A monocular, edge-deployable reinforcement learning system lets fixed-wing UAVs avoid unknown obstacles at cruise speed, with modest success-rate gains over PPO baselines in simulation.
Cooperative sensing enhanced uav path-following and obstacle avoidance with variable formation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Monocular Obstacle Avoidance Based on Inverse PPO for Fixed-wing UAVs
A monocular, edge-deployable reinforcement learning system lets fixed-wing UAVs avoid unknown obstacles at cruise speed, with modest success-rate gains over PPO baselines in simulation.