Toyota Material Handling Europe, in partnership with Nvidia and SoftServe, is deploying digital twin technology to cut autonomous forklift commissioning time by up to 50 percent and reduce time-to-market by up to 40 percent. Using Nvidia Omniverse and Isaac Sim, the team simulates warehouse environments, tests safety logic, and trains vision systems — achieving a 70 percent improvement in pallet detection recall. Executives Johan Rosén and Ernesto Dominguez emphasize 'zero muda' as a core operational goal.
According to Robotics & Automation News, Toyota Material Handling Europe is using Nvidia simulation and digital twin technologies to reduce autonomous forklift commissioning effort by up to 50 percent, with a parallel goal of cutting time-to-market for autonomous material handling systems by up to 40 percent.
Simulation-first development with Nvidia and SoftServe
The project leverages Nvidia Omniverse libraries and the Nvidia Isaac Sim robotics simulation framework, while SoftServe — an Nvidia Elite Partner since 2022 and Advanced Technology Partner since 2026 — developed the digital twin environment tailored to Toyota Material Handling Europe’s production processes.
The collaboration enables virtual testing and validation of autonomous vehicle systems before deployment at customer sites. By recreating factory and warehouse environments digitally, engineering teams can evaluate autonomous forklift navigation, safety logic, and vehicle behavior in advance — identifying issues that would otherwise require on-site adjustments.
This simulation-first approach also supports testing of customer-specific edge cases, including interactions between autonomous vehicles, human workers, manually driven forklifts, and other floor traffic — all within the digital twin environment prior to physical installation.
Digital twin benefits beyond commissioning
Johan Rosén, senior vice president research and development at Toyota Material Handling Europe, stated:
“Through virtual commissioning and digital twin technology, we can secure quality while eliminating muda, or waste, before deployment begins. By identifying and resolving issues earlier in the process, we can reduce implementation effort, accelerate customer value, and deliver automation solutions with greater confidence.”
The initiative extends into machine vision: synthetic data generated via Nvidia Omniverse libraries and augmented with Nvidia Cosmos open world foundation models trained a camera-based pallet detection system. According to the company, this yielded a 70 percent improvement in object-detection recall when evaluated against real-world warehouse datasets.
Olha Moroz, EVP and head of EMEA at SoftServe, emphasized the zero-waste objective:
“Zero Muda sets a clear bar: eliminate waste before it happens, not after. SoftServe is proud to support this by using Nvidia Omniverse and simulation engineering built for Toyota Material Handling Europe’s customers — catching issues by using simulations in the digital twin world long before they could ever reach the forklift on the customer’s floor.”
Broader strategic goals
Ernesto Dominguez, president and CEO of Toyota Material Handling Europe, affirmed the company’s ambition to achieve zero muda:
“Our ambition is to achieve zero muda: removing waste that hinders productivity in material handling operations. By combining our lean thinking and automation expertise with Nvidia’s platform for physical AI and SoftServe’s engineering capabilities, we can accelerate innovation, improve solution quality and help customers achieve zero muda in their automated and autonomous operations.”
The broader objective is to shift more of the development, validation, and commissioning workflow into simulation — thereby minimizing operational disruption when autonomous systems are installed at customer facilities. The project was reported on October 20, 2026, and builds on foundational partnerships established as early as 2022.
Source: Robotics & Automation News
Compiled from international media by the SCI.AI editorial team.
