Figure 1 - uploaded by Breno A. Beirigo
Content may be subject to copyright.
Example of the AMoD-H.

Example of the AMoD-H.

Source publication
Article
Full-text available
Current mobility services cannot compete on equal terms with self-owned mobility products concerning service quality. Due to supply and demand imbalances, ridesharing users invariably experience delays, price surges, and rejections. Traditional approaches often fail to respond to demand fluctuations adequately since service levels are, to some exte...

Contexts in source publication

Context 1
... Figure 1, we illustrate the interplay between the elements of our model. For the sake of simplicity, we represent both vehicle and request discrete locations on a one-dimensional space for each time step such that N = {A, B, C, D, E, F, G, H, I, J, K} and consider a time horizon T = {1, 2, . . . ...
Context 2
... this section, we illustrate the behavior of our π VFA policy. Besides the baseline parameters described in Table 2, we consider the best tuning settings achieved in Section 6.2, namely, the three hierarchical aggregation levels presented in Table 3, the five-vehicle limit per location, and the rebalancing strategy 8 × RC1. Figure 9 and Figure 10 compare the performance of the proposed VFA policy against the myopic policy on a single testing instance. Since the myopic policy reacts to request rejection, from Figure 9, we can see that the fleet can fulfill the demand entirely until about 6:45 AM, when the first rebalancing movement appears. ...
Context 3
... contrast, under our VFA policy, most vehicles are rebalancing before 6:30 AM. As can be seen in Figure 10, the π myopic rejects fewer users than π VFA until about 7:30 AM, but from this time on, the π VFA outperforms the myopic approach, ultimately resulting in about 14% more users serviced. The difference between the policies is further highlighted in the busiest period (from 8 AM to 9 AM). ...
Context 4
... can be seen in Figure 9, under our VFA policy, most vehicles are busy (i.e., rebalancing, picking up, or carrying users) during the demand peak. When rejections start to accumulate from about 6:30 and on (see Figure 10), we can see that the number of parked vehicles drop dramatically, especially in the myopic policy. In such a scarcity scenario, vehicles tend to reject users whose trips are not economically efficient. ...

Similar publications

Conference Paper
Full-text available
An essential task to prevent pedestrian injuries by an autonomous vehicle is the ability to correctly detect and predict its movement. A deep learning-based 2D human poses detector, as OpenPose, provides a skeleton of people present in an image captured by cameras mounted in the car. Nevertheless, these kinds of algorithms give a frame solution but...
Conference Paper
Full-text available
The development of highly autonomous vehicles (HAVs) may relieve drivers from driving tasks and allow new activities such as relaxation or conversation with passengers. Such activities would benefit from new seating configurations. Design concepts of HAVs include swivelling and reclining seats, and such arrangements were found desirable in voluntee...
Article
Full-text available
The proposed work presents efficient objection detection and tracking algorithm for autonomous vehicles, which is developed in MATLAB with Image Processing Computer Version Toolbox and Automated Driving Toolbox. The developed algorithm track and detects moving and stationary objects such as other vehicles, pedestrians, and traffic lanes. Accurate a...
Article
Full-text available
The introduction of connected and autonomous vehicles (CAVs) to the road transport ecosystem will change the manner of collisions. CAVs are expected to optimize the safety of road users and the wider environment, while alleviating traffic congestion and maximizing occupant comfort. The net result is a reduction in the frequency of motor vehicle col...
Preprint
Full-text available
Monocular 3D object detection is a key problem for autonomous vehicles, as it provides a solution with simple configuration compared to typical multi-sensor systems. The main challenge in monocular 3D detection lies in accurately predicting object depth, which must be inferred from object and scene cues due to the lack of direct range measurement....

Citations

... Feng et al. (2021) compared the efficiency of on-demand hailing systems to traditional street-hailing systems in specific circumstances. Addressing uncertain demand and idle vehicle supply, Beirigo et al. (2022) proposed a learning-based optimization approach to approximate the marginal value of vehicles iteratively under different availability settings. Chen et al. (2022) modeled the decision-making processes of drivers and the platform's optimization problem as a Stackelberg game, conducting a counterfactual analysis to determine optimal bonus rates for various scenarios. ...
Article
This paper examines the income inequality among rideshare drivers resulting from discriminatory cancellations by riders, considering the impact of demographic factors such as gender, age, and race. We investigate the tradeoff between income inequality, referred to as the fairness objective, and system efficiency, known as the profit objective. To address this issue, we propose an online bipartite-matching model that captures the sequential arrival of riders according to a known distribution. The model incorporates the notion of acceptance rates between driver-rider types, which are defined based on demographic characteristics. Specifically, we analyze the probabilities of riders accepting or canceling their assigned drivers, reflecting the level of acceptance between different rider and driver types. We construct a bi-objective linear program as a valid benchmark and propose two LP-based parameterized online algorithms. Rigorous analysis of online competitive ratios is conducted to illustrate the flexibility and efficiency of our algorithms in achieving a balance between fairness and profit. Furthermore, we present experimental results based on real-world and synthetic datasets, validating the theoretical predictions put forth in our study.
... Incorporating time estimation in action filtering improved profit and delivery rates by 9% and 8%, respectively. Introducing a learning-based optimisation approach for autonomous ride-sharing platforms, the authors in [129] improved service levels by iteratively improving policies for dispatching and rebalancing. The model considered the spatio-temporal distribution of user service level preferences and the availability of third-party vehicles, making it more robust and adaptive. ...
Article
Full-text available
Urban logistics encompass transportation and delivery operations within densely populated urban areas. It faces significant challenges from the evolving dynamic and stochastic nature of on-demand and conventional logistics services. Further challenges arise with application doctrines shifting towards crowd-sourced platforms. As a result, “traditional” deterministic approaches do not adequately fulfil constantly evolving customer expectations. To maintain competitiveness, logistic service providers must adopt proactive and anticipatory systems that dynamically model and evaluate probable (future) events, i.e., stochastic information. These events manifest in problem characteristics such as customer requests, demands, travel times, parking availability, etc. The Stochastic Dynamic Vehicle Routing Problem (SDVRP) addresses the dynamic and stochastic information inherent in urban logistics. This paper aims to analyse the key concepts, challenges, and recent advancements and opportunities in the evolving urban logistics landscape and assess the evolution from classical VRPs, via DVRPs, to state-of-art SDVRPs. Further, coupled with non-reactive techniques, this paper provides an in-depth overview of cutting-edge model-based and model-free reactive solution approaches. Although potent, these approaches become restrictive due to the “curse of dimensionality”. Sacrificing granularity for scalability, researchers have opted for aggregation and decomposition techniques to overcome this problem and recent approaches explore solutions using deep learning. In the scope of this research, we observed that addressing real-world SDVRPs with a comprehensive resolution encounters a set of challenges, emphasising a substantial gap in the research field that warrants further exploration.
... By separating drive and transport units, providers can increase the utilization of self-driving carriers (presumably, the most expensive assets) while increasing profits, adapting to changing demand profiles such as people and freight on the operational level. Typically, vehicle acquisition is a long-term investment, which makes deciding on adequate fleet size and mix a complex strategical decision [7,2]. Therefore, relying on a DCAV fleet may also mitigate losses due to drastic demand shifts. ...
... Equations (19) to (22) describe the decision variables in the model. Constraint (2) ensures that every request's pickup vertex is visited by at most one vehicle, however, every vertex does not need to be visited. A vehicle that has visited the pickup vertex of a request must also travel to the request's destination vertex, which is ensured by (3). ...
... In the worst-case scenario, the DCAV fleet could behave similarly to the single-purpose fleet by assigning a module to each carrier and having the same routes as the single-purpose vehicles. The parameter groups (H, n k , n n ) are as follows: (1, 2, 4), (1,2,8), (1,2,12), (1, 4, 4), (1,4,8), (1,4,12), (1,6,4), (1,6,8), (1,6,12), (8,2,12), (8,2,16), (8,2,24), (8,4,12), (8,4,16), (8,4,24). ...
Conference Paper
A Dynamically Configurable Autonomous Vehicle (DCAV) is a new class of autonomous vehicle concept using a separable design of lower and upper parts—carriers and modules—to allow more flexible operation. A fleet of DCAVs consists of a set of carriers and a set of compatible modules. Different, possibly crowd-sourced, modules can increase the number of use-cases for DCAVs, possibly leading to disruptive changes in the transport sector. This study investigates the use of DCAV system operating on an Autonomous Mobility-on-Demand (AMoD) scenario, combining passenger and freight transport flows. The novel problem is denoted as the Dynamically Configurable Autonomous Vehicle Pickup and Delivery Problem (DCAVPDP). We propose a mixed-integer linear programming (MILP) model aiming to minimize DCAV fleet size and distance traveled. We compare the performance of a DCAV fleet to the performance of a typical single-purpose fleet (consisting of dedicated passenger and freight vehicles). The numerical study, with 360 instances for each fleet type, considering four people-and-freight demand distribution scenarios, the inclusion of ridesharing, module-and-carrier (de)coupling locations, and different simulation horizon lengths, shows that the proposed modular DCAV system can fulfill a mixed people-and-freight demand using, on average, 18.77% fewer carriers than a regular AMoD system comprised of single-purpose vehicles while increasing on-duty fleet utilization by 4.82%.
... There is work that employs such an approach for related problems. [32,86,79,84,85] combine linear or (simple) piece-wise linear value function approximations (VFAs) with MILP solvers to search the action space in each decision point. However, linear VFAs are known to poorly approximate stateaction values for routing problems (see [46]). ...
Article
There has been a paradigm-shift in urban logistic services in the last years; demand for real-time, instant mobility and delivery services grows. This poses new challenges to logistic service providers as the underlying stochastic dynamic vehicle routing problems (SDVRPs) require anticipatory real-time routing actions. The complexity of finding efficient routing actions is multiplied by the challenge of evaluating such actions with respect to their effectiveness given future dynamism and uncertainty. Reinforcement learning (RL) is a promising tool for evaluating actions but it is not designed for searching the complex and combinatorial action space. Thus, past work on RL for SDVRP has either restricted the action space, that is solving only subproblems by RL and everything else by established heuristics, or focused on problems that reduce to resource allocation problems. For solving real-world SDVRPs, new strategies are required that address the combined challenge of combinatorial, constrained action space and future uncertainty, but as our findings suggest, such strategies are essentially non-existing. Our survey paper shows that past work relied either on action-space restriction or avoided routing actions entirely and highlights opportunities for more holistic solutions.
... The resulting MFDs from both networks showed a quasi-linear increase in network capacity with increasing market penetration rates. Furthermore, digital transportation platorms [17] are increasingly considering AVs to leverage unused vehicles in cities [18] and provide customers with a high-quality mobility services [19]. The literature on urban operational efficiency-related work is presented in Table 2. ...
Article
Full-text available
Next to environmental aspects, establishing areas for safe and economically viable automated driving in mixed-traffic settings is one major challenge for sustainable development of Autonomous Vehicles (AVs). This work investigates safety in the interactions between AVs, human-driven vehicles, and vulnerable road users, including cyclists and pedestrians, within a simulated urban environment in the Dutch city of Rotterdam. New junction and pedestrian models are introduced, and virtual AVs with an occlusion-aware driving system are deployed to deliver cargo autonomously. The safety of applying this autonomous cargo delivery service is assessed using a large set of Surrogate Safety Indicators (SSIs). Furthermore, Macroscopic Fundamental Diagrams (MFDs) and travel time loss are incorporated to evaluate the network efficiency. By assessing the impact of various measures involving Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), Vehicle-to-Everything (V2X) communications, infrastructure modifications, and driving behavior, we show that traffic safety and network efficiency can be achieved in a living lab setting for the considered case. Our findings further suggest that V2X gets implemented, new buildings are not placed close to intersections, and the speed limit of non-arterial roads is lowered.
... Sharing rides with other passengers is an alternative way of sharing transportation resources. Beirigo, Schulte, and Negenborn (2021) address the problem of traditional ridesharing platforms, namely, that they often do not adequately cope with demand fluctuation because they are bounded by fleet size. The authors propose to overcome this by including autonomous vehicles, and thereby they introduce the autonomous ridesharing problem, where idle vehicles can be hired on demand. ...
Article
Traditionally, individuals and firms have bought and owned resources. For instance, owning a car was a status symbol for people. In recent years, this focus has changed. Young people just want to have some convenient means of transportation available. Sharing cars, bikes, or rides is also acceptable and has the advantage of increased sustainability compared with everyone owning such a device. A similar development can also be observed in industry. Already for decades, smaller farmers in rural areas have shared some expensive harvesting machines, via cooperatives. In recent years, cost pressures have incentivized all firms to use their equipment more efficiently and to avoid idle capacities. This has led, among other things, to the exchange of transportation requests between smaller carriers, when one of them faces an overload situation and another has idle resources. Similarly, some production firms share storage space and logistics service providers operate this storage jointly with greater efficiency than each firm could do separately. All these tendencies have led to the development of a new paradigm, the “Sharing Economy.” In transportation, these resources are the vehicles used to deliver goods or move passengers. Given an increasing pressure to act economically and ecologically sustainable, efficient mechanisms that help to benefit from idle capacities are on the rise. They are typically organized through digital platforms that facilitate the efficient exchange of goods or services and help cope with data privacy issues. Both transportation companies and heavy users of transportation services need to learn how to play in a world of shared idle capacities. “Transportation in the Sharing Economy” was the theme of the 2019 Transportation Science and Logistics Workshop held in Vienna, and it is therefore also the focus of this associated special issue. The papers included cover several forms of shared resources in transportation, where the first part deals with freight, whereas in the second part, the focus lies on passenger transportation. Each study highlights the benefits of sharing resources. We received 40 submissions, of which 10 papers were accepted for this special issue after the reviewing process.
... These idle hireable vehicles, which we refer to as FAVs, may be readily available during predefined time windows to join larger, centrally controlled fleets in exchange for compensation. As suggested by Hyland and Mahmassani (2017) and shown by Beirigo et al. (2021), AV fleet managers can significantly benefit from such short-term fleet size elasticity, increasing or decreasing the fleet to adequately meet the demand, by either hiring privately-owned AVs or drivers with non-AVs. ...
Article
Full-text available
With the popularization of transportation network companies (TNCs) (e.g., Uber, Lyft) and the rise of autonomous vehicles (AVs), even major car manufacturers are increasingly considering themselves as autonomous mobility-on-demand (AMoD) providers rather than individual vehicle sellers. However, matching the convenience of owning a vehicle requires providing consistent service quality, taking into account individual expectations. Typically, different classes of users have different service quality (SQ) expectations in terms of responsiveness, reliability, and privacy. Nonetheless, AMoD systems presented in the literature do not enable active control of service quality in the short term, especially in light of unusual demand patterns, sometimes allowing extensive delays and user rejections. This study proposes a method to control the daily operations of an AMoD system that uses the SQ expectations of heterogeneous user classes to dynamically distribute service quality among riders. Additionally, we consider an elastic vehicle supply, that is, privately-owned freelance AVs (FAVs) can be hired on short notice to help providers meeting user service-level expectations. We formalize the problem as the dial-a-ride problem with service quality contracts (DARP-SQC) and propose a multi-objective matheuristic to address real-world requests from Manhattan, New York City. Applying the proposed service-level constraints, we improve user satisfaction (in terms of reached service-level expectations) by 53% on average compared to conventional ridesharing systems, even without hiring additional vehicles. By deploying service-quality-oriented on-demand hiring, our hierarchical optimization approach allows providers to adequately cater to each segment of the customer base without necessarily owning large fleets.
... With the popularization of app-based transportation services, the DARP has been the basis for passenger ridesharing services (see, e.g., [13], [19]). More recently, the advantages of autonomous vehicles for ridesharing have been explored, for instance, considering service quality improvements when platforms activate idle/ parked vehicles [2]. ...
Article
Full-text available
The shared autonomous vehicle (SAV) is a new concept that meets the upcoming trends of autonomous driving and changing demands in urban transportation. SAVs can carry passengers and parcels simultaneously, making use of dedicated passenger and parcel modules on board. A fleet of SAVs could partly take over private transport, taxi, and last-mile delivery services. A reduced fleet size compared to conventional transportation modes would lead to less traffic congestion in urban centres. This paper presents a method to estimate the optimal capacity for the passenger and parcel compartments of SAVs. The problem is presented as a vehicle routing problem and is named variable capacity share-a-ride-problem (VCSARP). The model has a MILP formulation and is solved using a commercial solver. It seeks to create the optimal routing schedule between a randomly generated set of pick-up and drop-off requests of passengers and parcels. The objective function aims to minimize the total energy costs of each schedule, which is a trade-off between travelled distance and vehicle capacity. Different scenarios are composed by altering parameters, representing travel demand at different times of the day. The model results show the optimized cost of each simulation along with associated routes and vehicle capacities.
Article
Full-text available
With the growing demand for high-quality mobility services, transportation service providers need to offer transit services that not only fulfill passengers’ basic travel needs but also ensure an appealing quality of service. During rush hours, fleet sizes are often insufficient to cater to all passenger preferences on service quality, such as ride time and number of co-riders, leading to the sacrifice of service quality for some passengers. Motivated by these practices, we investigate a first-mile ridesharing problem incorporating passenger service quality preferences. This problem involves intricate decisions about the match between requests and vehicles, vehicle routing, and route schedules. To solve this problem, we first develop an arc-based mixed-integer linear programming (MILP) model for this problem. For obtaining near-optimal solutions within practical computation time requirements, we reformulate the MILP model as a trip-based set-partitioning model and propose a math-heuristic algorithm. This algorithm builds upon the column-generation algorithm and tailored bidirectional labeling algorithms with novel dominance rules. Additionally, we introduce a proposition to determine the best schedule for each ridesharing route. To obtain the optimal solution for large-scale instances, we introduce a branch-and-price exact algorithm. Computational experiments based on real-world road networks and randomly generated instances confirm the effectiveness and efficiency of the proposed approaches, demonstrating that the proposed matheuristic finds near-optimal solutions within 40 s for all instances. The results also show that the presented approach significantly improves the quality of first-mile services for prioritized riders, with the ratio of satisfied requests increasing by 23% even when the fleet is generally insufficient.