Pickup Locations Research Articles

Two-Stage Solution for Meal Delivery Routing Optimization on Time-Sensitive Customer Satisfaction

The online-to-offline (O2O) meal delivery mode in which takeout meals are ordered online and delivered offline is recently emerging. The fast delivery of huge meal orders for time-sensitive customers imposes great challenges on O2O meal delivery platforms. This study establishes a two-stage solution for meal delivery routing optimization with the objective of maximizing time-sensitive customer satisfaction. In the first stage, a large number of meal orders are hierarchically classified and merged into delivery bundles based on the nearest pickup location rule by applying the hierarchical agglomerative clustering (HAC) algorithm, to increase fast meal delivery efficiency. In the second stage, a genetic algorithm (GA) is applied to solve the cluster-based delivery routing optimization model to find an optimal delivery route for meal orders in each delivery bundle. The numerical simulation results verify that the two-stage routing optimization solution is effective to schedule timely meal delivery and improve customer time satisfaction. The comparison of the results indicates the superiority of the proposed two-stage solution with HAC and GA on customer satisfaction while ensuring the delivery of all orders within 60 minutes. The sensitivity analysis shows the impact of time-sensitive customer heterogeneity on meal delivery satisfaction. This research has significant managerial insights for fast delivery services of O2O meal delivery platforms.

Development of predictive modeling and deep learning classification of taxi trip tolls

Several studies discussed the predictive modeling of deep learning in different applications such as classifying tissue features from microstructural data, Crude Oil Prices, mechanical constitutive behavior of materials, microbiome data, and mineral prospectively. Commercial navigation includes a wealth of trip-related data, including distance, expected journey time, and tolls that may be encountered along the way. Using a classification algorithm, it is possible to extract drop-off and pickup locations from taxi trip data and estimate if the tour would incur tolls. In this work, let’s use the classification learner to create classification models, compare their performance, and export the findings for additional study. The workflow for the classification learner is the same as for the regression learner. The purpose is to make predictions based on fresh data in order to see how well the model performs with new data. To train the model, it’s critical to separate the data set. The combined training and validation data is next pre-processed, which involves tasks such as cleaning and developing new features skills. Once the data has been prepared, it’s time to begin the supervised machine learning process and test a number of ways to identify the best model, such as the type of model that should be used, the important features, and the best parameters of the model to find the best fit for the considered data. The results of analyzing different predictive multiclass classification models with taxi trip tolls show that it is possible to use a machine learning-based model when we like to avoid road tolls depending on historical data on taxi trip tolls. The outcome of this study can help to expect road tolls from the drop-off and pickup locations of a taxi data

A branch‐and‐cut algorithm for the pickup‐and‐delivery traveling salesman problem with handling costs

AbstractIn the Pickup‐and‐Delivery Traveling Salesman Problem with Handling Costs (PDTSPH), a single vehicle has to satisfy multiple customer requests, each defined by a pickup location and a delivery location. Cargo handling is performed at the rear end of the vehicle, in a Last‐In‐First‐Out (LIFO) order for PDTSPH. However, additional handling operations are permitted with a penalty if other loads that block the access to the delivery have to be unloaded and reloaded. The objective of PDTSPH is to minimize the total transportation and handling cost. In this paper, we present a new Mixed Integer Programming (MIP) model and a branch‐and‐cut algorithm to solve PDTSPH. We also present new integral separation procedures to effectively handle the exponential number of constraints in our MIP model. A family of inequalities are introduced to enhance the scalability of our implementation. The performance of our approach is compared with a compact formulation from the literature (Veenstra et al. [21]) in instances ranging from 9 to 21 customer requests. Computational results show our algorithm outperforming the compact formulation in 69% of instances with an average runtime improvement of 57%.

Car-sharing between two locations: Online scheduling with flexible advance bookings

We study an online scheduling problem that is motivated by applications such as car-sharing. Users submit ride requests, and the scheduler aims to accept requests of maximum total profit using a single server (car). Each ride request specifies the pick-up time and the pick-up location (among two locations, with the other location being the destination). The scheduler has to decide whether or not to accept a request immediately at the time when the request is submitted (booking time). We consider two variants of the problem with respect to constraints on the booking time: In the fixed booking time variant, a request must be submitted a fixed amount of time before the pick-up time. In the variable booking time variant, a request can be submitted at any time during a certain time interval that precedes the pick-up time. We present lower bounds on the competitive ratio of deterministic and randomized algorithms for both variants and propose a greedy algorithm that achieves the best possible competitive ratio among deterministic algorithms.

The pickup and delivery problem with alternative locations and overlapping time windows

Online second-hand marketplaces have seen a vast increase in transactions in recent years, although sending and receiving parcels can be an inconvenience for private buyers and sellers in C2C settings. To facilitate transportation providers expanding their product portfolio with alternative concepts, we consider the pickup and delivery problem (PDP) with alternative locations and overlapping time windows. The transportation requests have to be served by a fleet of homogeneously capacitated vehicles. Each request may have multiple roaming pickup locations throughout the day with non-overlapping time windows (since the product cannot be in two places at once). A request may also have many roaming delivery locations, and additionally an alternative recipient with their own set of roaming locations. As such, several persons in different locations can be available simultaneously to accept a delivery. Recipients could also use 24-hour locker boxes if these are conveniently located.We propose a solution approach based on a multi-start, adaptive, large neighborhood search with problem specific operators, to solve the pickup and delivery problem with alternative locations. We compare our algorithm with similar problems from the literature and examine in detail different scenarios based on real data provided by an Austrian logistics provider. In particular, we explore the benefits of locker boxes, roaming locations, alternative recipients, and mixed customer profiles based on different preferences concerning data sharing and convenience. We found that an increase in flexibility and convenience for the customers translates into cost savings up to almost 30% for the carriers.

Optimization of personalized price discounting scheme for one-way station-based carsharing systems

As a promising pattern of shared mobility, one-way carsharing systems provide users with flexible car-rental services and have enjoyed rapid development in the past few years. Almost all previous relevant optimization studies assume that the objective of the pricing or discounting scheme is to balance the fleet from the standpoint of the carsharing companies. However, the users’ preferences for various levels of service have not been explored sufficiently. This paper introduces a carsharing personalized price discounting scheme (CSPPDS) problem for one-way reservation-based11It is assumed that users make reservations for their trips one day ahead of set-off in this work. services, considering user acceptance of the discounted price and various levels of service that the system provides to the users. To maximize the system’s profit, the presented CSPPDS problem decides the discounting scheme and whether to accept the requests. Meanwhile, the actual requests travel plans that can be different from the users’ original travel requests in pick-up locations and start times are optimized. A real-world case study based on a one-way carsharing system in Beijing is conducted to demonstrate the applicability of the presented model.

Abstract WP43: Modeling The Decay In Probability Of Receiving Endovascular Thrombectomy Based On Time From Stroke Onset

Introduction: Large-vessel occlusion (LVO) stroke patients with infarct core volumes greater than 70 mL do not meet current AHA guidelines for thrombectomy eligibility. Therefore, it is important to understand how time-dependent infarct core growth translates to a patient’s declining probability of thrombectomy eligibility. Modeling the probability that a suspected LVO patient would qualify for thrombectomy can help inform the optimal prehospital emergency transport strategy which maximizes the likelihood of an excellent patient outcome. Methods: We determined the time from stroke onset required for an infarct core to grow to 70 mL as a function of penumbra volume and collateral score. After applying a series of numerical interpolations, our framework outputted the probability a suspected LVO patient qualifies for thrombectomy (based on core volume threshold) as a function of time from stroke onset to imaging. We then incorporated this function into an existing model of prehospital emergency transport, which previously assumed all patients were thrombectomy-eligible, in order to assess the impact that considering treatment eligibility had on optimal transport decisions. Results: An exponential decay curve best fit the numerically-generated probability function. We found that after integrating this eligibility model into the emergency transport decision tool the optimal transport strategy changed from drip and ship to mothership in 8.5% of possible patient pickup locations in Alberta, Canada. Conclusions: This methodology provides a novel, mechanistic approach to deriving a thrombectomy eligibility curve. As a result, we are able to better optimize prehospital transport decisions to improve outcomes of suspected LVO patients.

Abstract 74: Area Deprivation Index, Stroke Outcomes, And Structural Changes To Improve Access To Thrombectomy

Introduction: In New York City (NYC), expanding the reach of thrombectomy-capable stroke centers (TSC) is key to combating socioeconomic disparities in stroke care. The Area Deprivation Index (ADI), a validated, neighborhood-level composite measure (scored 1-100) that includes income, education, employment, and housing quality, has informed healthcare delivery but has not been used to identify disadvantaged neighborhoods with poor access to stroke care. We sought to evaluate the impact of establishing Mount Sinai Queens Hospital (MSQ) as a TSC in 2017 on transfer times and to explore the association between ADI and stroke care access. Methods: Thrombectomy patient pick-up addresses were obtained through Emergency Medical Services runsheets from June 2016 to July 2021 and matched to census-tract level ADI scores from Neighborhood Atlas. Preliminary analyses compared both ADIs and time to stroke care access in both Queens and Manhattan. The primary outcome measure was the duration between ambulance arrival and groin puncture. Simple linear regression and T-tests were used to assess the association between ADI and time to groin puncture by borough. Results: Among 517 cases between 2016-2021, the average ADI of pick-up locations was 10.35 (range: 1 - 70.5). Across all centers, higher ADI (greater deprivation) was significantly associated with increased time to groin puncture (p = 0.024). Notably, Queens patients were picked up in census tracts with higher ADI (p=0.0289) but had a faster pick up to groin puncture time (p=0.006). Conclusions: Across urban census tracts, a higher ADI was associated with delays in access to thrombectomy. Thrombectomy centers in areas with higher ADI can play a role in reducing healthcare disparities for stroke patients.

Minimizing Travel Time and Latency in Multi-Capacity Ride-Sharing Problems

Motivated by applications in ride-sharing and truck-delivery, we study the problem of matching a number of requests and assigning them to cars. A number of cars are given, each of which consists of a location and a speed, and a number of requests are given, each of which consists of a pick-up location and a drop-off location. Serving a request means that a car must first visit the pick-up location of the request and then visit the drop-off location. Each car can only serve at most c requests. Each assignment can yield multiple different serving routes and corresponding serving times, and our goal was to serve the maximum number of requests with the minimum travel time (called CSsum) and to serve the maximum number of requests with the minimum total latency (called CSlat). In addition, we studied the special case where the pick-up and drop-off locations of a request coincide. Both problems CSsum and CSlat are APX-hard when c≥2. We propose an algorithm, called the transportation algorithm (TA), which is a (2c−1)-approximation (resp. c-approximation) algorithm for CSsum (resp. CSlat); these bounds are shown to be tight. We also considered the special case where each car serves exactly two requests, i.e., c=2. In addition to the TA, we investigated another algorithm, called the match-and-assign algorithm (MA). Moreover, we call the algorithm that outputs the best of the two solutions found by the TA and MA the CA. We show that the CA is a two-approximation (resp. 5/3) for CSsum (resp. CSlat), and these ratios are better than the ratios of the individual algorithms, the TA and MA.

Data-Driven Pick-Up Location Recommendation for Ride-Hailing Services

Ride-hailing service (RHS) has become an important transportation mode in our daily life. Although many works have been proposed to improve RHS from different aspects, only few works focus on the selections of pick-up locations, where rider and driver meet and start a trip. In this paper, we present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPLRec</i> , a data-driven pick-up location recommendation system that exploits riders' specific mobility demands, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> destination, and historical experiences to meet riders' travel requirements. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPLRec</i> generates potential pick-up locations over the road network and characterizes them with rich features that describe a location from the riders' perspective. We also build spatio-temporal indexes to organize potential pick-up locations and historical data for facilitating online recommending. When processing an online recommendation request, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPLRec</i> derives candidate pick-up locations and investigates them with materialized features, which are computed from historical order and trajectory data while considering rider's mobility demands. Based on these features, a novel scoring function is used to derive the best pick-up location for each request. Moreover, we implement an RHS simulator to evaluate <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPLRec</i> using large-scale practical ride-hailing datasets. Extensive experiments and simulations demonstrate the effectiveness and efficiency of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPLRec</i> , which can complete each request within 0.5 s and largely reduce the ride-hailing costs when compared to baseline methods.

EtherRider: A Decentralized Intercity Ride-Sharing Platform using Block-Chain Technology

Ridesharing entails the sharing of journeys in order to make optimal use of fuel by allowing people to go along the same route to share rides. It allows regular passengers to share trips with others, having the additive benefit of lowering travel costs and reducing traffic congestion. Most current ride choices rely on a centralized authority to enable the system, leaving it vulnerable to faults at a specific point in the system and raising concerns about privacy disclosure to attackers acting both within and outside. Furthermore, they are vulnerable to external threats and fraud, and the payment made by the current ride-sharing service provider is rather costly. As a result, we have proposed the system named EtherRider, based on the Ethereum blockchain technology. EtherRider enables drivers to provide transportation services without the need for a central system. Both the passenger and the driver will know about sharing ride details, secure their travel details, such as pick-up and drop-off locations, arrival/departure times, and secure payment through the ethereum blockchain.With a distributed ledger, drivers and riders could create a more user-driven,value-oriented marketplace.In the context of car-sharing systems, our work also indicates that the design of such an integrated platform is dependent on striking the correct balance between important design concepts (such as security and privacy, authenticity, traceability and reliability, scalability, and interoperability).

Novel model for integrated demand-responsive transit service considering rail transit schedule.

This research aims to develop an optimization model for optimizing demand-responsive transit (DRT) services. These services can not only direct passengers to reach their nearest bus stops but also transport them to connecting stops on major transit systems at selected bus stops. The proposed methodology is characterized by service time windows and selected metro schedules when passengers place a personalized travel order. In addition, synchronous transfers between shuttles and feeder buses were fully considered regarding transit problems. Aiming at optimizing the total travel time of passengers, a mixed-integer linear programming model was established, which includes vehicle ride time from pickup locations to drop-off locations and passenger wait time during transfer travels. Since this model is commonly known as an NP-hard problem, a new two-stage heuristic using the ant colony algorithm (ACO) was developed in this study to efficiently achieve the meta-optimal solution of the model within a reasonable time. Furthermore, a case study in Chongqing, China, shows that compared with conventional models, the developed model was more efficient formaking passenger, route and operation plans, and it could reduce the total travel time of passengers.

Online patient portal-based management of medication renewal and refill pickup in ambulatory care settings: A retrospective utilization study at tertiary care hospital in Saudi Arabia

BackgroundThe prescription pickup and renewal process in ambulatory care settings requires numerous steps, such as making an appointment with a physician to renew prescriptions and direct pharmacy visits to pick up medications. This process can be difficult or cumbersome for some patients; however, digital health-associated patient portals can reduce the burden on both patients and healthcare professionals. MethodsA retrospective study was conducted in an ambulatory care setting of Johns Hopkins Aramco Healthcare. We analyzed the utilization pattern of MyChart for medication renewal and refill pickup services for ambulatory care patients of all specialties from October 1, 2018, to September 30, 2020. The data were extracted electronically from the Epic-Hyperspace EHR system, and the effects of factors such as year of access and COVID-19 on MyChart utilization were analyzed. ResultsA total of 125,538 patients were registered using MyChart. In the first and second year of this study, MyChart was utilized by 44,063 (8.7%) and 59,622 (13.6%) patients, respectively, for medication pickup. Additionally, in these two years, 92,997 (21.6%) and 156,020 (38.9%) medication refills were requested through MyChart (with no direct pharmacy visit) and collected from different pickup locations, respectively. In two years, there were 363,159 medications sent to physicians for renewal through Epic-MyChart, of which 347,244 (95.6%) were approved and 15,915 (4.4%) were denied. A significant increasing (p less than 0.05) trend in utilization, medication requests, and renewal requests using the MyChart were observed over a period of 24 months and during quarantine due to COVID-19. Although there was a decrease in physicians denying renewal request, these were not significantly affected by time or COVID-19. ConclusionThe high and consistent utilization of the patient portal MyChart indicates its broad acceptance, significantly minimizing the barriers to medication pickup and renewal processes in ambulatory care settings. The year of access and COVID-19 were significantly associated with an increasing trend in MyChart utilization. With increased utilization and higher acceptability, the internet-based patient portal MyChart continues to hold great potential for providing quality healthcare services by increasing access and making patients decision-makers in their healthcare.

Pengembangan Prototipe Aplikasi Kurir Antarjemput Kotak Amal LazisMu Umbulharjo Menggunakan Metode User Centered Design

LazisMu Umbulharjo has quite a number of social activities, including raising funds through charity boxes to several points, such as places of worship, community services, and Muhammadiyah residents in the Umbulharjo area and its surroundings. LazisMu Umbulharjo has managed at least 900 charity boxes spread across 7 sub-districts of the Umbulharjo area and also outside the Umbulharjo area. Currently, the courier who shuttles the charity box is guided by the address that is packaged in a printed sheet that comes from Excel data. Some of the difficulties experienced by couriers when picking up charity boxes at these 900 points, among others, the large number of points that must be visited by one courier. Couriers have difficulty memorizing the positions of the hundreds of charity boxes. Courier difficulties and often missed on the way to the points of the charity box. Problems occur if the staff replaces them with new ones so that adjustments are made from scratch again in learning the pick-up location. This research was conducted based on the stages in the User Centered Design (UCD) process. Plan the human centered process, specify the context of use, specify user and organizational requirements, product design solutions, and evaluate design against user requirements. Research has produced a prototype of the LazisMu Umbulharjo application with the main features of a dashboard for managing data and general information and managing a charity box. User management, charity box location management, and finally the determination of the pick-up route. The application prototype has been tested for usability and calculated using the System Usability Scale (SUS) with an average score of 82. Based on this score, the prototype of the LazisMu Umbulharjo application can be accepted by users (ACCEPTABLE) with grade A and gets an EXCELLENT level

The pickup and delivery problem with time windows, multiple stacks, and handling operations

In this paper, we introduce, model and solve the pickup and delivery problem with time windows, multiple stacks, and handling operations (PDPTWMS-H). In the PDPTWMS-H, a fleet of vehicles based at a depot is used to complete a set of requests which consist of transporting items from a pickup location to a delivery location. The vehicles have multiple stacks operated using last-in-first-out (LIFO) loading which requires the vehicle to be rear-loaded and items can only be unloaded if they are closest to the back door. In the PDPTWMS-H, additional handling operations, referred to as rehandling, are allowed and an additional handling time might be incurred when rehandling items (by unloading and reloading items). The problem consists of determining the number of vehicles and the vehicle routes needed to complete the set of requests at minimal cost while respecting the possible handling operations. We model the PDPTWMS-H with a set-partitioning formulation and resort to branch-price-and-cut (BPC) for its solution. To solve the pricing problem, we derive a unified labeling algorithm that is able to cope with the different rehandling possibilities. The labeling algorithm keeps track about the information of on-board items such that symmetries with respect to both stacks and item positions are reduced. Extensive tests are performed on benchmark instances to assess the performance of the proposed BPC methodology and to provide insights on the impact of the rehandling flexibility on solution quality and time.

Route recommendation based on temporal–spatial metric

The acquisition and analysis of large amounts of mobile trajectory data promote the rapid development of mobile recommender systems, which can essentially recommend a series of positions to the mobile users. In this paper, we concentrate on the mobile sequential recommendation problem by considering both the distance and time factors, the objective of which is to recommend an optimal driving route consisting of a sequence of pick-up locations for the drivers. Firstly, we formulate this problem and develop a potential travel cost function to comprehensively evaluate each candidate route. Then we propose an efficient and effective Route recommendation based on Temporal-Spatial metric scheme called RTS, which adopts the simulated annealing algorithm and can achieve real-time route recommendation without severely sacrificing the recommendation performance. The extensive experiments based on both the real-world and synthetic data are conducted, the results of which demonstrate the efficiency and effectiveness of the proposed RTS scheme.

A Spatio-Temporal Schedule-Based Neural Network for Urban Taxi Waiting Time Prediction

Taxi waiting times is an important criterion for taxi passengers to choose appropriate pick-up locations in urban environments. How to predict the taxi waiting time accurately at a certain time and location is the key solution for the imbalance between the taxis’ supplies and demands. Considering the life schedule of urban residents and the different functions of geogrid regions, the research developed in this paper introduces a spatio-temporal schedule-based neural network for urban taxi waiting time prediction. The approach integrates a series of multi-source data from taxi trajectories to city points of interest, different time frames and human behaviors in the city. We apply a grid-based and functional structuration of an urban space that provides a lower-level data representation. Overall, the neural network model can dynamically predict the waiting time of taxi passengers in real time under some given spatio-temporal constraints. The experimental results show that the granular-based grids and spatio-temporal neural network can effectively predict and optimize the accuracy of taxi waiting times. This work provides a decision support for intelligent travel predictions of taxi waiting time in a smart city.

Multi-Source Information Based Short-term Taxi Demand Prediction Using Deep-Learning Approaches

Taxi service is of great importance in public transportation for its flexibility and convenience. As the advent of smartphones, traditional taxi service is under revolution. Instead of randomly taking a taxi, people are able to call for a taxi pickup by the smartphone applications (e. g. Uber and Lyft). Once the nearest taxi driver receives the request, he can head to the pick-up location. While in most urban areas, the taxi service demand and supply are imbalanced, which indicates that sometimes passengers wait too long for taxis and drivers roam too long with vacant taxicabs. Short-term demand prediction is of great importance to the on-demand ride-hailing services. Predicted taxi demand information can facilitate efficient operations and rebalance both demand and supply sides. This paper proposes a multi-source information based spatiotemporal neural network (MSI-STNN) deep learning architecture to predict short-term taxi demand. The model fuses pick-up and drop-off time-series data, weather information, and location popularity data, using three deep-learning models, including stacked convolutional long short-term memory (ConvLSTM) model, stacked long short-term memory (LSTM) model and convolutional neural network (CNN) model. ConvLSTM captures the spatiotemporal features of pick-up and drop-off time series. LSTM and CNN extracts information of weather and popularity. Case studies were performed to predict short-term pick-up demand at zonal levels in 15 minutes using New York taxi data. The experiment results validate the accuracy performance of the proposed approach comparing with state-of-art time-series and deep learning approaches, including ARIMA, ConvLSTM, CNN, and LSTM.

Optimizing Emergency Stroke Transport Strategies Using Physiological Models.

The criteria for choosing between drip and ship and mothership transport strategies in emergency stroke care is widely debated. Although existing data-driven probability models can inform transport decision-making at an epidemiological level, we propose a novel mathematical, physiologically derived framework that provides insight into how patient characteristics underlying infarct core growth influence these decisions. We represent the physiology of time-dependent infarct core growth within an ischemic penumbra as an exponential function with consideration to rate-determining collateral blood flow. Monte Carlo methods generate distributions of infarct core volumes, which are translated to distributions of 90-day modified Rankin Scale scores. We apply the model to a stroke network that serves rural Bastrop County and urban Travis County by simulating transport strategies from thousands of potential patient pickup locations. In every pickup location, the simulation yields a distribution of outcomes corresponding to each transport strategy. A 2-sample Kolmogorov-Smirnov test and Student t test determine which transport strategy provides a significantly better probability of a good outcome for a given pickup location in each respective county (P<0.01). In Travis County, drip and ship provides significantly better probabilities of a good outcome in 24.0% of the pickup locations, while 59.8% favor mothership. In Bastrop County, 11.3% of the pickup locations favor drip and ship, while only 7.1% favor mothership. The remaining pickup locations in each county are not statistically significant in either direction. We also reveal how differing rates of infarct core growth, the application of bypass policies, and the use of large vessel occlusion field tests impact these results. Modeling stroke physiology enables the use of clinically relevant metrics for determining comparative significance between drip and ship and mothership in a given geography. This formalism can help understand and inform emergency medical service transport decision-making, as well as regional bypass policies.

Mitigating childhood food insecurity during COVID-19: a qualitative study of how school districts in California's San Joaquin Valley responded to growing needs.

To explore best practices and challenges in providing school meals during COVID-19 in a low-income, predominantly Latino, urban-rural region. Semi-structured interviews with school district stakeholders and focus groups with parents were conducted to explore school meal provision during COVID-19 from June to August 2020. Data were coded and themes were identified to guide analysis. Community organisations were involved in all aspects of study design, recruitment, data collection and analysis. Six school districts in California's San Joaquin Valley. School district stakeholders (n 11) included food service directors, school superintendents and community partners (e.g. funders, food cooperative). Focus groups (n 6) were comprised of parents (n 29) of children participating in school meal programmes. COVID-19-related challenges for districts included developing safe meal distribution systems, boosting low participation, covering COVID-19-related costs and staying informed of policy changes. Barriers for families included transportation difficulties, safety concerns and a lack of fresh foods. Innovative strategies to address obstacles included pandemic-electronic benefits transfer (EBT), bus-stop delivery, community pick-up locations, batched meals and leveraging partner resources. A focus on fresher, more appealing meals and greater communication between school officials and parents could boost participation. Districts that leveraged external partnerships were better equipped to provide meals during pandemic conditions. In addition, policies increasing access to fresh foods and capitalising on United States Department of Agriculture waivers could boost school meal participation. Finally, partnering with community organisations and acting upon parent feedback could improve school meal systems, and in combination with pandemic-EBT, address childhood food insecurity.