Dynamic robot routing optimization: State-space decomposition for operations research-informed reinforcement learning.
Marlon LöppenbergSteve YuwonoMochammad Rizky DiprasetyaAndreas SchwungPublished in: Robotics Comput. Integr. Manuf. (2024)
Keyphrases
- state space
- reinforcement learning
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- dynamic programming
- mobile robot
- real robot
- optimization algorithm
- heuristic search
- dynamic optimization
- routing protocol
- robot control
- dynamical systems
- continuous state spaces
- dynamic environments
- optimization problems
- goal state
- robot navigation
- action space
- model free
- state abstraction
- state variables
- machine learning
- computer science
- multi agent
- function approximation
- perceptual aliasing
- changing environment
- routing problem
- robotic systems
- ad hoc networks
- path planning
- particle filter
- vision system
- markov decision problems
- learning algorithm
- reward shaping
- logistics distribution
- vehicle routing
- partially observable
- belief state
- reward function
- action selection
- human robot interaction
- multi robot
- routing algorithm
- shortest path