Reducing traffic energy consumption is crucial for smart cities, and vehicle carbon emissions are a key energy indicator. Traffic signal control (TSC) is a useful method because it can affect the energy consumption of vehicles on the road by controlling the stop-and-go of vehicles at traffic intersections. However, setting traffic signals to reduce energy consumption will affect traffic efficiency and this is not in line with traffic management objectives. Current studies adopt multi-objective optimization methods with high traffic efficiency and low carbon emissions to solve this problem. However, most methods use static weights, which cannot adapt to complex and dynamic traffic states, resulting in non-optimal performance. Current energy indicators for urban transportation often fail to consider passenger fairness. This fairness is significant because the purpose of urban transportation is to serve people’s mobility needs not vehicles. Therefore, this paper proposes Multi-objective Adaptive Meta-DQN TSC (MMD-TSC), which introduces a dynamic weight adaptation mechanism to simultaneously optimize traffic efficiency and energy saving, and incorporates the per capita carbon emissions as the energy indicator. Firstly, this paper integrates traffic state data such as vehicle positions, velocities, vehicle types, and the number of passengers and incorporates fairness into the energy indicators, using per capita carbon emissions as the target for reducing energy consumption. Then, it proposes MMD-TSC with dynamic weights between energy consumption and traffic efficiency as reward functions. The MMD-TSC model includes two agents, the TSC agent and the weight agent, which are responsible for traffic signal adjustment and weight calculation, respectively. The weights are calculated by a function of traffic states. Finally, the paper describes the design of the MMD-TSC model learning algorithm and uses a SUMO (Simulation of Urban Mobility) v.1.20.0 for traffic simulation. The results show that in non-highly congested traffic states, the MMD-TSC model has higher traffic efficiency and lower energy consumption compared to static multi-objective TSC models and single-objective TSC models, and can adaptively achieve traffic management objectives. Compared with using vehicle average carbon emissions as the energy consumption indicator, using per capita carbon emissions achieves Pareto improvements in traffic efficiency and energy consumption indicators. The energy utilization efficiency of the MMD-TSC model is improved by 35% compared to the fixed-time TSC.
With the enhanced interoperability of information among vehicles, the demand for collaborative sharing among vehicles increases. Based on blockchain, the classical consensus algorithms in collaborative IoV (Internet of Vehicle), such as PoW (Proof of Work), PoS (Proof of Stake), and DPoS (Delegated Proof of Stake), only consider the node features, which is hard to adapt to the immediacy and flexibility of vehicles. On the other hand, classical consensus algorithms often require mass computing, which undoubtedly increases the communication overhead, resulting in the inability to achieve collaborative IoV under asymmetric networks. Therefore, proposing a low failure rate consensus algorithm that takes into account running time and energy consumption becomes a major challenge in IoV applications. This paper proposes an AI-enabled consensus algorithm with vehicle features, combining vehicle-based metrics and neural networks. First, we introduce vehicle-based metrics such as vehicle online time, performance, and behavior. Then, we propose an integral model and a hierarchical classification method, which combine with a BP neural network to obtain the optimal solution for interconnection. Among them, we also use Informer to predict the future online duration of vehicles, which effectively solves the situation that the primary node vehicle drops off in collaborative IoV. Finally, the experimentations show that the vehicle-based metrics eliminate the problem of the primary node vehicle being offline, which realizes the collaborative IoV considering vehicle features. Meanwhile, it reduces the vehicle network system delay and energy consumption.
Green navigation presents a challenge to sustainable mobility. Carbon emissions are a key indicator for evaluating the sustainability of a route. Some methods of green navigation consider the fastest and shortest route to be the least carbon-emitting option, solely from the driver’s perspective. To address this issue, various studies have incorporated road factors into the sustainability evaluation model and designed static route planning algorithms to minimize carbon emissions. However, there has been no comprehensive analysis of carbon emissions from both the road and the driver perspectives, and the influence of a sustainability evaluation using dynamic traffic states has not been considered. In this paper, we propose a carbon emission evaluation model based on the life cycle assessment (LCA) and a dynamic route planning algorithm that focuses on near-real-time traffic states. First, we develop an evaluation model for carbon emissions from both the road and the driver perspectives using a carbon footprint measurement method. Next, we propose a route planning method with both a static calculation and near-real-time adjustment to minimize carbon emissions. Finally, we select three cases from South China with different characteristics to verify the effectiveness of our model and algorithm. This evaluation model calculates the carbon emissions caused by all parties involved, providing a comprehensive assessment of the total carbon emissions generated by traffic. This approach addresses the problem of traditional route planning, which often fails to account for the influences of variable traffic conditions on the greenest route. We verify the effectiveness of the greenest navigation algorithm and near-real-time green navigation and apply these two aspects to cases where the greenest route is compared with other common navigation results from different dimensions. We compare carbon emissions from vehicles and roads from electric vehicles and gasoline-powered vehicles. If an electric vehicle is equipped with a wind power generator, the proportion of the vehicle’s carbon emissions will be very small. For other vehicle types, the carbon emissions will be more than 1000 times the road emissions.
Small object detection remains a challenge in computer vision due to low pixel occupancy, feature scarcity, and susceptibility to background interference. Conventional single-backbone networks often struggle to balance deep semantic extraction with the preservation of shallow details. Deep down-sampling can lead to the loss of edge and texture information, while late-stage fusion may fail to recover these details effectively. To address these limitations, this paper proposes a Cross-Stage Fusion Network with a Dual Backbone (CSF-Net). Our network employs an asymmetric design: a shallow backbone maintains a higher resolution to preserve fine-grained details, while a deep backbone extracts contextual semantics. These two streams interact via progressive cross-stage connections, facilitating the early fusion of small object information. Experiments on the Micro RGB UAV dataset indicate that CSF-Net improves the mAP of the YOLOV8 baseline from 62.8% to 67.0%, validating the effectiveness of the proposed architecture in enhancing detection performance for small targets.