Emergency-Response Locomotion of Hexapod Robot with Heuristic Reinforcement Learning Using Q-Learning.
Ming-Chieh YangHooman SamaniKening ZhuPublished in: ICR (2019)
Keyphrases
- emergency response
- reinforcement learning
- legged robots
- real robot
- robot control
- mobile robot
- function approximation
- information sharing
- reinforcement learning algorithms
- decision making
- dynamic programming
- state space
- decision support
- model free
- public safety
- decision makers
- rough terrain
- robotic systems
- situational awareness
- optimal policy
- action selection
- multi agent
- markov decision processes
- emergency medical services
- robot moves
- central pattern generator
- temporal difference
- government agencies
- exploration strategy
- learning algorithm
- reinforcement learning methods
- humanoid robot
- inverted pendulum
- stochastic approximation
- inter organizational
- machine learning
- multi robot
- data mining
- learning agent
- virtual organization
- cumulative prospect theory
- databases