGrasp: Data Efficient Grasping by Affordance Interpreter Network
MetaGrasp: Data Efficient Grasping by Affordance Interpreter Network
复制标题
MetaGrasp：通过 Affordance 解释器网络高效抓取数据
DOI：
10.1109/icra.2019.8793912
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Jingcheng Su
中科院分区：
文献类型：
--
作者：
Junhao Cai;Hui Cheng;Zhanpeng Zhang;Jingcheng Su
数据驱动的抓取方法近年来取得了重大进展。但是这些方法通常需要大量的训练数据。为了提高抓取数据收集的效率，本文提出了一种新的抓取训练系统，包括从数据收集到模型推理的整个流程。系统通过对映抓取规则辅助的纠偏策略收集有效抓取样本，并设计了一个功能解释网络来预测像素级抓取功能图。我们将可抓性、不可抓性和背景定义为可抓性启示。该系统的关键优势在于，在对映规则下，仅使用少量抓取样本训练的像素级功能解释器网络可以在完全看不见的物体和背景上取得显著的性能。训练样本只在模拟中收集。大量的定性和定量实验证明了我们提出的方法的准确性和稳健性。在真实世界的抓取实验中，我们在一组家庭物品上的抓取成功率为93%，在一组对抗性物品上的抓取成功率为91%，只有大约6300个模拟样本。在杂波情况下，准确率达到87%。虽然该模型仅使用RGB图像进行训练，但当改变背景纹理时，它也表现良好，在对抗性对象集上甚至可以达到94%的准确率，优于当前最先进的方法。
Data-driven approach for grasping shows significant advance recently. But these approaches usually require much training data. To increase the efficiency of grasping data collection, this paper presents a novel grasp training system including the whole pipeline from data collection to model inference. The system can collect effective grasp sample with a corrective strategy assisted by antipodal grasp rule, and we design an affordance interpreter network to predict pixelwise grasp affordance map. We define graspability, ungraspability and background as grasp affordances. The key advantage of our system is that the pixel-level affordance interpreter network trained with only a small number of grasp samples under antipodal rule can achieve significant performance on totally unseen objects and backgrounds. The training sample is only collected in simulation. Extensive qualitative and quantitative experiments demonstrate the accuracy and robustness of our proposed approach. In the real-world grasp experiments, we achieve a grasp success rate of 93% on a set of household items and 91% on a set of adversarial items with only about 6,300 simulated samples. We also achieve 87% accuracy in clutter scenario. Although the model is trained using only RGB image, when changing the background textures, it also performs well and can achieve even 94% accuracy on the set of adversarial objects, which outperforms current state-of-the-art methods.
DOI：
--
发表时间：
2018-06
期刊：
ArXiv
影响因子：
--
作者：
J. Matas;Stephen James;A. Davison
通讯作者：
J. Matas;Stephen James;A. Davison
影响因子：
51.1
作者：
Fassnacht, Martin;Berruti, Alfredo;Hammer, Gary D.
通讯作者：
Hammer, Gary D.