Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning.
Zhehui HuangZhaojing YangRahul KrupaniBaskin SenbaslarSumeet BatraGaurav S. SukhatmePublished in: ICRA (2024)
Keyphrases
- end to end
- collision avoidance
- visual navigation
- reinforcement learning
- formation control
- path planning
- collision free
- mobile robot
- dynamic environments
- obstacle avoidance
- particle swarm optimization
- congestion control
- autonomous navigation
- real robot
- state space
- path finding
- admission control
- outdoor environments
- image sequences
- internet protocol
- learning algorithm
- fuzzy neural network
- motion estimation
- search space
- artificial neural networks