arXiv subjects

Venktesh Pandey

Publications and source records attributed to Venktesh Pandey.

7 recordsLinked to original sources

arXiv2026

Microtransit revenue management informed by citywide travel demand and joint subscription-mode choice modeling

As an IT-enabled multi-passenger mobility service, microtransit can improve accessibility, reduce congestion, and promote sustainability. However, realizing its business potential requires a deeper understanding of traveler preferences, highlighting the need for more effective tools for demand forecasting and revenue management, especially when actual usage data are limited. We propose an innovative modeling approach that integrates travel behavioral insights into microtransit policymaking. The approach operates by (1) leveraging citywide synthetic data to achieve greater spatiotemporal granularity, (2) estimating a nonparametric nested model for joint travel mode and ride-pass subscription choices, and (3) employing a simulation-based method to calculate revenue and traveler benefits under various policy scenarios. We demonstrate the applicability of our approach through a case study in Arlington, TX, one of the largest deployments of microtransit (Via) in the U.S. Using the simulation-based workflow, we evaluate alternative policy scenarios, including ride-pass discounts, event-based subsidies, and place-based subsidies, to assess their impacts on microtransit ridership, system revenue, and traveler welfare. The results indicate that reducing the weekly pass price from $25 to $18.9 and the monthly pass price from $80 to $71.5 would increase total revenue by approximately $127 per day. A 100% trip fare discount could reduce 61 car trips to AT&T Stadium during a game event while generating an additional 82 microtransit trips per day to Medical City Arlington. However, achieving these mode shifts would require subsidies of approximately $533 per event and $483 per day, respectively.

econ.EM↗

arXiv2024

A Bi-criterion Steiner Traveling Salesperson Problem with Time Windows for Last-Mile Electric Vehicle Logistics

This paper addresses the problem of energy-efficient and safe routing of last-mile electric freight vehicles. With the rising environmental footprint of the transportation sector and the growing popularity of E-Commerce, freight companies are likely to benefit from optimal time-window-feasible tours that minimize energy usage while reducing traffic conflicts at intersections and thereby improving safety. We formulate this problem as a Bi-criterion Steiner Traveling Salesperson Problem with Time Windows (BSTSPTW) with energy consumed and the number of left turns at intersections as the two objectives while also considering regenerative braking capabilities. We first discuss an exact mixed-integer programming model with scalarization to enumerate points on the efficiency frontier for small instances. For larger networks, we develop an efficient local search-based heuristic, which uses several operators to intensify and diversify the search process. We demonstrate the utility of the proposed methods using benchmark data and real-world instances from Amazon delivery routes in Austin, US. Comparisons with state-of-the-art solvers shows that our heuristics can generate near-optimal solutions within reasonable time budgets, effectively balancing energy efficiency and safety under practical delivery constraints.

math.OC↗

arXiv2022

Computationally-Efficient Decomposition Heuristic for the Static Traffic Assignment Problem

Applications such as megaregional planning require efficient methods for solving traffic assignment problems (TAPs) on large-scale networks. We propose a decomposition heuristic that generates approximate TAP solutions by partitioning the complete network into subnetworks which are solved in parallel and use an iterative-refinement algorithm for improving the network partitions. A novel network transformation and three-stage algorithm are also proposed to solve a constrained shortest path problem as a subproblem of the heuristic. Experiments on various networks show that the heuristic can generate 15.1-67.8% computational savings in finding solutions with initial relative gap of 0.02. The performance benefits of the proposed heuristic when warmstarting standard TAP algorithms are demonstrated with an average computational savings of 10-35% over a TAP solver without warmstarting.

math.OC↗

arXiv2022

Temporal Multimodal Multivariate Learning

We introduce temporal multimodal multivariate learning, a new family of decision making models that can indirectly learn and transfer online information from simultaneous observations of a probability distribution with more than one peak or more than one outcome variable from one time stage to another. We approximate the posterior by sequentially removing additional uncertainties across different variables and time, based on data-physics driven correlation, to address a broader class of challenging time-dependent decision-making problems under uncertainty. Extensive experiments on real-world datasets ( i.e., urban traffic data and hurricane ensemble forecasting data) demonstrate the superior performance of the proposed targeted decision-making over the state-of-the-art baseline prediction methods across various settings.

cs.LG↗

arXiv2020

Time-Equitable Dynamic Tolling Scheme For Single Bottlenecks

Dynamic tolls present an opportunity for municipalities to eliminate congestion and fund infrastructure. Imposing tolls that regulate travel along a public highway through monetary fees raise worries of inequity. In this article, we introduce the concept of time poverty, emphasize its value in policy-making in the same ways income poverty is already considered, and argue the potential equity concern posed by time-varying tolls that produce time poverty. We also compare the cost burdens of a no-toll, system optimal toll, and a proposed ``time-equitable" toll on heterogeneous traveler groups using an analytical Vickrey bottleneck model where travelers make departure time decisions to arrive at their destination at a fixed time. We show that the time-equitable toll is able to eliminate congestion while creating equitable travel patterns amongst traveler groups.

econ.TH↗

arXiv2019

Deep Reinforcement Learning Algorithm for Dynamic Pricing of Express Lanes with Multiple Access Locations

This article develops a deep reinforcement learning (Deep-RL) framework for dynamic pricing on managed lanes with multiple access locations and heterogeneity in travelers' value of time, origin, and destination. This framework relaxes assumptions in the literature by considering multiple origins and destinations, multiple access locations to the managed lane, en route diversion of travelers, partial observability of the sensor readings, and stochastic demand and observations. The problem is formulated as a partially observable Markov decision process (POMDP) and policy gradient methods are used to determine tolls as a function of real-time observations. Tolls are modeled as continuous and stochastic variables, and are determined using a feedforward neural network. The method is compared against a feedback control method used for dynamic pricing. We show that Deep-RL is effective in learning toll policies for maximizing revenue, minimizing total system travel time, and other joint weighted objectives, when tested on real-world transportation networks. The Deep-RL toll policies outperform the feedback control heuristic for the revenue maximization objective by generating revenues up to 9.5% higher than the heuristic and for the objective minimizing total system travel time (TSTT) by generating TSTT up to 10.4% lower than the heuristic. We also propose reward shaping methods for the POMDP to overcome the undesired behavior of toll policies, like the jam-and-harvest behavior of revenue-maximizing policies. Additionally, we test transferability of the algorithm trained on one set of inputs for new input distributions and offer recommendations on real-time implementations of Deep-RL algorithms. The source code for our experiments is available online at https://github.com/venktesh22/ExpressLanes_Deep-RL

eess.SY↗

arXiv2019

On the needs for MaaS platforms to handle competition in ridesharing mobility

Ridesharing has been emerging as a new type of mobility. However, the early promises of ridesharing for alleviating congestion in cities may be undermined by a number of challenges, including the growing number of proposed services and the subsequent increasing number of vehicles, as a natural consequence of competition. In this work, we present optimization-based approaches to model cooperation and competition between multiple ridesharing companies, in a real-time on-demand setting. A recent trend relies on solving the integrated combination of Dial-A-Ride Problems (DARP), which compute the cost of assigning incoming requests to vehicle routes, plus Linear Assignment Problems (LAP), which assign vehicles to requests. While the DARPs, are solved at the level of the vehicles of each company, we introduce cooperative and competitive approaches to solve the LAP. The cooperative model, which could make use of Mobility as a Service platforms, is shown to solve the LAP to optimality following closely results from the literature, and limiting the amount of information the companies are required to share. We investigate how a realistic model of competition deviates from this optimality and provide worst case bounds. We evaluate these models with respect to a centralized model on one-week instances of the New York City taxi dataset. Model variants coping with noise in the travel time estimations, bias in the assignment costs, and preferences in the competitive case are also presented and validated. The computational results suggest that cooperation among ridesharing companies can be conducted in such a way to limit the degradation of the level of service with respect to a centralized model. Finally, we argue that the competition can lower the quality of the ridesharing service, especially in the case customer preferences are accommodated.

cs.CY↗