New Findings on Robotics and Automation from Shanghai Jiao Tong University Summa rized (Semi-autonomous Grasping Control of Prosthetic Hand and Wrist Based On Mo tion Prior Field)
New Findings on Robotics and Automation from Shanghai Jiao Tong University Summa rized (Semi-autonomous Grasping Control of Prosthetic Hand and Wrist Based On Mo tion Prior Field)
上海交通大学机器人与自动化研究新进展综述(基于运动先验场的假肢手腕半自主抓取控制)
扫码查看
点击上方二维码区域，可以放大扫码查看
摘要
由新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-机器人和自动化的最新数据在一份新的报告中呈现。根据NewsRx记者从中华人民共和国上海发回的新闻报道，研究表明，"如何从任意方向获取复杂形状物体的多个启示部分仍然是腕关节假手的一个难题.本文提出了一种半自主控制方法,该方法只使用集成的手持凸轮A来预测物体在接近物体时的最终抓取部分,并获得合适的腕关节角度和预形类型."本研究经费来源于国家自然科学基金(NSFC)。新闻记者引用了上海交吴大学的一篇研究文章:“我们收集人类专家的趋近-抓握运动序列,构建运动先验场(MPF),并通过行为克隆得到预测模型MPFNet。通过噪声增强和混合回归-分类策略训练,得到预测模型MPFNet。”我们的预测模型在对每个物体进行少量(15)演示的情况下,预测偏差小于2 cm .我们将我们的控制方法应用于具有2个自由度的(DoF)腕关节的假手,使其能够抓取复杂形状物体的多个部分,并且在位置和方向变化下保持鲁棒性.该方法使抓握成功率提高65.4%/26.3%,控制时间提高40.4%/26.3%,误差距离提高35.6%/27.8%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Robotics - Robotics and Automation are presented in a new report. According to news reporting from Shang hai, People's Republic of China, by NewsRx journalists, research stated, "Graspi ng multiple affordance parts and from arbitrary directions for complex shaped ob jects still remains a challenging problem for prosthetic hand with wrist. We pro pose a semi-autonomous control method that uses only an integrated in-hand camer a to predict the final grasping part on an object as the hand approaches it and obtain the appropriate wrist joint angles and preshape type." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). The news correspondents obtained a quote from the research from Shanghai Jiao To ng University, "We collect approach-grasp motion sequences from human experts to construct a motion prior field (MPF) and derive the prediction model MPFNet by behavior cloning. With noise augmentation and a hybrid regressioncategorization policy training, our prediction model gets less than 2 cm predicting deviation under a small number (15) of demonstrations for each object. We apply our contro l method to a prosthetic hand with a 2 degrees -of-freedom (DoF) wrist, enabling it to grasp multiple parts of complex shaped objects and remain robust under th e position and orientation variation. Compared to state-of-the-art myoelectric c ontrol and semi-autonomous control methods, respectively, our method improves 65 .4%/26.3% in grasp success rate, 40.4%/2 6.3% in control time, and 35.6%/27.8% i n error distance."
Key words
Shanghai/People's Republic of China/As ia/Robotics and Automation/Robotics/Shanghai Jiao Tong University
NETL
NSTL