Reactive optimal motion planning for a class of holonomic planar agents using reinforcement learning with provable guarantees.
Panagiotis RousseasCharalampos P. BechlioulisKostas J. KyriakopoulosPublished in: Frontiers Robotics AI (2023)
Keyphrases
- motion planning
- reinforcement learning
- multi agent
- path planning
- degrees of freedom
- mobile robot
- trajectory planning
- agent architecture
- robot arm
- reactive agents
- multi agent systems
- collision free
- humanoid robot
- multiagent systems
- dynamic programming
- learning agents
- robotic arm
- robotic tasks
- dynamic environments
- inverse kinematics
- autonomous mobile robot
- action selection
- optimal control
- multi agent reinforcement learning
- optimal solution
- multi robot
- multiple agents
- software agents
- control law
- intelligent agents
- robot control
- model free
- configuration space
- belief space
- mechanical systems
- machine learning
- markov decision processes
- spatio temporal
- control policy
- learning agent
- real robot
- single agent
- obstacle avoidance