Dynamic-TD3 models UAV navigation as a constrained Markov decision process, using an adaptive trajectory mechanism and a physically aware Kalman filter to achieve better collision avoidance, lower energy use, and smoother paths than prior methods in dynamic obstacle scenarios.
Champion-level drone racing using deep reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction
Dynamic-TD3 models UAV navigation as a constrained Markov decision process, using an adaptive trajectory mechanism and a physically aware Kalman filter to achieve better collision avoidance, lower energy use, and smoother paths than prior methods in dynamic obstacle scenarios.