Uav path planning optimization strategy: considerations of urban morphology, microclimate, and energy efficiency using q

Of 34 Scenari Simple Q-learning -greedy decay SARSA START TARGET OBSTACLE Path planing Simple Q-learning Path planing -greedy decay Path planing SARSA COLLISION UAV path analyze wind speed Simple Q-learning -greedy decay SARSA Wind Speed (m/s) 21 of 34 Scenari Simple Q-learning -greedy decay SARSA START TARGET OBSTACLE Path planing Simple Q-learning Path planing -greedy decay Path planing SARSA COLLISION 0 0 UAV path analyze wind speed Simple Q-learning -greedy decay SARSA Wind Speed (m/s) 22 of 34 Scenari Simple Q-learning -greedy decay SARSA START TARGET OBSTACLE Path planing Simple Q-learning Path planing -greedy decay Path planing SARSA COLLISION UAV path analyze wind speed Simple Q-learning -greedy decay SARSA Wind Speed (m/s) 23 of 34 Scenari Simple Q-learning -greedy decay SARSA START TARGET OBSTACLE Path planing Simple Q-learning Path planing -greedy decay Path planing SARSA COLLISION 0 UAV path analyze wind speed Simple Q-learning -greedy decay SARSA Wind Speed (m/s) 24 of 34 Scenari Simple Q-learning -greedy decay SARSA START TARGET OBSTACLE Path planing Simple Q-learning Path planing -greedy decay Path planing SARSA COLLISION UAV path analyze wind speed Simple Q-learning -greedy decay SARSA Wind Speed (m/s) 25 of 34 6. The complexity of the path taken by UAVs 5, 9, 12, 14, and 15 SARSA has approached the naive solution, which makes this strategy less attentive to changes in the scenario compared to others that identify high-speed zones from the wind, making it a less efficient solution than Simple Q-learning and e-greedy decays. Of 34 Naive SARSA Q-learning with Compared to Simple Q-learning (only obstacle) Compared to naive solution Naive SARSA Q-learning with Compared to Simple Q-learning (only obstacle) Compared to naive solution 29 of 34 @@