AI-Enabled Trajectory Optimization of Logistics UAVs With Wind Impacts in Smart Cities
Bibliographic record
Abstract
AI-enabled logistics unmanned aerial vehicles (UAVs) are progressively revealing their unique advantages for future smart cities. Nevertheless, the existing research on logistics UAV path planning lacks to simultaneously consider the UAV energy consumption constraints, the customer time windows, the impacts of wind speed and direction. This omission renders the existing models inappropriate for real-world transportation systems. Besides, the UAVs are still constrained by the limited payload and battery due to the highly automatic delivery process. Consequently, we investigate the effect of wind speed and direction on UAV flight states, establishes pertinent parameters and their resolution methods impacted by wind conditions, and delves into the logistics UAV path planning issue that concurrently considers the UAV energy consumption constraints, the customer time windows, and the impact of wind conditions. To resolve the proposed trajectory optimization issue, the large-scale neighborhood search algorithm (LNS) is amalgamated with the genetic algorithm (GA), forming the GA-LNS, to address the static problem, while dynamic planning concepts are employed in the decoding process of GA-LNS to solve the dynamic trajectory optimization problem. Simulation results demonstrate that the devised algorithms yield superior solutions within a plausible timeframe, reducing distribution costs by approximately 9% in comparison to the conventional GA. Unlike the no-wind and static scenarios, path planning that incorporates dynamic wind conditions circumvents issues related to energy constraints and customer satisfaction bias evident in the prior cases. Furthermore, the proposed algorithm can provide a high-efficiency, low-energy-consumption, and low-delay UAV planning strategy in the scenario of UAV-assisted data collection.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".