Speed Planning Based on Terrain-Aware Constraint Reinforcement Learning in Rugged Environments.
Andong YangWei LiYu HuPublished in: IEEE Robotics Autom. Lett. (2024)
Keyphrases
- reinforcement learning
- action selection
- uncertain environments
- multiresolution
- function approximation
- real time
- deterministic domains
- high speed
- stochastic domains
- rough terrain
- complex domains
- partially observable
- planning problems
- real world
- three dimensional
- partial observability
- reinforcement learning algorithms
- markov decision processes
- dynamic programming
- reinforcement learning problems
- multi agent environments
- learning algorithm
- macro actions
- planning process
- partially observable markov decision processes
- single agent
- learning process
- search space
- multi agent
- partially observable domains
- plan generation
- temporal difference
- autonomous robots