Combining Reinforcement Learning and Differential Inverse Kinematics for Collision-Free Motion of Multilink Manipulators.
Pedro MartínJosé del R. MillánPublished in: IWANN (1997)
Keyphrases
- motion planning
- inverse kinematics
- collision free
- reinforcement learning
- robot arm
- degrees of freedom
- path planning
- end effector
- mobile robot
- humanoid robot
- robotic arm
- multi robot
- control law
- joint angles
- optimal policy
- state space
- markov decision processes
- robot manipulators
- learning algorithm
- machine learning
- neural network
- adaptive control
- real robot
- multi modal