Autonomous operation decision-making method of picking manipulator

An autonomous operation decision-making method of a picking manipulator, wherein the picking manipulator is provided with an end effector configured to pick a fruit off a branch;

• and
• the autonomous operation decision-making method of a picking manipulator comprises:
• acquiring sample images of fruits and branches and constructing a plurality of virtual scenes, wherein each of the plurality of virtual scenes comprises a picking manipulator model, a fruit model, and a branch model;
• in the virtual scene, determining a target picking point and a target picking plane of an end effector model, and inputting azimuth information of the target picking point and the target picking plane as parameters to a reward function;
• performing reinforcement learning training on picking action flows of the picking manipulator in the plurality of virtual scenes according to the reward function to determine an optimal picking action function;
• and
• controlling the picking manipulator to execute a picking task in an actual environment according to the optimal picking action function.