NVIDIA brings AI to the supply chain



The global pandemic has created a supply chain crisis affecting just about every person and business on the planet.

For consumers, imbalances between supply and demand could be written off as a minus present under the Christmas tree. Businesses, however, count the balance sheet in millions of dollars of profit.

To help the $ 9 trillion logistics industry move goods efficiently from factories to stores and homes, NVIDIA today released NVIDIA ReOpt AI software.

Combining NVIDIA RAPIDS software with local search heuristics algorithms and metaheuristics such as Tabu search, NVIDIA ReOpt is an accelerated big data solver that optimizes real-time vehicle route planning and logistics.

NVIDIA ReOpt provides new tools for dynamic logistics and supply chain management to a wide range of industries, including transportation, warehousing, manufacturing, retail and quick-service restaurants.

A demonstration of ReOpt at NVIDIA GTC used NVIDIA Isaac Sim, powered by the NVIDIA Omniverse platform to simulate and collaborate in virtual worlds and 3D workflows, to first create a scalable robotic simulation application showing a re -dynamic optimization in a photorealistic environment.

At a time when the global supply chain faces massive disruption, NVIDIA ReOpt provides the AI ​​software required for everything from vehicle routing for last mile delivery to efficient picking and packaging of warehoused goods. for homes and offices.

From oven to door

The rapid exploitation of big data is crucial for Domino’s Pizza. The company claims there are 34 million ways to build a pizza – depending on the potential combinations of toppings, crust, cheese, sauce, and size. Providing all of these possible pizza combinations as efficiently as possible is important for hungry customers. Together with the NVIDIA ReOpt team, the company has implemented a real-time predictive system that helps it meet delivery standards important to dinner-hungry customers.

“The results we have achieved working with NVIDIA have shown great promise in delivering real-time, actionable insights that help us better serve our customers every day,” said Andrew Birch, vice president of data science at Domino’s.

Optimizing Domino’s Pizza Delivery Routes Using NVIDIA ReOpt

Planning for a post-pandemic economy

The logistics industry is a highly integrated network of supply chains that connects producers and consumers through multiple modes of transportation, including air and express delivery services, rail freight, ocean transportation, and transportation. truck transport.

Delivering goods directly to a customer’s door, known as last mile delivery, has been a costly challenge even before the pandemic disrupted logistics, just as millions more people have switched to online shopping.

It is estimated that more than half of total shipping costs result from last mile deliveries, which has an impact on profitability, according to ABI Research. According to logistics company Onfleet, companies themselves typically consume around 25% of that cost, a figure that is increasing due to inefficiencies in the supply chain.

ReOpt, now available in early access, offers software-driven process changes, including:

  • Route optimization. Dynamic Route Optimization uses advanced algorithms that provide dispatchers and drivers with a route that can dramatically reduce kilometers, fuel costs, CO2 emissions, and downtime. Businesses get real-time information on road conditions, traffic data, and route suggestions to create more accurate arrival windows.
  • Advanced constraints. Modeling of the movements of vehicles with finite capacities and different costs. This includes taking into account items such as fresh produce that must be transported by refrigerated trucks, or that customers are only available during specific windows.
  • Pick up in warehouse. Businesses can create better human-machine interaction for automated storage and retrieval during picking and packaging that dynamically route and reroute robots for efficient truck loading as new orders arrive.
  • Optimization of the fleet mix. Tracks routing throughout the supply chain with locations and fleet statistics for aircraft, train, truck and container fleets. The software can take into account the number of pilots, drivers or vessels available to operate these vehicles on a given day and take into account maintenance costs.

NVIDIA Accelerated Computing Delivers Industry-Leading Accuracy

NVIDIA GPUs deliver the computing power to power the most ambitious heuristics while supporting the toughest constraints. ReOpt takes advantage of NVIDIA’s massively parallel architecture to generate thousands of candidate solutions and refine them to select only the best in the end.

As a result, ReOpt can adapt to the most important issues in seconds with world-class precision. The software showed an average precision deviation of 2.96% from the world’s best-known solution for the number of vehicles, in the first tests on the Gehring & Homberger benchmark.

Try ReOpt on Google Colab today and sign up for updates and early access.


Nvidia Company published this content on November 09, 2021 and is solely responsible for the information it contains. Distributed by Public, unedited and unmodified, on 09 November 2021 08:22:04 AM UTC.


Leave A Reply

Your email address will not be published.