Docs
  • Solver
  • Models
    • Field Service Routing
    • Employee Shift Scheduling
    • Pick-up and Delivery Routing
  • Platform
Try models
  • Pick-up and Delivery Routing
  • Introduction

Pick-up and Delivery Routing

    • Introduction
    • Getting started: Hello world
    • User guide
      • Terminology
      • Use case guide
      • Planning AI concepts
      • Integration
      • Constraints
      • Understanding the API
      • Demo datasets
      • Input datasets
        • Model configuration
        • Model input
        • Planning window
      • Input validation
      • Output datasets
        • Metadata
        • Model output
        • Input metrics
        • Key performance indicators (KPIs)
      • Routing with Timefold’s maps service
      • Metrics and optimization goals
    • Driver resource constraints
      • Lunch breaks and personal appointments
      • Route optimization
      • Shift hours and overtime
    • Job service constraints
      • Time windows and opening hours
      • Skills
      • Movable stops and multi-day schedules
      • Dependencies between stops
      • Priority jobs and optional jobs
      • Stop service level agreement (SLA)
      • Job requirements and tags
        • Job required drivers
        • Job pooling
        • Prohibit job combinations
        • Maximum time burden
        • Driver capacity
        • Tags
    • Recommendations
      • Job time window recommendations
      • Stop time window recommendations
    • Real-time planning
      • Real-time planning: pinning stops
    • Changelog
    • Upgrading to the latest versions
    • Feature requests

Introduction

The Pick-up and Delivery Routing model is one of Timefold’s planning AI models and is available on the Timefold Platform.

The Pick-up and Delivery Routing model assigns pick-ups and deliveries to drivers so that multiple pick-ups and deliveries can be made at the same time. The model balances the driver’s vehicle capacity, current load, and demand while minimizing driving time and customer wait times.

The model runs on the Timefold Platform and the application includes Timefold Enterprise Solver, a scalable optimization engine that can solve complex constraint satisfaction problems.

The Pick-up and Delivery Routing model includes constraints for:

  1. Scheduling customer pick-ups and deliveries when customers have agreed to be available.

  2. Assigning drivers with the right skills for the jobs.

  3. Prioritizing jobs and meeting job requirements.

  4. Fairly assigning work to drivers and respecting their work hours.

To learn more about individual constraints, see the Driver resource constraints and Job requirements and tags guides.

Visualization of a Pick-up and delivery routing schedule
Figure 1. Visualization of a Pick-up and delivery routing schedule

Constraints have configurable weights, making them adjustable to meet different business goals and priorities.

The integrated maps service provides real-world routing and optimizing for the shortest travel time or travel distance.

The real time planning API makes plans adaptable when unforeseen events inevitably occur, and the recommendations API can help you figure out which drivers to assign to which jobs.

The REST API layer is defined on top of the model and serves as a communication point with the engine to provide a stable interface that allows you to manage the lifecycle of the optimization problem, from submitting the initial dataset to retrieving the final solution.

Introduction for integration & application developers

Backend developers, integration engineers, full-stack developers, and technical consultants implement the model in an application or workflow.

Concern Documentation

How to get a first working solution quickly

Getting started: Hello world

Correct API usage

Integration, Dataset lifecycle

Understanding available constraints and features

Driver resource constraints and Job service constraints

Debugging invalid inputs or unexpected results

Input validation

How the model supports reacting to unexpected events and replanning with the least amount of disruption

Real-time planning

Performance tuning

Configuration parameters and profiles

Introduction for platform & enterprise architects

Enterprise architects, solution architects, security architects, IT governance leads, and platform owners are responsible for system integration, compliance, and long-term maintainability.

Concern Documentation

How the model integrates into existing enterprise systems

Integration

API contracts, and long-term stability

Model maturity and versioning

Authentication, authorization, and request integrity

API keys, Member management and roles, Secrets management

Auditability of configuration changes

Reviewing the audit log

Risk profile, product security, data security and general trust

Trust

Introduction for product, business & decision makers

Product managers, project managers, business analysts, operations managers, and executives evaluate value, scope, and speed of delivery.

Concern Documentation

What business problems the model solves

Use case guide, Metrics and optimization goals

How results can be evaluated and explained to stakeholders

Interpreting dataset results, Validating an optimized plan with Explainable AI

How the model can support strategic decision making

Uncovering inefficiencies in operational planning, Balancing different optimization goals

Following up on new features

Changelog and Upgrading to the latest versions

Whether the model can evolve with changing business needs

Feature requests

Next

  • See the full API spec or try the online API.

  • Follow the Getting started guide.

  • © 2026 Timefold BV
  • Timefold.ai
  • Documentation
  • Changelog
  • Send feedback
  • Privacy
  • Legal
    • Light mode
    • Dark mode
    • System default