AI-driven Green Logistics: Optimizing Last-mile Delivery Networks with Electric Vehicles for Carbon Neutrality in U.S. Metropolitan Areas
Bibliographic record
Abstract
The last-mile delivery process has continued to be the costliest, time-consuming, and environmentally challenging part of logistics systems, and this challenge has been further amplified in the context of quickly increasing large cities worldwide. The conventional logistics delivery chain also faces issues such as traffic congestion, increasing fuel prices, downtime, route inefficiency, and high emissions. Artificial intelligence optimization in logistics systems and electric vehicles have emerged as new approaches to improve last-mile delivery performance. The current research aims to investigate to what degree last-mile delivery can be improved by artificial intelligence optimization in routing and electric vehicles. The research followed a descriptive and analytical research study design, mainly depending on secondary sources with research data collected from peer-reviewed journals, reports published from the logistics industry, case research, and transport data published by concerned government bodies from 2018 to 2025. The data were systematically filtered to determine their appropriateness, sound methodology, measurable variables, and level of empirical research. Important variables such as delivery time, cost of delivery, distance travelled, emissions from vehicles, energy utilization, traffic congestions, and customer density were utilized for comparative analysis and cause-effect analysis. Analysis of the results shows that there was a great improvement in delivery performance through routing via artificial intelligence. The average time reduced by 34.6 percent, cost of delivery fell by 31.5 percent, and distance travelled to complete delivery reduced by 34 percent. The percentage of successful deliveries rose to 89 percent. Failed deliveries fell to less than half. The reduction in carbon dioxide emissions reached 86.6 percent for electric delivery vehicles compared to gasoline vehicles. The emissions of nitrogen oxides were eliminated entirely. Analysis of customer density indicated that areas of high density receive even greater advantages from artificial intelligence clustering and electric vehicles. The trend of congestions also indicated that predictive models of artificial intelligence result in reduced delays within peak hours. All case study comparisons among large cities across America confirmed these results. The paper concludes that combining Artificial Intelligence and electric vehicles represents a scalable, cost-efficient, and sustainable solution for last-mile delivery route optimization. The combination of these solutions improves route optimization performance and helps to avoid disruptions in last-mile delivery operations. In conclusion, it can be seen that modern cities require intelligent route optimization solutions and environmentally sustainable last-mile delivery vehicles to meet the demands of modern cities.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".