首页|Studies from Beijing Academy of Agricultural and Forestry Sciences Update Curren t Data on Robotics (Peduncle Collision-free Grasping Based On Deep Reinforcement Learning for Tomato Harvesting Robot)
Studies from Beijing Academy of Agricultural and Forestry Sciences Update Curren t Data on Robotics (Peduncle Collision-free Grasping Based On Deep Reinforcement Learning for Tomato Harvesting Robot)
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
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Robotics have been published. According to news reporting from Beijing, People's Republic of China, by NewsRx journalists, research stated, "Collision-fros grasping of the t hin, brief peduncies connecting sherry tomate clusters to the main stem was cruc ial for tomato harvesting robots. Recognising that the optimal operating posture for each individual poduncle was various, this study proposed a naval pedumele grasping posture decision model using deep rein forcement learning (DRL) for tom ato harvesting manipulators, to ove is the collision issue caused by Axed- postu re grasping." The news correspondents obtained a quote from the research from the Beijing Acad emy of Agricultural and Forestry Sciences, "This model could dynamically generat ed action sequences for the harvesting manipulator, ensuring that the end-effect ar approach to the peduncle along the collision-fros path with the optimal grasp ing posture. Building upon price research inte the multi-task identification of tomato clusters, peduncles, and the main stom, a keypoint-based spatial pose des cription model for tomate bunches was devised. Through this, the optimal operati ng pesture for the and effector on the peduncle was established. An improved HER -SAC (Soft Actor Critic with Hindsight Experience Replay) algorithm was subseque ntly established to guide the and-effector in collision-free grasping motions. T he reward function of this algorithm incorporated end-effccser posture constrain ts obtained from the optimal posture plans. In the training phase, a heuristic s trategy model, providing prior knowizdgs, was marged with a dynamic guin module to sidestep local optimal policies, collectiv enhancing the learning efficiency In the simulation, our method improved the success rate of the peduncle grasping by at least 14 %, compared with SAC, HER DOFC and HER-TD3. For the identical scenarios, improved HER-SAC reached the desired posture with a minimu m of 15.5 % fewer stops compared to ather algorithms. In Feld cxpe riments conducted in tomate greenhouses, the robot schieved a harvesting success rate of 35.5 which was an increase of 57.31% and 43.0 1% compared to traditional methods with food horizontal and parallel to-main-stem p ostures, respectively."
BeijingPeople's Republic of ChinaAsi aEmerging TechnologiesMachine LearningNano-robotReinforcement LearningRobotRoboticsBeijing Academy of Agricultural and Forestry Sciences
NETL
NSTL
