Monocular Reactive Collision Avoidance for MAV Teleoperation with Deep Reinforcement Learning.
Raffaele BrilliMarco LegittimoFrancesco CrocettiMirko LeomanniMario Luca FravoliniGabriele CostantePublished in: ICRA (2023)
Keyphrases
- collision avoidance
- reinforcement learning
- path planning
- mobile robot
- dynamic environments
- image sequences
- ground vehicles
- visual navigation
- path finding
- pose estimation
- fuzzy neural network
- learning algorithm
- state space
- dynamic programming
- collision free
- machine learning
- motion planning
- robotic arm
- formation control
- optical flow
- stereo camera
- real robot
- real time