Peduncle collision-free grasping based on deep reinforcement learning for tomato harvesting robot.
Yajun LiQingchun FengYifan ZhangChuanlang PengYuhang MaCheng LiuMengfei RuJiahui SunChunjiang ZhaoPublished in: Comput. Electron. Agric. (2024)
Keyphrases
- collision free
- reinforcement learning
- path planning
- motion planning
- mobile robot
- collision avoidance
- path planner
- dynamic environments
- manipulation tasks
- control policy
- real robot
- vision system
- free space
- potential field
- multiple robots
- robotic arm
- state space
- multi robot
- human robot interaction
- optimal policy
- dynamic programming
- humanoid robot
- navigation tasks
- learning algorithm
- robot control
- machine learning
- degrees of freedom
- markov decision processes
- shortest path
- optimal path
- robot arm
- high dimensional
- motor skills
- object manipulation