首页|New Robotics Study Findings Recently Were Reported by Researchers at University of Bordeaux (Multi Actor-critic Ddpg for Robot Action Space Decomposition: a Framework To Control Large 3d Deformation of Soft Linear Objects)
New Robotics Study Findings Recently Were Reported by Researchers at University of Bordeaux (Multi Actor-critic Ddpg for Robot Action Space Decomposition: a Framework To Control Large 3d Deformation of Soft Linear Objects)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
IEEE
Research findings on Robotics are discussed in a new report. According to news reporting from Talence, France, by NewsRx journalists, research stated, “Robotic manipulation of deformable linear objects (DLOs) has great potential for applications in diverse fields such as agriculture or industry. However, a major challenge lies in acquiring accurate deformation models that describe the relationship between robot motion and DLO deformations.” Financial support for this research came from Horizon 2020. The news correspondents obtained a quote from the research from the University of Bordeaux, “Such models are difficult to calculate analytically and vary among DLOs. Consequently, manipulating DLOs poses significant challenges, particularly in achieving large deformations that require highly accurate global models. To address these challenges, this letter presents MultiAC6: a new multi Actor-Critic framework for robot action space decomposition to control large 3D deformations of DLOs. In our approach, two deep reinforcement learning (DRL) agents orient and position a robot gripper to deform a DLO into the desired shape. Unlike previous DRL-based studies, MultiAC6 is able to solve the sim-to-real gap, achieving large 3D deformations up to 40 cm in real-world settings. Experimental results also show that MultiAC6 has a 66% higher success rate than a single-agent approach.”
TalenceFranceEuropeEmerging TechnologiesMachine LearningRobotRoboticsUniversity of Bordeaux
NETL
NSTL
IEEE
