Reward Shaping-based Double Deep Q-networks for Unmanned Surface Vessel Navigation and Obstacle Avoidance.
Zihan GanJinghong ZhengZhenyu JiangRenzhi LuPublished in: IECON (2022)
Keyphrases
- obstacle avoidance
- path planning
- autonomous vehicles
- mobile robot
- reward shaping
- visual navigation
- potential field
- motion planning
- visually guided
- dynamic environments
- collision avoidance
- d objects
- multi robot
- path finding
- computational intelligence
- route planning
- bayesian networks
- underwater vehicles
- knowledge base
- machine learning