Path Optimization in Different Road Sections Based on Improved
Ant Colony Algorithm
Dan Li
Chongqing Vocational and Technical University of Mechatronics, Chongqing, China
Keywords: Swarm Foraging Theory, Improved Ant Colony Algorithm, Segments, Low-Carbon Logistics, Path
Optimization.
Abstract: The traditional ant colony algorithm has certain limitations to solve the path optimization problem, and its
effect is relatively unsatisfactory. In the context of sustainable development, low-carbon logistics has become
an inevitable trend in the development of the modern logistics industry. Traditional logistics and distribution
often ignore the environmental impact of transportation, resulting in wasted energy and increased CO2
emissions. In order to meet this challenge, researchers and logistics companies are looking for innovative
solutions, and intelligent algorithms provide an efficient way. This paper will focus on how to optimize low-
carbon logistics paths in different road sections through improved ant colony algorithms.
1 INTRODUCTION
As a highly cooperative creature in nature, ants'
ability to search for food inspired computer scientists
to simulate their behavior, and then developed the
famous Ant Colony Optimization (ACO) algorithm
(Zhou and Xu, 2023). In the field of logistics, the
algorithm is used to solve the Vehicle Routing
Problem (VRP) to reduce logistics costs and improve
efficiency (Zhao, 2021). However, in pursuing low-
carbon goals, we must not only focus on cost and
efficiency, but also on the carbon footprint of the
entire distribution process (Li Yanzhen,2023).
2 RELATED CONCEPTS
2.1 Improved Mathematical
Description of the Ant Colony
Algorithm
In response to this demand, an improved ant colony
algorithm came into being. The core of the algorithm
is to simulate the behavior of ants releasing
pheromones, so that the concentration of pheromones
on the optimal path is gradually increased, and the
subsequent ants are guided to choose these paths, so
as to find the optimal solution (Zhang and Huang,
2021). The improved ant colony algorithm adds the
consideration of carbon emissions on the basis of the
traditional model (Liu and Gu, et al. 2023), so that the
algorithm not only considers the length of the path
and the economic cost, but also takes into account the
environmental benefits.
2
4
lim( ) max( 2)
2
iij ij ij
x
bb ac
yt y t
a
→∞
−± −
⋅= ≥ ÷
(1
)
The judgment of outliers is shown in Equation (2).
()
2
1!
max( ) ( 2 ) ( 4)
2! !
ij ij ij ij
n
ttt t
rnr
=∂ + ⋅ +
−


M
(2
)
Specifically, the improved algorithm introduces a
carbon footprint assessment function into the
pheromone update mechanism, and comprehensively
calculates the carbon emissions of each road section
according to the traffic conditions, road slopes,
vehicle types and other factors of different road
sections (Zhang and Wu, et al. 2022). In the process
of algorithm execution, it is more inclined to choose
those path segments with low carbon emissions, so as
to gradually screen out the logistics routes with the
smallest overall carbon emissions (Jiang and Gao, et
al. 2021). In addition, the algorithm can dynamically
adjust the rate of pheromone evaporation and
accumulation to adapt to changing road conditions
and environmental requirements.
74
Li, D.
Path Optimization in Different Road Sections Based on Improved Ant Colony Algorithm.
DOI: 10.5220/0013535700004664
Paper published under CC license (CC BY-NC-ND 4.0)
In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 74-79
ISBN: 978-989-758-763-4
Proceedings Copyright © 2025 by SCITEPRESS – Science and Technology Publications, Lda.

2
4
() 2
7
2
iii
bb ac
F
dty
a
ξ
−± −
=⋅→⋅




(3)
2.2 Selection of Logistics Route
Optimization Scheme
Through this intelligent method, logistics companies
can effectively avoid high-pollution areas, reduce
unnecessary detours, and choose greener driving
routes on the premise of meeting the delivery
timeliness (Wang, 2021). This not only helps
enterprises establish the brand image of green
logistics, but also has great significance for
alleviating urban traffic pressure and improving
urban air quality.
𝑔(𝑡

)=𝑥

⋅𝑧

𝐹(𝑑

)
𝑑𝑦
𝑑𝑥
−𝑤

𝛫
𝛥𝑦
𝛥
𝑥
(4
)
It is worth mentioning that the improved ant
colony algorithm is also suitable for complex logistics
networks with multiple warehouses and distribution
points, which can flexibly deal with logistics path
optimization problems of various scales and types,
and provide a scientific basis for logistics planning.
𝑙𝑖𝑚
→
∞
𝑔(𝑡

)+𝐹(𝑑

)≤
𝑑𝑦
𝑑𝑥
𝑚𝑎𝑥(𝑡

)
(5
)
With the continuous iterative upgrading of
algorithms, real-time dynamic optimization can even
be realized in the future to respond to the needs of
emergencies or temporary changes.
𝑔(𝑡

)+𝐹(𝑑

)

↔𝑚𝑒𝑎𝑛(𝑡

+4)
(6
)
2.3 Analysis of Logistics Path
Optimization Scheme
In conclusion, the improved ant colony algorithm
opens a path to green logistics for us. On this path,
scientific and technological innovation and
environmental protection go hand in hand and
complement each other (Jin and He, et al. 2021). With
the maturity of technology and the popularization of
applications, we look forward to seeing more logistics
companies join the ranks of low-carbon logistics,
jointly promote the green development of the logistics
industry, and create a more sustainable future.

2
() ( )
()
(4)
ii
i
ij
gt Fd
No t
mean t u v
+
∂Ω
=
+∂∂

(7
)

() ( )
1
(4)
ii
ij
gt Fd
mean t
+
≤
+

Conclusion: Green
logistics is not only related to the sustainable
development of an enterprise, but also the
embodiment of social responsibility and
environmental friendliness.
𝑍ℎ(𝑡

)=

[𝑔(𝑡

)+𝐹(𝑑

)

]
(8
)
Through the improved ant colony algorithm, it has
become possible to optimize low-carbon logistics
routes, so that we can work together towards a more
environmentally friendly logistics era, reduce the
burden on the planet, and add greenery to the future.
𝑎𝑐𝑐𝑢𝑟(𝑡

)=
𝑚𝑖𝑛[
∑
𝑔(𝑡

)+𝐹(𝑑

)

]
√
𝑎

+𝑏

∑
𝑔(𝑡

)+𝐹(𝑑

)

×100%
(9
)
In today's society that pursues sustainable
development, reducing carbon emissions has become
one of the goals of all walks of life. As the main
source of global carbon dioxide emissions, the path
optimization of transportation is not only related to
logistics costs, but also closely related to
environmental protection (Xing and Yan, et al. 2021).
Traditional path optimization methods often ignore
environmental factors, while modern intelligent
algorithms, such as ant colony algorithms, provide a
solution that is both energy-efficient and efficient
(Wu and Hu, 2022). In this paper, we will discuss how
to improve the ant colony algorithm to achieve low-
carbon path optimization.
𝑎𝑐𝑐𝑢𝑟(𝑡

)=
𝑚𝑖𝑛[
∑
𝑔(𝑡

)+𝐹(𝑑

)

]
√
2
∑
𝑔(𝑡

)+𝐹(𝑑

)

(10
)
First, we need to understand what ant colony
algorithms are. Simulating the way ants find food
paths in nature, this heuristic algorithm is able to
evolve through a positive feedback mechanism to find
the shortest path. Ants release pheromones as they
travel, and other ants choose paths based on
pheromone concentrations, resulting in an optimal
path (Tang and Tang, et al. 2021). However, the
traditional ant colony algorithm may fall into the local
optimal solution when dealing with complex
networks, and it has the disadvantage of low
efficiency for multi-objective optimization problems.
Path Optimization in Different Road Sections Based on Improved Ant Colony Algorithm
75

3 OPTIMIZATION STRATEGY
FOR LOGISTICS ROUTE
OPTIMIZATION
To overcome these limitations, the researchers
proposed an improved ant colony algorithm. These
improvements include the introduction of heuristics
to guide the search process, adaptive adjustment of
pheromone evaporation rate, and reinforcement
learning strategies (Chen and Liu, 202). These
improvements allow the algorithm to find solutions in
a wider search space, while speeding up convergence
and reducing the risk of falling into local optimums
(Wang, 2021).
3.1 Introduction to the Optimization of
Logistics Routes
In low-carbon path optimization, we need to consider
not only the length of the path, but also the energy
consumption of the vehicle, the environmental impact
of the route, and possible congestion.
Table 1: Logistics route optimization requirements.
Scope of
application
Grade Accuracy
Logistics
route
optimization
Indra-city
logistics
I 87.21 91.16
II 88.43 89.37
Long-distance
logistics and
transportation
I 89.18 89.25
II 94.40 90.98
Multi-modal
logistics and
trans
p
ortation
I 91.42 89.07
II 93.16 87.44
The logistics route optimization process in Table
1 is shown in Figure 1.
The improved ant colony algorithm can take these
factors into account and evaluate the comprehensive
cost of different paths through multi-dimensional
evaluation functions. For example, algorithms can
give higher cost values to high-carbon emission
pathways, thereby inducing the search process to
Improve the
colony
Analyse
Path
optimization
Group
foraging
Discuss
Railway
Low carbon
logistics
Figure 1: The analysis process of logistics route
optimization.
favor low-carbon and environmentally friendly
choices.
3.2 Optimization of Logistics Routes
Furthermore, combined with real-time traffic data and
weather forecast information, the improved ant
colony algorithm can dynamically adjust the path
planning to avoid additional energy consumption and
delays caused by traffic congestion or bad weather.
This dynamic adaptability is incomparable to
traditional static path planning.
Table 2: The overall picture of the logistics route
optimization scheme.
Category Random
data
Reliability Analysis
rate
Indra-city
logistics
90.40 92.89 87.33
Long-distance
logistics and
trans
p
ortation
90.63 90.27 90.04
Multi-modal
logistics and
transportation
88.17 88.98 89.91
Mean 92.23 89.64 89.18
X6 87.82 91.11 91.99
P=1.249
3.3 Logistics Path Optimization and
Stability
In addition, the improved ant colony algorithm can
also be used for charging station planning for electric
vehicles. By analyzing the user's driving habits and
charging needs, the algorithm can arrange the most
reasonable charging stations in the city, reduce the
detour caused by the lack of battery life of electric
vehicles, and reduce the overall carbon emissions at
the macro level.
In the field of modern logistics, efficient path
optimization is not only a key part of cost control, but
also an important means to improve service quality
and win market competitiveness. With the continuous
development of artificial intelligence technology,
more and more intelligent algorithms are applied to
logistics route optimization.
INCOFT 2025 - International Conference on Futuristic Technology
76

Figure 2: Logistics route optimization with different
algorithms.
Table 3: Comparison of the accuracy of logistics route
optimization of different methods
Algorithm
Survey
data
Logistics
route
optimization
Magnitude
of change
Error
Improving
the ant
colony
al
g
orith
m
93.35 89.80 91.80 90.46
Ant
colony
algorith
m
91.36 88.68 91.95 89.40
P 92.97 87.39 91.73 92.63
In summary, through the improvement of the ant
colony algorithm, we can achieve low-carbon path
optimization more effectively. This not only helps to
reduce environmental pollution and energy
consumption, but also improves the efficiency of
logistics and transportation. Of course, any algorithm
has its limitations, and improved ant colony
algorithms also need to be constantly tested and tuned
in practice. In the future, with the continuous progress
of computing technology and the increasing
abundance of environmental data, we have reason to
believe that the improved ant colony algorithm will
play a more critical role in the field of low-carbon
path optimization and contribute a green intelligent
force to our earth.
Figure 3: Improved logistics path optimization of ant
colony algorithm.
The core of the ant colony algorithm is to simulate the
behavior of ants by releasing and sensing pheromones
to find food sources and ultimately find the shortest
path. In the process of logistics route optimization, we
can consider the distribution point of goods as a food
source, and the route of goods from the warehouse to
each distribution point can be analogous to the path
of ants looking for food. Each virtual "ant" represents
a potential solution, they choose the path according to
the intensity of the pheromone, and leave a certain
amount of pheromone as they pass through the path,
and over time, the pheromones on the shorter path
will become stronger and stronger, thus guiding more
"ants" to choose this path, forming a positive
feedback process, gradually converging to the
optimal or approximate optimal solution.
3.4 The rationality of Logistics Route
Optimization
However, there are still some shortcomings in the
practical application of the traditional ant colony
algorithm, such as slow convergence speed and easy
to fall into local optimum. Therefore, the
improvement of the traditional ant colony algorithm
is the key to improve its performance in logistics
route optimization applications.
Path Optimization in Different Road Sections Based on Improved Ant Colony Algorithm
77

Figure 4: Logistics route optimization with different
algorithms.
For example, we can introduce the crossover and
mutation mechanisms from genetic algorithms into
ant colony algorithms to increase search diversity and
jump out of local optimal solutions. In addition, the
hybrid algorithm strategy can be used to further
improve the global search ability and efficiency of the
algorithm by combining the advantages of particle
swarm optimization and simulated annealing.
3.5 Effectiveness of Logistics Route
Optimization
At the same time, according to the needs of specific
logistics scenarios, the ratio of pheromone
volatilization coefficient and heuristic information
can also be customized to adapt to different
optimization goals and constraints.
Figure 5: Logistics route optimization with different
algorithms.
Improvement strategies typically include
adjusting pheromone update rules, introducing
heuristics to guide search directions, and
incorporating other optimization algorithms.
Table 4: Comparison of the effectiveness of logistics route
optimization of different methods.
Algorithm Survey
data
Logistics
route
optimization
Magnitude
of change
Error
Improving
the ant
colony
al
g
orith
m
86.38 93.10 92.94 87.83
Ant
colony
algorith
m
88.52 90.91 88.00 90.37
P 89.53 89.57 90.08 89.46
In the context of big data and the Internet of
Things, real-time dynamic optimization is possible.
By collecting real-time data such as vehicle location,
traffic conditions, and weather forecasts, the
pheromone distribution can be dynamically adjusted,
so that the ant colony algorithm can respond to real-
time changes and provide a more flexible and
accurate path optimization scheme. This real-time
and dynamic application can not only reduce delays
caused by unexpected situations such as traffic
congestion, but also predict and avoid possible risks
in the future to a certain extent, and ensure the
efficiency and safety of logistics and transportation.
Figure 6: Improved ant colony algorithm logistics path
optimization.
Among them, ant colony algorithm, as a heuristic
algorithm that simulates the foraging behavior of ants
in nature, has shown great potential and unique
advantages in logistics path optimization with its
unique pheromone communication mechanism and
parallel search ability.
INCOFT 2025 - International Conference on Futuristic Technology
78

4 CONCLUSIONS
In conclusion, through the continuous improvement
and innovation of traditional ant colony algorithms,
we are expected to develop more efficient and
intelligent logistics route optimization tools. These
improvements not only improve the performance of
the algorithm, but also broaden its application
scenarios, so that the logistics industry can better
adapt to the rapidly changing market demand, realize
the optimal allocation of resources, and ultimately
promote the progress and development of the entire
industry.
REFERENCES
Chen Jing, & Liu. (2021). Research on the optimization of
cold chain logistics path based on ant colony algorithm.
Transportation Technology and Economy, 23 (5), 7.
Li Yanzhen. (2023). Research on the optimization of the
low-carbon distribution path of the fresh e-commerce
cold chain based on the ant colony algorithm. Journal
of Tianjin Vocational University, 32 (2), 76-83.
Liu Jianguo, Gu Xiaoyan, Chen Liang, & Chen Mengtong.
(2023). Study on grazing path optimization based on an
improved ant colony algorithm. computer simulation.
Jiang Fangtao, Gao Yajing, Zhang Chong, Jiang Haoyang,
& Yang Naiyu. (2021). Optimization of cold chain
logistics transportation path based on ant colony
algorithm —— Take f company as an example.
Computer Knowledge and Technology: Academic
Edition.
Wang Zhiyi. (2021). Research on ship path planning
technology based on improved ant colony algorithm.
(Doctoral dissertation, Harbin Engineering University).
Jin Juting, He Weijie, Xu Changyuan, Zhang Junyao, & Dai
Dan. (2021). Research on optimization of logistics
distribution path based on improved ant colony
algorithm. Shopping mall modernization (10), 3.
Xing Shubao, Yan Xiujuan, & Bai Zongwen. (2021).
Planning and design of logistics distribution path in
leather market based on ant colony algorithm ——
Evaluation Research on optimization of Logistics
Distribution System in Metropolitan isa. Leather
Science and Engineering.
Wu Jiming, & Hu Changsheng. (2022). Study on
optimization of intercity cargo transport path based on
improved ant colony algorithm. Journal of Changchun
Institute of Engineering: Natural Science Edition, 23
(4), 109-112.
Tang Huiling, Tang Hengshu, & Zhu Xingliang. (2021).
Research on low-carbon vehicle path problem based on
improved ant colony algorithm. Chinese Management
Science (007), 029.
Wang Yu. (2021). Research on the optimization method of
aviation logistics distribution path based on ant colony
algorithm. Information Technology (011), 000.
Zhang Danlu, & Huang Xianghong. (2021). Research on
logistics path optimization based on improved ant
colony algorithm —— Take the logistics network in
Henan Province as an example. Journal of Henan
University of Technology (Social Science Edition), 037
(002), 56-60,96.
Zhang Guijun, Wu Chuxiong, Chen Chi, Sun Huzeng, Yuan
Fengqiao, & Li Yuanfeng. (2022). A multi-distribution
center vehicle path optimization method based on an
improved ant colony algorithm. CN201910763723.X.
Zhao Jiangli. (2021). Optimize the site selection system
design of the low-carbon logistics distribution center
based on the improved ant colony algorithm. Modern
electronic technology, 44 (13), 5.
Zhou Yuxuan, & Xu Wei. (2023). The application of
improved ant colony algorithm in the optimization of
low-carbon cold chain logistics path. Logistics
technology, 42 (5), 105-110.
Path Optimization in Different Road Sections Based on Improved Ant Colony Algorithm
79