Green and Intelligent Planning of Drone Launch in Truck-Drone Collaborative Delivery
Bibliographic record
Abstract
The Internet of Things (IoT) paradigm has enabled innovative applications across various domains, significantly enhancing efficiency in the transportation sector through intelligence-driven and sustainable solutions. In the field of parcel delivery, the integration of trucks and drones has attracted considerable attention from both academia and industry as a means to optimize logistics networks and reduce last-mile delivery costs. Traditionally, research on truck-drone collaborative delivery (TDCD) has focused on routing and scheduling problems within hypothetical scenarios. This study, however, seeks to address the problem using a more realistic approach by introducing a newly generated customer order dataset, which includes data from 191 customer locations over a span of 7 days. The goal is to evaluate the efficiency of drone deliveries assisted by trucks. Utilizing this dataset, we applied the Self-Organizing Feature Map (SOFM) algorithm, a type of artificial neural network, to the TDCD problem. This novel approach identifies the optimal location for truck-based drone launches to minimize overall travel distance. Thanks to its adaptive nature, the SOFM algorithm dynamically selects the launch location based on daily customer orders rather than relying on a static, predetermined site. This method has resulted in a 4.4% reduction in the total distance traveled by drones and a $\mathbf{1. 1 \%}$ reduction in the distance covered by trucks over the seven-day period. These efficiencies translate into savings of $30.28 \mathrm{gCO2}$ in carbon emissions and 80.16 Wh of energy consumption, equivalent to 288.58 Kjoules.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".