Driver Route Research Articles

Personalised electric vehicle charging stop planning through online estimators

AbstractIn this paper, we address the problem of finding charging stops while travelling in electric vehicles (EVs) using artificial intelligence (AI). Choosing a charging station is challenging, because drivers have very heterogeneous preferences in terms of how they trade off the features of various alternatives (for example, regarding the time spent driving, charging costs, waiting times at charging stations, and the facilities provided at the charging stations). The key problem here is eliciting the diverse preferences of drivers, assuming that these preferences are typically not fully known a priori, and then planning stops based on each driver’s preferences. Our approach to solving this problem is to develop an intelligent personal agent that learns preferences gradually over multiple interactions. This study proposes a new technique that utilises a small-scale discrete choice experiment as a method of interacting with the driver in order to minimise the cognitive burden on the driver. Using this method, drivers are presented with a variety of routes with possible combinations of charging stops depending on the agent’s latest belief about their preferences. In subsequent iterations, the personal agent will continue to learn and refine its belief about the driver’s preferences, suggesting more personalised routes that are closer to the driver’s preferences. Based on real preference data from EV drivers, we evaluate our novel algorithm and show that, after only a few queries, our method quickly converges to the optimal routes for EV drivers [This paper is an extended version of an ECAI workshop short paper (Shafipour Yourdshahi et al., in: ECAI 2023 workshops, Kraków, Poland, 2023)].

ВОПРОСЫ СОВЕРШЕНСТВОВАНИЯ ТРАНСПОРТНОЙ ОТРАСЛИ В УСЛОВИЯХ РАЗВИТИЯ ПОДКЛЮЧЁННЫХ ТРАНСПОРТНЫХ СРЕДСТВ

The article examines topical issues of improving the transportation industry in the context of the active development and implementation of connected vehicles (CVs). The relevance of the topic is driven by the rapid growth in the number of CVs, their increasing impact on the transportation system, and the need for a comprehensive optimization of the industry to fully realize the potential of new technologies. The main objective of the work is to identify key ways and specific measures to improve the transportation industry that will allow maximizing the benefits of CVs. To achieve this goal, a systems approach is used, which involves a comprehensive consideration of the complex interrelationships between vehicles, infrastructure, and transportation services. The implementation of Intelligent Transportation Systems (ITS) plays a crucial role in optimizing the interaction of these components. The article identifies the main opportunities and challenges associated with the development of CVs. New opportunities include improving road safety, reducing emissions, optimizing logistics and transportation, and enhancing mobility. At the same time, new challenges are emerging, including the need to ensure cybersecurity of CVs, standardization of heterogeneous systems and technologies, and their seamless interaction. The impact of CVs on key aspects of the transportation industry – safety, environment, economy, and social sphere – is analyzed in detail. Specific ways to improve safety are shown through accident prevention systems and driver monitoring systems. The potential of CVs to reduce emissions through traffic optimization and development of alternative modes of transportation is considered. Ways to increase efficiency through logistics optimization, vehicle maintenance, and driver routing are identified. Social effects in the form of increased mobility and new services for passengers are highlighted. The scientific novelty lies in the comprehensive systems consideration of a wide range of problems and ways to improve the transportation industry, taking into account the rapid development of CVs. The practical significance is the specific recommendations on applying a systems approach and implementing ITS to achieve maximum effect. Further research directions include a detailed elaboration of the proposed specific measures to maximize the benefits and minimize the risks associated with the proliferation of CVs. In particular, it is recommended to further optimize logistics processes, vehicle fleets and driver activities, accelerate the development of alternative modes of transportation and services to improve passenger comfort and safety, and establish close cooperation among all stakeholders.

Route choice model using angular indicators

The geometry of the road network significantly affects drivers’ route choice behavior. Among indicators of road network geometry, the lengths of links and connection relations have been widely focused on. On the other hand, indicators related to angles have not received much attention so far. The directional change between neighboring links may affect the route choice behavior among the angular indicators. For example, a route that is similar to a U-turn with a large angle right/left turn is less likely to be desired by drivers. On the other hand, routes that require large detours to reduce the directional change and increase the travel distance are also undesirable. The importance of the angular indicator in route choice behavior can be measured by determining the effect of the directional change on drivers’ route choices. This research examines how directional changes at intersections within the road network affect driver route choice behavior. Initially, we develop a discrete choice model that incorporates both directional changes and travel distance as components within the utility function. Subsequently, we estimate the model's parameters using actual route choice data to ascertain the influence of angular indicators on route selection behavior. In the case study, we observe that directional changes significantly affect route choice behavior, with a single left or right turn equivalent to an additional travel distance of approximately 1 kilometer.

Driver routing and scheduling with synchronization constraints

This paper investigates a novel type of driver routing and scheduling problem motivated by a practical application in long-distance bus networks. A key difference from other crew scheduling problems is that drivers can be exchanged between buses at arbitrary intermediate stops en route such that our problem requires additional synchronization constraints. We present a mathematical model for this problem that leverages a time-expanded multi-digraph and derive bounds for the total number of required drivers. Moreover, we develop a destructive-bound-enhanced matheuristic that converges to provably optimal solutions and apply it to a real-world case study for Flixbus, one of Europe’s leading coach companies. We demonstrate that our matheuristic outperforms a standalone MIP implementation in terms of solution quality and computational time and reduces the number of required drivers by up to 56% compared to approaches currently used in practice. Our solution approach provides feasible solutions for all instances within seconds and solves instances with up to 390 locations and 70 requests optimally with an average computational time under 210 sec. We further study the impact of driver exchanges on the total driver count and show that allowing for such exchanges leads to average savings of 42.69%.

Memory Implementation on Navigation Systems

Nowadays, cases in which people get lost under the guidance of navigation systems still occur. In order to render the situation, the essay seek for ways to improve the navigation system in ways other than enhancing navigational message expression. This paper mainly discusses the feasibility of memory implementation on navigation systems. By memorizing past records and past mistakes, the navigation system will be able to provide a revised route for drivers individually, reducing their possibility of making mistakes, and further increasing their system using experience. Meanwhile, with the support of big data, the navigation system could provide better routes for every user, using their own memories. The main method is to mark every hotspot, that is, a spot where drivers are likely to make mistakes themselves, and provide them with alternative routes that cover as small number of hotspots as possible.

Evaluation of Machine Leaning Algorithms for Streets Traffic Prediction: A Smart Home Use Case.

This paper defines a smart home use case to automatically adjust home temperature and/or hot water. The main objective is to reduce the energy consumption of cooling, heating and hot water systems in smart homes. To this end, the residents set a temperature (i.e., X degree Celsius) for home and/or hot water. When the residents leave homes (e.g., for work), they turn off the cooling or heating devices. A few minutes before arriving at their residences, the cooling or heating devices start working automatically to adjust the home or water temperature according to the residents' preference (i.e., X degree Celsius). This can help reduce the energy consumption of these devices. To estimate the arrival time of the residents (i.e., drivers), this paper uses a machine learning-based street traffic prediction system. Unlike many related works that use machine learning for tracking and predicting residents' behaviors inside their homes, this paper focuses on predicting resident behavior outside their home (i.e., arrival time as a context) to reduce the energy consumption of smart homes. One main objective of this paper is to find the most appropriate machine learning and neural network-based (MLNN) algorithm that can be integrated into the street traffic prediction system. To evaluate the performance of several MLNN algorithms, we utilize an Uber's dataset for the city of San Francisco and complete the missing values by applying an imputation algorithm. The prediction system can also be used as a route recommender to offer the quickest route for drivers.

Route planning and benefit assessment of container drayage platooning considering truck laden-or-empty state

This study investigates the local container drayage problem in semi-automated platooning mode, focusing on the effect of laden-or-empty state of trucks on platoon fuel consumption. The fuel economy characteristics of platoon trucks are described according to the change in the laden-or-empty state of the truck after the platoon serves the customer while considering the sequence of the truck in the platoon. Accordingly, a mixed integer linear programming model for the truck and driver route planning problem is developed, and the lower bound of the problem is analyzed. A simulated annealing algorithm is designed to solve the problem efficiently. Finally, a series of numerical experiments are conducted to evaluate the performance of the proposed algorithm, assess the benefits of the platooning mode considering truck laden-or-empty state, and analyze the influences of some key parameters.

A general dynamic sequential learning framework for vehicle trajectory reconstruction using automatic vehicle location or identification data

Vehicle trajectory data derived from automatic vehicle location (AVL) and automatic vehicle identification (AVI) systems provide critical support for intelligent transportation systems. However, the field-obtained vehicle trajectories are usually incomplete due to sensor malfunction or communication issues. To recover the incomplete data, the existing reconstruction methods have to impose strong assumptions on driver route choice behaviors (network level) and/or traffic dynamics (link level). With the tremendous data available, leveraging data-driven approaches to address the vehicle trajectory reconstruction problem with minimal assumptions is promising. This paper proposes a general dynamic sequential learning framework to reconstruct vehicle trajectory points for both AVL and AVI data. First, an Isolation Forest based ensemble learning model is developed to extract trajectory sequences attributed to different trips in an entire trip chain of a vehicle. Second, the dynamic recurrent neural network (dynamic RNN) is tailored to learn the underlying patterns from the complete AVL and AVI trajectories, respectively. Third, a sequential prediction scheme is customized to reconstruct AVL and AVI trajectories based on the trained networks. To validate the proposed method, two experiments are conducted. One is a simulation experiment with AVL data gathered from a well-calibrated simulation model. The other is a field experiment with AVI data collected from a real-world automatic license plate recognition (ALPR) system. The results show that the proposed method achieves superior performance for both AVL and AVI data compared with the traditional methods. The impacts of different sampling rates and traffic conditions on the model performance are also discussed.

Driver Route Planning Method Based on Accident Risk Cost Prediction

The number of cars on roadways around the world continues to increase year over year. However, the imbalance between traffic supply and demand has not only brought traffic congestion but also caused serious safety problems. To reduce travel risk, this study proposes a driver route planning method based on accident risk cost prediction for connected and automated vehicles. According to the entropy weight method and an improved algorithm of K shortest paths, a route planning model with accident risk as the main optimization objective was established. Firstly, an accident risk evaluation system was built based on traffic accident data, and a quantitative prediction model of accident risk cost based on driver-, vehicle-, road-, and environment-related factors was constructed. Secondly, the entropy weight method was used to calculate the weights of each indicator to determine accident risk considering the aforementioned factors. Then, the route planning model was established, and the solution algorithm based on K shortest paths was designed to solve the optimal route by comprehensively considering accident risk cost and travel time. The accident risk index of each road section in the example road network was assigned, and the risk of the road section was quantified according to the accident risk cost model. Three candidate paths were calculated by using the path planning algorithm proposed in this study; the total risk cost is 6.19, 6.26, and 6.39, respectively; and the total travel time is 29, 29, and 31, respectively. After comparison, the optimal path and two alternative paths are obtained. The results show that the accident risk cost prediction model based on historical accident data can be used to quantify driving risk. The proposed method can help drivers in the connected and automated environment choose the optimal travel route with the lowest risk and shortest travel time and improve overall traffic safety and efficiency.

PITS: An Intelligent Transportation System in pandemic times

The control of the pandemic caused by SARS-CoV-2 is a challenge for governments all around the globe. To manage this situation, countries have adopted a bundle of measures, including restrictions to population mobility. As a consequence, drivers face with the problem of obtaining fast routes to reach their destinations. In this context, some recent works combine Intelligent Transportation Systems (ITS) with big data processing technologies taking the traffic information into account. However, there are no proposals able to gather the COVID-19 health information, assist in the decision-making process, and compute fast routes in an all-in-one solution. In this paper, we propose a Pandemic Intelligent Transportation System (PITS) based on Complex Event Processing (CEP), Fuzzy Logic (FL) and Colored Petri Nets (CPN). CEP is used to process the COVID-19 health indicators and FL to provide recommendations about city areas that should not be crossed. CPNs are then used to create map models of health areas with the mobility restriction information and obtain fast routes for drivers to reach their destinations. The application of PITS to Madrid region (Spain) demonstrates that this system provides support for authorities in the decision-making process about mobility restrictions and obtain fast routes for drivers. PITS is a versatile proposal which can easily be adapted to other scenarios in order to tackle different emergency situations.

A Study Examining the Effects of Driver Profile and Route Characteristics on Vehicle Performance and Tailpipe Emissions under Virtual Real Driving Scenarios

A Study Examining the Effects of Driver Profile and Route Characteristics on Vehicle Performance and Tailpipe Emissions under Virtual Real Driving Scenarios

Crowdshipping: An open VRP variant with stochastic destinations

E-commerce continues to grow throughout the world due to people’s preference to stay at home rather than going to a brick-and-mortar retail store. COVID-19 has exacerbated this trend. Concurrently, crowd-shipping has been gaining in popularity due to both the increase in e-commerce and the current pressures due to COVID-19. We consider a setting where a crowd-shipping platform can fulfill heterogeneous delivery requests from a central depot with a fleet of professionally driven vehicles and a pool of capacitated occasional drivers. We divide delivery requests into sectors to represent different neighborhoods in a city. Occasional drivers have unknown destinations that can be anywhere inside the sectors. Route duration constraints are modeled to motivate participation and increase the probability of route-acceptance by keeping routes short. We assume that occasional drivers will choose routes that are better compensated and that the probability of route-acceptance is dependent on other routes being offered. We propose a two-stage stochastic model to formulate the problem. We use a branch-and-price algorithm capable of solving 50-customer instances, and develop a heuristic that can solve larger 100-customer instances quickly. An upper bound for the total number of occasional drivers is used to reduce the number of constraints in the master problem and reduce the complexity of the pricing problems. We show that occasional drivers with destinations far from the depot reduce the cost by over 30%, while occasional drivers with destinations that are near the depot reduce the cost by 20%. We show that route duration constraints and capacity constraints can restrict the occasional driver routes and both need to simultaneously increase in order to have cost reductions. This setting of crowd-shipping is a viable option for last-mile deliveries.

GPS data in taxi-sharing system: Analysis of potential demand and assessment of fuel consumption based on routing probability model

With the emergence of big geospatial data and the breakthrough of massive data processing, taxi-sharing offers the public a novel transportation mode with high comfort but low cost. However, designing a taxi-sharing system to effectively allocate taxi resources and provides high public acceptance services is an urgent problem to be solved. Furthermore, to what extent the taxi-sharing can be an eco-friendly service without bringing extra pressure to urban emission, fuel consumption, and transportation system is still an unanswered question. This paper proposes a methodology framework to design a taxi-sharing system with driver routing probability based matching and dispatching algorithms. The methodology is capable of matching multiple taxi trips into a sharing trip, with consideration of temporal and spatial feasibilities. The matching of sharing trips includes the determination of which trips to match and the sequence of the destinations. To examine the potential of operation efficiency improved and fuel consumption reduced in taxi-sharing, three scenarios are proposed with different constraints, representing different operation strategies. The sharing trips are then dispatched to the taxis. The potential of operating performance improvement and the potential of fuel consumption reduction are analyzed in the three scenarios. It is found that the delivery part of taxi-sharing may produce more travel distance because of the detour. The key factor for taxi-sharing service to reduce Vehicle Kilometres Travelled is the idle trips and the taxi resources saved. Considering both delivery trips and idle trips together, although taxi-sharing can reduce total fuel consumption in the city, it may increase traffic pressure in certain range area, especially in the key road sections or intersections in the urban road network and the area with high traffic demand.

Network traffic instability with automated driving and cooperative merging

Connected and/or automated vehicles (CAVs or AVs) have been shown to dampen stop-and-go waves in mixed autonomy traffic, thus improving string stability. However, their effects on network traffic instability due to turning and merging maneuvers are less known. In this paper, we characterize such effects using the macroscopic or network fundamental diagram (MFD or NFD). We first revisit and extend the theoretical two-ring network, and then develop an integrated modeling and simulation framework that explicitly accounts for different microscopic traffic models of human-driven vehicles (HVs), AVs, and CAVs. Results suggest that network traffic instability resulting from turning and merging maneuvers persists even if vehicles become automated and cooperative. When the turning probability is low, the presence of CAVs does not induce a significant change in the bifurcation point of the NFD. Scatter in both link fundamental diagrams (FDs) and NFDs, however, reduces resulting in higher and more stable network flows. When the turning probability is high, AVs without cooperation turn out to worsen network traffic stability, giving rise to an NFD that undergoes bifurcation long before the theoretical critical network density is reached. This is in contrast to the case with CAVs that perform cooperative merging. Results also suggest that, whenever the penetration rate of CAVs is too low or too high, making HVs connected is not as effective in delaying the bifurcation of the NFD as when the penetration rate is moderate. We further compare cooperative merging with adaptive signal control and adaptive driver routing to demonstrate its benefits in improving network flows. Simulation experiments on a real motorway segment in Sydney, Australia are also performed to confirm our findings.

Digital twin enabled sustainable urban road planning

Sustainable urban road planning should endeavor to meet current and future traffic-related demands and achieve financial, environmental, and social benefits, which is a complex and interdisciplinary issue that needs to consider various factors and data. Multi-criteria decision making (MCDM) can provide reasonable solutions, and some existing studies integrated MCDM with geographic information system (GIS) technology. This paper presents an urban road planning approach based on digital twin (DT), MCDM, and GIS called DT-MCDM-GIS framework. DT can digitalize the physical world to provide various data for the whole process; MCDM can provide criteria and evaluation methods; GIS can provide an integrated environment for analysis. Building demolition and land use, traffic congestion, driving route selection habits, air quality, and noise are all considered in the framework for urban road planning. The proposed approach can provide a functional, economic, people-friendly, eco-friendly urban road planning scheme considering new road construction and existing old road widening to alleviate traffic congestion and provide an alternative route for drivers that conforms to their habits.

Alibaba Vehicle Routing Algorithms Enable Rapid Pick and Delivery

Alibaba Group pioneered integrated online and offline retail models to allow customers to place online orders of e-commerce and grocery products at its participating stores or restaurants for rapid delivery—in some cases, in as little as 30 minutes after an order has been placed. To meet these service commitments, quick online routing decisions must be made to optimize order picking routes at warehouses and delivery routes for drivers. The solutions to these routing problems are complicated by stringent service commitments, uncertainties, and complex operations in warehouses with limited space. Alibaba has developed a set of algorithms for vehicle routing problems (VRPs), which include an open-architecture adaptive large neighborhood search to support the solution of variants of routing problems and a deep learning-based approach that trains neural network models offline to generate almost instantaneous solutions online. These algorithms have been implemented to solve VRPs in several Alibaba subsidiaries, have generated more than $50 million in annual financial savings, and are applicable to the broader logistics industry. The success of these algorithms has fermented an inner-source community of operations researchers within Alibaba, boosted the confidence of the company’s executives in operations research, and made operations research one of the core competencies of Alibaba Group.

A metaheuristic for crew scheduling in a pickup‐and‐delivery problem with time windows

AbstractA simultaneous vehicle routing and crew scheduling problem (SVRCSP) consists of planning routes for a fleet of vehicles and scheduling their crews, with the particularity that the vehicle–crew correspondence is not fixed through time. This allows a greater planning flexibility and a more efficient use of the fleet, but in counterpart it requires high synchronization. In this work, an SVRCSP is presented, where long‐distance pickup‐and‐delivery requests must be fulfilled over a multiday planning horizon, subject to several constraints such as multiple time windows, hour of services regulation, among others. Crews can be composed of one or two drivers and any of them can be relieved in a given set of locations. Also, they are allowed to travel between locations with noncompany shuttles. The objective is to minimize the cost of travel in company and noncompany vehicles, which depends on the distance, and the penalization for completing requests with delay. A two‐stage sequential approach is applied: a set of truck routes is computed in the first stage and a set of driver routes consistent with the previous routes is obtained in the second stage. An algorithm based on the GRASP × ILS metaheuristic, embedded with a repair heuristic to facilitate the construction of initial solutions, is proposed and evaluated for the latter stage. High‐quality solutions were found for instances generated with up to 3000 requests and a planning horizon of one to four weeks spread over 15 Argentine cities in less than an hour. Additionally, the possibility of carrying an additional driver reduced the cost of external shuttles by 2.25 times on average compared to individual crews and, in some cases, removed this cost completely.

When Hashing Met Matching: Efficient Spatio-Temporal Search for Ridesharing

Shared on-demand mobility holds immense potential for urban transportation. However, finding ride matches in real-time at urban scale is a very difficult combinatorial optimization problem and mostly heuristic approaches are applied. In this work, we introduce a principled approach to this combinatorial problem. Our approach proceeds by constructing suitable representations for rides and driver routes capturing their essential spatio-temporal aspects in an appropriate vector space, and defining a similarity metric in this space that expresses matching utility. This then lets us mathematically model the problem of finding ride matches as that of Near Neighbor Search (NNS). Exploiting this modeling, we devise a novel spatio-temporal search algorithm for finding ride matches based on the theory of Locality Sensitive Hashing (LSH). Apart from being highly efficient, our algorithm enjoys several practically useful properties and extension possibilities. Experiments with large real-world datasets show that our algorithm consistently outperforms state-of-the-art heuristic methods thereby proving its practical applicability.

Do Digital Platforms Reduce Moral Hazard? The Case of Uber and Taxis

Digital platforms provide a variety of technology-enabled tools that enhance market transparency, such as real-time monitoring, ratings of buyers and sellers, and low-cost complaint channels. How do these innovations affect moral hazard and service quality? We investigate this problem by comparing driver routing choices and efficiency on a large digital platform, Uber, with traditional taxis. The identification is enabled by matching taxi and Uber trips at the origin-destination-time level so they are subject to the same underlying optimal route, by exploiting characteristics of the pricing schemes that differentially affect the incentives of taxi and Uber drivers in various circumstances, and by examining changes in behavior when drivers switch from taxis to Uber. We find that (1) taxi drivers route longer in distance than matched Uber drivers on metered airport routes by an average of 8%, with nonlocal passengers on airport routes experiencing even longer routing; (2) no such long routing is found for short trips in dense markets (e.g., within-Manhattan trips) or airport trips with a flat fare; and (3) long routing in general leads to longer travel time, instead of saving passengers time. These findings are consistent with digital platform designs reducing driver moral hazard, but not with competing explanations such as driver selection or differences in driver navigation technologies. We also find evidence of Uber drivers’ long routing on airport trips in times of surge pricing, suggesting that the tech-enabled market designs may not be binding in our setting. This paper was accepted by Chris Forman, information systems.

Evaluation of Road Service Performance Based on Human Perception of Vibration While Driving Vehicle

Road surface monitoring is a significant issue in providing smooth road infrastructure for vehicles, and the key to road condition monitoring is to detect road potholes that affect driving comfort and transportation safety. This paper presents a simple, efficient, and accurate way to evaluate road service performance based on the acquisition of road vibration data by vibration sensors installed in vehicles. Inspired by the discrete fast Fourier transform, the vibration acceleration is processed, and the RMS value of vibration acceleration at 1/2 octave is calculated, after which the road vibration level is calculated. The vibration level is optimized according to the human body’s sensitivity to different frequencies of vibration, resulting in road service performance indicators that can reflect the human body’s real feelings. According to the road service performance index values on the road grading, combined with GPS data on the electronic map color block labeling, the results obtained for the road condition warning, road maintenance, driver route selection have an important significance.