Large Scale Distributed Collaborative Unlabeled Motion Planning With Graph Policy Gradients.
Arbaaz KhanVijay KumarAlejandro RibeiroPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- motion planning
- degrees of freedom
- path planning
- trajectory planning
- mobile robot
- humanoid robot
- robot arm
- autonomous mobile robot
- robotic arm
- robotic tasks
- geographically dispersed
- multi robot
- distributed systems
- optimal policy
- obstacle avoidance
- climbing robot
- belief space
- configuration space
- semi supervised learning
- inverse kinematics
- training data
- labeled data
- dynamic environments
- mechanical systems
- collision free
- potential field
- manipulation tasks
- kinematic model
- collaborative learning
- multi agent