Using Crowdsourcing to Generate Surrogate Training Data for Robotic Grasp Prediction
Using Crowdsourcing to Generate Surrogate Training Data for Robotic Grasp Prediction
复制标题
使用众包生成机器人抓取预测的代理训练数据
DOI：
10.1609/hcomp.v2i1.13193
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Ravi Balasubramanian
中科院分区：
文献类型：
--
作者：
Matt Unrath;Zhifei Zhang;Alex K. Goins;Ryan Carpenter;Weng;Ravi Balasubramanian
作为从物理机器人平台收集训练数据以学习机器人抓取质量预测的费力过程的替代方案，我们探索使用来自机器人抓取图像的众包评估的替代训练数据。我们表明，在抓取特征空间的某些区域，使用此替代数据训练的抓取预测器几乎与使用机器人物理测试数据构建的预测器一样准确。
As an alternative to the laborious process of collecting training data from physical robotic platforms for learning robotic grasp quality prediction, we explore the use of surrogate training data from crowd-sourced evaluations of images of robotic grasps. We show that in certain regions of the grasp feature space, grasp predictors trained with this surrogate data were almost as accurate as predictors built using data from physical testing with robots.