A path planning strategy for marine vehicles based on deep reinforcement learning and data-driven dynamic flow fields prediction.
Qiming SangYu TianQianlong JinJiancheng YuPublished in: CACRE (2021)
Keyphrases
- path planning
- data driven
- flow field
- dynamic environments
- autonomous vehicles
- reinforcement learning
- mobile robot
- path planning algorithm
- optic flow
- multi robot
- collision avoidance
- optical flow
- collision free
- obstacle avoidance
- unmanned aerial vehicles
- optimal path
- potential field
- optical flow estimation
- motion planning
- optical flow fields
- motion field
- multiple robots
- dynamic and uncertain environments
- fluid motion
- motion parameters
- motion analysis
- image sequences
- robot path planning
- motion segmentation
- motion detection
- configuration space
- real robot
- ground vehicles
- machine learning