A combined reactive and reinforcement learning controller for an autonomous tracked vehicle.
Isabelle VincentQiao SunPublished in: Robotics Auton. Syst. (2012)
Keyphrases
- reinforcement learning
- real time
- autonomous vehicles
- land vehicle
- optimal control
- autonomous learning
- control system
- function approximation
- agent architecture
- control architecture
- cooperative
- closed loop
- control policy
- pid controller
- learning capabilities
- reinforcement learning algorithms
- actor critic
- adaptive control
- control algorithm
- control scheme
- robotic systems
- learning process
- learning algorithm
- control method
- temporal difference
- pedestrian detection
- optimal policy
- state space
- autonomous navigation
- image sequences
- neural network