Accelerated AI Logistics and Route Optimization

NVIDIA ReOpt™ is an AI logistics software API that enables near real-time routing optimizations. ReOpt empowers logistics and operational research developers to leverage larger data sets and faster processing, delivering new capabilities like dynamic-rerouting, simulations, and sub-second solver response time for last-mile delivery, supply chain, warehouse picking, and food delivery.

Join Now

AI Logistics and Route Optimization

NVIDIA ReOpt™ is a route optimization software suite that uses GPU-accelerated logistics solvers relying on heuristics (tabu search, guided local search, ant colony, Lin-Kernighan), and optimizations (hyperparameters, batch processing) to calculate complex vehicle routing problem variants with a wide range of constraints. NVIDIA ReOpt provides a C++ and a Python interface that relies on NVIDIA® CUDA® libraries and RAPIDS™ primitives. Native support for distance and time matrices with asymmetric patterns enables a smooth integration with popular map engines.


ReOpt Features

Dynamic Rerouting

Rerun models and adjust for changes like down drivers, inoperable vehicles, traffic/weather disruptions, and the addition of new orders—all within SLA time constraints.

World-Record Accuracy

Achieve world-record accuracy with a 2.98% error gap on the Gehring & Homberger benchmark.

Scale Seamlessly

Scale out to 1000s of nodes to facilitate computationally heavy use cases. NVIDIA ReOpt performs better than SOTA solutions to address innovative use cases not otherwise possible today.

Real-Time Analytics

Route 1,000 packages in 10 seconds instead of 20 minutes (that’s 120X faster), with the same level of accuracy.

Get Started Quickly

Explore NVIDIA ReOpt Early Access notebooks and guides available on Google Colab today.

Save Millions

Reduce travel times and fuel costs by 15% with dynamic rerouting—which saves companies millions.

Solving Logistics and Route Optimization Challenges

Last Mile Delivery

In 2020, parcel shipping exceeded 131 billion in volume globally and it's likely to more than double by 2026 (Source: Pitney Bowes Parcel Shipping Index).

Transport and logistics companies are also facing multiple new challenges arising from the pandemic and the changing economic and geo-political landscape within the industry.

As a result of these conditions, Last Mile Delivery (LMD) has become the most expensive portion of the logistics fulfillment chain, representing over 41% of overall supply chain costs for industries like retail, quick service restaurants (QSRs), consumer packaged goods (CPG), and manufacturing (Source: Capgemini Research Institute, The Last-Mile Delivery Challenge).

Based on these conditions, the challenges of last-mile delivery are manifesting as shrinking delivery timelines, profitability concerns, scaling issues, and numerous evolving delivery options.

Reducing these challenges has become critical for businesses to fully optimize the final leg of the transportation journey and reduce the total cost of delivery.


Vehicle Routing Problem

Consider the Vehicle Routing Problem (VRP), which asks "What is the optimal set of routes for a fleet of vehicles to traverse in order to deliver to a given set of customers?" It generalizes the well-known traveling salesman problem (TSP).

Operations Research (OR) and logistics issues at greater scale are incredibly compute intensive with massive operational costs. As the number of destinations increases, the corresponding number of roundtrips surpasses the capabilities of even the fastest supercomputers.

With 10 destinations, there can be more than 3 million roundtrip permutations and combinations. With 15 destinations, the number of possible routes could exceed a trillion.

Adjusting for changes in these parameters due to inclement weather, a driver out sick, vehicle maintenance, and new orders greatly increases the scope of the problem.

Anatomy Of The Routing Problem

In this simple food delivery example, a pizza shop is planning to deliver pizzas to four different addresses, then return to the store. The problem is represented as a graph with five nodes, including the depot (pizza shop). The edges represent the ability to go from a location to the other with a given cost. The solver supports multiple cost or weights dimensions (eg. distance and time). Costs could be asymmetric and triangle inequality compliance is not required. From there, the pizza delivery application models and solves the problem through the following steps:

  1. Query a mapping app to determine the distance between any two addresses in this list.
  2. Pizzas must be delivered to customers within defined time windows. This is encoded into this distance matrix and constraint tuple. The transaction time and the number of pizzas per address is also encoded.
  3. Encode the fleet information into a second tuple with vehicle properties (weight capacity). The number of capacity dimensions is arbitrary.
  4. Pass the result to NVIDIA ReOpt to discover that the optional approach is to send one driver to locations one and two, and another driver to locations three and four.

Apply for early access to NVIDIA ReOpt.

Join Now