Motion Planning of Targeted Tea Leaves Harvesting by Manipulator Based on State Parsing

In recent years, the application of intelligent robotics in agriculture has been growing, driving the field towards intelligence. Harvesting research has emerged accordingly, with tea picking posing demanding requirements for manipulator motion planning. Challenges like low precision and poor robustness have persisted in robotic tea harvesting research. Hence, motion planning for tea-picking manipulators has become an important topic. This study focuses primarily on motion planning for tea picking tasks using manipulators, proposing a state parsing based approach. We validate its applicability to tea picking and generalizability to small target harvesting. The designed motion planning utilizes optimized algorithms to achieve efficient, accurate and stable tea leaf picking in various environments. The state parsing based planning signifies an innovative solution for small target grasping. It can effectively enhance efficiency, ensure quality, and realize modernization and intelligence of tea production. Meanwhile, it provides new insights into small target robotic grasping research with immense application potential in intelligent agricultural equipment.