GOGREEN: Carbon Aware Eco-Route Optimization for Multi Vehicle Transportation

Authors:

Mr. Vishva Kiran R C1, Veerendra R2, Shreyas S3, Venkat S S4

1 Associate Professor, Department of CSE, K.S. Institute of Technology (KSIT), Bengaluru, India

2 Student, Department of CSE, K.S. Institute of Technology (KSIT), Bengaluru, India.

3 Student, Department of CSE, K.S. Institute of Technology (KSIT), Bengaluru, India.

⁴ Student, Department of CSE, K.S. Institute of Technology (KSIT), Bengaluru, India.

Email: ¹vishvakiran@ksit.edu.in , ²rveerendra244@gmail.com , ³shreyas290806@gmail.com , ⁴venkatss827@gmail.com

Abstract - Transportation systems are one of the major contributors to global carbon emissions, fuel consumption, and urban air pollution. Traditional routing systems mainly focus on minimizing travel distance or travel time without considering environmental impact, traffic congestion, or fuel efficiency. This limitation increases greenhouse gas emissions and reduces transportation sustainability, especially in large-scale logistics and multi-vehicle transportation systems. In recent years, Artificial Intelligence (AI), Machine Learning (ML), and eco-routing techniques have gained significant importance in developing intelligent and environmentally responsible transportation frameworks. This survey paper analyzes recent research works related to carbon-aware transportation systems, eco-route optimization, traffic prediction, fuel consumption estimation, and intelligent transportation management using machine learning and optimization techniques. The study reviews various approaches including Random Forest, XGBoost, Deep Learning, multi-objective optimization, and traffic-aware routing frameworks used for sustainable transportation planning. The survey identifies that most existing systems focus separately on traffic analysis, carbon emission prediction, or route optimization, while very few frameworks integrate these components into a unified intelligent transportation system. The paper highlights major research gaps including lack of integrated eco-routing frameworks, limited multi-vehicle coordination, insufficient real-time adaptive optimization, and inadequate AI-driven sustainability analysis. The survey also discusses future research directions such as deep learning-based eco-routing, reinforcement learning for transportation optimization, electric vehicle routing, and smart city transportation integration for achieving sustainable and intelligent transportation systems.

Keywords : Eco-Routing, Carbon Emission, Machine Learning, Sustainable Transportation, Route Optimization, Traffic Analysis, Intelligent Transportation Systems, Multi-Vehicle Transportation