Fast stochastic motion planning with optimality guarantees using local policy reconfiguration.
Ryan LunaMorteza LahijanianMark MollLydia E. KavrakiPublished in: ICRA (2014)
Keyphrases
- motion planning
- degrees of freedom
- trajectory planning
- mobile robot
- path planning
- humanoid robot
- robot arm
- control policies
- optimal policy
- average cost
- robotic arm
- inverse kinematics
- autonomous mobile robot
- robotic tasks
- multi robot
- average reward
- climbing robot
- manipulation tasks
- mechanical systems
- configuration space
- initial state
- obstacle avoidance
- optimal solution
- infinite horizon
- control policy
- long run
- markov decision processes
- state space
- reinforcement learning