Search for: All records

California has set a goal for all drayage trucks operating in the state to be zero-emitting by 2035. In order to achieve this goal, drayage operators would need to transition 100% of their Heets to zero-emission vehicles such as battery electric trucks (BETs). This article presents an intelligently controlled charging model for BETs that minimizes charging costs while optimizing subsequent tour completion. To develop this model, real-world activity data from a drayage truck Heet operating in Southern California was combined with a two-stage clustering technique to identify trip and tour patterns. The energy consumption for each trip and tour was then simulated for BETs with a battery capacity of 565 kWh using a 150 kW charging power level. Home base charging load profiles were generated using the proposed charging model, subject to constraints of the energy needed to complete the next subsequent tour and Time-of-Use energy cost rates. A sensitivity analysis evaluated three scenarios: a passive scenario with a 5% state-of-charge (SOC) constraint after completing the subsequent tour, an average scenario with a 50% SOC constraint, and an aggressive scenario with an 80% SOC constraint. Results indicated that the 80% SOC constraint scenario achieved the lowest charging cost. However, it also yielded the lowest tour completion rate (51%). In contrast, the 5% SOC constraint scenario registered the highest tour completion rate. These results revealed that 96% of the tours could be successfully completed using the intelligently controlled charging model. The remaining tours were infeasible, indicating that the available time at the home base was inadequate for charging the necessary energy for the next tour. In terms of total costs, the scenario with a 5% SOC constraint resulted in an annual cost of approximately $40,000, whereas the 80% SOC scenario nearly doubled that amount. 

In this paper, we examine the problem of the Dilemma Zone (DZ) in depth, weaving together the various influences that span the environment, the ego-vehicle, and ultimately the characteristics of the driver. Driver behavior in dilemma zone situations is crucial, and more research is urgently needed in this area. The journey through various modeling approaches and data acquisition techniques sheds new light on driver behavior within the dilemma zone context. Our thorough examination of the current research landscape has revealed that several significant areas remain overlooked. As well as the dynamic impact of vehicles, vehicle interactions, and a strong tendency to over-rely on infrastructure information, there are also concerns about the lack of comprehensive evaluation tools. However, we do not see these gaps as stumbling blocks, but rather as steppingstones for future research opportunities. A more focused study of cooperative solutions is required considering the potential of personalized modeling, the untapped power of machine learning techniques, and the importance of personalized modeling. It is our hope that by embracing innovative approaches that can capture and simulate personalized behavioral data using “everything-in-the-loop” simulations, future research endeavors will be guided. To effectively mitigate the DZ problem, we also point out the research gaps and opportunities for further research in the DZ. 

Exclusive bus lane strategy is widely adopted in many cities to improve bus operation effciency and reliability. With the development of connected vehicle technologies, the dynamic bus lane (DBL) strategy was proposed, with allowing general vehicles to share use of the bus lane to improve traffc effciency in general purpose lanes (GPLs). Previous studies have rarely considered the eco-driving strategy of connected and automated vehicles/buses (CAVs/CABs) in GPLs under the mixed traffc conditions, and how to ensure bus priority with DBL control. In this study, a novel DBL control strategy was developed under the partially connected vehicle environment. A trajectory planning method while considering the joint effects of bus stop and signal phase for CAB was adopted, an eco-driving strategy for CAVs in GPL was proposed using a trigonometry trajectory planning method. And a novel DBL control method was established by integrated trajectory planning for both the CAVs and CABs to ensure bus operation priority. Numerical experiments were conducted to evaluate performance of the proposed novel DBL control in terms of travel time and energy consumption of general vehicles at the different levels of CAV market penetration rates (MPRs). Results indicated that about 16%-42% energy savings can be achieved with MPR varying from 20% to 100%, and the travel time can be improved by about 4%-10%. Meanwhile, sensitivity analysis was conducted to quantify the impacts of key parameters, including vehicle target speeds, heterogeneous traffc fow, random arrival interval of cars, position of bus stop, traffc volume in GPL 

Isolated actuated signalized intersection is a pressing challenge for conventional eco-approach methods, due to the ever-changing signal timing strategy. This research proposes an optimal control based eco-approach method tailored to tackle this challenge. The proposed method bears the following features: i) capable of predicting the ever-changing actuated signal timing; ii) with enhanced fuel efficiency via proactively catching a feasible passing time window; iii) with real-time computation efficiency for implementation. Simulation results demonstrate that the proposed method enhances fuel efficiency by 9.1%, reduces stop count by 14.8%, and enhances safety performance by 317.14%, compared to conventional human-driven vehicles. The passing time window predic- tion capability is confirmed with an accuracy of 3.1 s. All the aforementioned benefit is at a cost of a minimal travel time increase of 5.5 s. Moreover, the average computation time of the proposed method is 12 ms, demonstrating its readiness for field implementation. 

The emerging prevalence of electric vehicles (EVs) in shared mobility services has led to a groundbreaking trend for decarbonizing the shared mobility sector. However, it is still unclear how to maximize the efficiency of EVs to reduce greenhouse gas (GHG) emissions while maintaining high service quality, particularly considering the ongoing transition towards a fully electrified service fleet. In this paper, focusing on meal delivery, we proposed an eco-friendly on-demand meal delivery (ODMD) system to maximize the utilities of EVs to mitigate GHG emissions and maintain low operational cost and delay cost. The main feature of our system is that its fleet consists of electric and gasoline vehicles mirroring the evolving electrification trend in the shared delivery sector. A rolling horizon framework integrated with the adaptive large neighborhood search (RHALNS) algorithm was proposed to efficiently solve the meal order dispatching and routing problem with the mixed fleet. Three delivery policies were explored in the numerical study. Experiment results demonstrated that it is necessary for online meal delivery platforms to actively collect information of electric vehicles and take initiative to employ an eco-friendly delivery policy. 

Interest in cooperative perception is growing quickly due to its remarkable performance in improving perception capabilities for connected and automated vehicles. This improvement is crucial, especially for automated driving scenarios in which perception performance is one of the main bottlenecks to the development of safety and efficiency. However, current cooperative perception methods typically assume that all collaborating vehicles have enough communication bandwidth to share all features with an identical spatial size, which is impractical for real-world scenarios. In this paper, we propose Adaptive Cooperative Perception, a new cooperative perception framework that is not limited by the aforementioned assumptions, aiming to enable cooperative perception under more realistic and challenging conditions. To support this, a novel feature encoder is proposed and named Pillar Attention Encoder. A pillar attention mechanism is designed to extract the feature data while considering its significance for the perception task. An adaptive feature filter is proposed to adjust the size of the feature data for sharing by considering the importance value of the feature. Experiments are conducted for cooperative object detection from multiple vehicle-based and infrastructure-based LiDAR sensors under various communication conditions. Results demonstrate that our method can successfully handle dynamic communication conditions and improve the mean Average Precision by 10.18% when compared with the state-of-the-art feature encoder. 

Despite numerous studies on trajectory prediction, existing approaches often fail to adequately capture the multifaceted and individual nature of driving behavior. In recognition of this gap and based on DenseTNT, an end-to-end and goal-based trajectory prediction method, our study developed a new version of DenseTNT that incorporates personalized nodes within the graph neural network in VectorNet as context encoder. Throughout the neural network computations, these nodes represent individual driver labels, allowing a more granular understanding of diverse driving behaviors to be gained. Based on comparative analysis, our model has a 11.4% reduction in minADE when compared to baseline models that do not have personalized labels. 

Utilizing the latest advances in Artificial Intelligence (AI), the computer vision community is now witnessing an unprecedented evolution in all kinds of perception tasks, particularly in object detection. Based on multiple spatially separated perception nodes, Cooperative Perception (CP) has emerged to significantly advance the perception of automated driving. However, current cooperative object detection methods mainly focus on ego-vehicle efficiency without considering the practical issues of system-wide costs. In this paper, we introduce VINet, a unified deep learning-based CP network for scalable, lightweight, and heterogeneous cooperative 3D object detection. VINet is the first CP method designed from the standpoint of large-scale systemlevel implementation and can be divided into three main phases: (1) Global Pre-Processing and Lightweight Feature Extraction which prepare the data into global style and extract features for cooperation in a lightweight manner; (2) Two-Stream Fusion which fuses the features from scalable and heterogeneous perception nodes; and (3) Central Feature Backbone and 3D Detection Head which further process the fused features and generate cooperative detection results. An open-source data experimental platform is designed and developed for CP dataset acquisition and model evaluation. The experimental analysis shows that VINet can reduce 84% system-level computational cost and 94% system-level communication cost while improving the 3D detection accuracy. 

Perceiving the surrounding environment is critical to enable cooperative driving automation, which is regarded as a transformative solution to improving our transportation system. Cooperative perception, by cooperating information from spatially separated nodes, can innately unlock the bottleneck caused by physical occlusions and has become an important research topic. Although cooperative perception aims to resolve practical problems, most of the current research work is designed based on the default assumption that the communication capacities of collaborated perception entities are identical. In this work, we introduce a fundamental approach - Dynamic Feature Sharing (DFS) - for cooperative perception from a more pragmatic context. Specifically, a DFS-based cooperative perception framework is designed to dynamically reduce the feature data required for sharing among the cooperating entities. Convolution-based Priority Filtering (CPF) is proposed to enable DFS under different communication constraints (e.g., bandwidth) by filtering the feature data according to the designed priority values. Zero-shot experiments demonstrate that the proposed CPF method can improve cooperative perception performance by approximately +22% under a dynamic communication-capacity condition and up to +130% when the communication bandwidth is reduced by 90 %. 

Advanced Driver Assistance Systems (ADAS) are increasingly important in improving driving safety and comfort, with Adaptive Cruise Control (ACC) being one of the most widely used. However, pre-defined ACC settings may not always align with driver's preferences and habits, leading to discomfort and potential safety issues. Personalized ACC (P-ACC) has been proposed to address this problem, but most existing research uses historical driving data to imitate behaviors that conform to driver preferences, neglecting real-time driver feedback. To bridge this gap, we propose a cloud-vehicle collaborative P-ACC framework that incorporates driver feedback adaptation in real time. The framework is divided into offline and online parts. The offline component records the driver's naturalistic car-following trajectory and uses inverse reinforcement learning (IRL) to train the model on the cloud. In the online component, driver feedback is used to update the driving gap preference in real time. The model is then retrained on the cloud with driver's takeover trajectories, achieving incremental learning to better match driver's preference. Human-in-the-loop (HuiL) simulation experiments demonstrate that our proposed method significantly reduces driver intervention in automatic control systems by up to 62.8%. By incorporating real-time driver feedback, our approach enhances the comfort and safety of P-ACC, providing a personalized and adaptable driving experience.