Route Optimization


Achieve world-record accuracy and performance to solve complex problems, save time, and reduce costs and carbon footprints.

What Is NVIDIA cuOpt?

NVIDIA® cuOpt™ optimizes operations by enabling better, faster decisions with accelerated computing. cuOpt helps teams solve complex routing problems with multiple constraints and delivers new capabilities such as dynamic rerouting, horizontal load-balancing, and robotic simulations, with subsecond solver response times. With 23 world-record benchmarks, cuOpt owns all of the world records on the largest routing benchmarks from the past three years.

Advances in Operations Optimization

Explore recent advances in pickup and delivery, optimizing fleets of robots, digital twins, and more.

Operational Research, Logistics, and Route Optimization

cuOpt uses GPU-accelerated logistics solvers relying on heuristics, metaheuristics, and optimizations to calculate complex vehicle routing problems with a wide range of constraints. cuOpt can be deployed in any data center or cloud. With support for distance and time matrices with asymmetric patterns, it can be seamlessly integrated with popular map engines.

Explore the Features of NVIDIA cuOpt

Dynamic Rerouting

Rerun models and adjust for changes like inoperable vehicles, traffic and weather disruptions, and the addition of new orders—all within service-level agreement (SLA) time constraints.

World-Record Accuracy

Experience world-record performance, achieved across Li & Lim and Gehring & Homberger accuracy benchmarks.

Scale Seamlessly

Scale out to 15,000 routing tasks to facilitate computationally heavy use cases.

Real-Time Analytics

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

Lower Costs and Carbon Footprint

Achieve a 15 percent reduction in travel times and fuel costs, an 87 percent decrease in cloud resource costs, reductions in data center usage

Enterprise Offering

Access a secure, production-ready microservice, as part of NVIDIA AI Enterprise, designed to deploy anywhere and accelerate time to value.

NVIDIA cuOpt—Now Available

cuOpt—which owns all 23 world records set in the past three years on the largest routing benchmarks—is now available.

Use Cases of cuOpt

Last-Mile Delivery

Fleets of trucks are dispatched from distribution centers to deliver orders to stores and end customer addresses. cuOpt reduces miles driven and accelerates delivery times with the same level of accuracy.

NVIDIA cuOpt reduces miles driven and accelerates delivery times

Field Dispatch

A service provider is dispatched to fulfill a list of different service requests. These are allocated a certain amount of time per service request and the time can vary according to request. For example, a telecommunications technician is assigned to a customer’s home to install a router and then to a different home to install a data cable. cuOpt enables technicians to be equipped with all required tools before departure and complete the tasks based on optimized schedules.

AT&T Supercharges Operations With cuOpt

Fleet Management

For the inbound and outbound transportation of goods and vehicles with long-haul fleets, it’s critical to optimize scheduling and route planning. cuOpt allows users to factor in the number of available pilots, drivers, or ships to recommend the most optimized route and schedule.

cuOpt recommends the most optimized route and scheduling

Warehouse and Factory Robotics

Efficient picking and packing play a large role in warehouse operations and meeting customer expectations. With cuOpt, companies can create better human-machine interactions for automated storage and retrieval, dynamically routing and rerouting robots for efficient truck loading as new orders arrive and old orders are returned.

Dynamically routing and rerouting robots for efficient truck loading

Supply Chain Management

The retail, energy, and manufacturing industries can benefit from cuOpt for long-haul transportation management, pick-up path optimization within a warehouse from receiving dock to shipping dock, return optimization, and auto-fulfillment optimization.

Pick-up path optimization within a warehouse from receiving dock to shipping dock

Pick Up and Drop Off

A vehicle fulfills orders by picking them up and dropping them off at a different location. For example, a food delivery driver picks up a food order from a restaurant and delivers it to the customer’s home address. cuOpt allows users to tune and set their own solver time, independent of the number of tasks or locations. It optimizes routes with acceptable solution quality in seconds.

NVIDIA brings AI to the supply chain

Starting Options

Get Started With NVIDIA cuOpt

Use the right tools to take logistics optimization projects from development to production.

Experience APIs and Interactive Demos

For individuals looking to experience cuOpt, the API catalog offers a UI-based playground and access to NVIDIA-managed API endpoints for free as a great starting point.

Try Before You Buy

For enterprises looking to try cuOpt before purchasing NVIDIA AI Enterprise for production, there are two options to get started for free:

Without Infrastructure:
For those without existing infrastructure, NVIDIA offers free hands-on labs through NVIDIA LaunchPad.

With Infrastructure:
For those with existing infrastructure, NVIDIA offers a free evaluation license to try NVIDIA AI Enterprise for 90 days.



World Record Route Optimization With NVIDIA cuOpt

Find out how organizations are driving greater efficiency, saving money, and boosting revenue and customer satisfaction with real-time route optimization.

Optimized Vehicle Routing Course

In this self-paced course from the NVIDIA Deep Learning Institute, you’ll work through a common vehicle routing optimization problem and learn how to preprocess input data for use by cuOpt, composing variants of the problem that reflect real-world business constraints.

Route Optimization LaunchPad Lab

Have an accelerated optimization project? Get access to the route optimization workflow with a free curated lab in NVIDIA LaunchPad, which includes a step-by-step guide and ready-to-use software, sample data, and applications.

Accelerated AI Logistics and Route Optimization 101

In this hands-on lab, you’ll get a brief introduction to a vehicle routing problem and learn how to create a real-time fleet routing workflow using GPU-accelerated heuristics, metaheuristics, and optimization solvers. You’ll use RAPIDS™, GPU-accelerated Python libraries, and cuOpt to solve a real-world supply chain problem.

NVIDIA Scores 23 World Records for Route Optimization

NVIDIA cuOpt world-record-breaking route optimization engine helps Kawasaki Heavy Industries with railway safety and Adient in manufacturing optimizations.

Solving Complex Routing Problems With NVIDIA cuOpt

Explore an in-depth guide to the various ways you can get started with NVIDIA cuOpt, including trying it from your browser through the NVIDIA API catalog or trying the route optimization AI workflow in NVIDIA LaunchPad.

Optimizing Robot Route Planning With NVIDIA cuOpt

The NVIDIA cuOpt for Isaac Sim™ extension enables teams to tap into the accelerated performance of NVIDIA. You can generate thousands of environments and configurations in a fraction of the time by providing optimized task assignments and routing solutions informed by a collision-based occupancy map.

Advances in Operations Optimization

Learn about recent advances in accelerated routing with NVIDIA cuOpt, including advances in the pickup and delivery problem, the latest updates in optimizing fleets of robots and digital twins, and improvements to the user experience for cloud and enterprise deployments.

Optimizing Digital Twins to Reduce Intra-Factory Costs

Explore the ongoing collaboration between BMW, Ipolog, and NVIDIA that shows how digital twins and accelerated combinatorial optimization can lead to a 20 percent reduction in the required number of transport vehicles.

Solving the Largest Optimization Problems

Whether it’s optimizing for last-mile delivery, warehouse, and manufacturing, intra-logistics, or food pickup and delivery, organizations can improve efficiency and dynamically adjust plans. Learn how to enable new capabilities on dynamic rerouting, simulations in digital twins, and orchestration of fleets of autonomous robots by using cuOpt.


Reinventing Manufacturing Operations With NVIDIA cuOpt and Jetson Orin

Kawasaki Heavy Industries, Ltd. is a manufacturing company that’s been building large machinery for more than a hundred years. With NVIDIA cuOpt and Jetson Orin™, Kawasaki transformed its track maintenance and inspection capabilities.

cuOpt User Forum

Explore the online community for NVIDIA cuOpt, where you can browse how-to questions, learn best practices, engage with other developers, and report bugs.

NVIDIA Developer Program

Connect with millions of like-minded developers and access hundreds of GPU-accelerated containers, models, and SDKs—all the tools necessary to successfully build apps with NVIDIA technology—through the NVIDIA Developer Program.

Accelerate Your Startup

NVIDIA Inception is a free program for cutting-edge startups that offers critical access to go-to-market support, technical expertise, training, and funding opportunities.

Next Steps

Ready to Get Started?

Find the right resources to take route optimization projects from development to production.

Get in Touch

Talk to an NVIDIA product specialist about moving from pilot to production with the assurance of security, API stability, and support with NVIDIA AI Enterprise.

Get the Latest on NVIDIA cuOpt

Sign up for the latest news, updates, and more from NVIDIA.