MENU

Robot shelf stackers roll out in Japan

Robot shelf stackers roll out in Japan

Technology News |
By Nick Flaherty



Tokyo-based startup Telexistence is using AI-powered robots to restock shelves at hundreds of FamilyMart convenience stores in Japan.

FamilyMart has around 16,000 stores and Telexistence aims to save time for these stores by offloading repetitive tasks like refilling shelves to a robot, allowing retail staff to tackle more complex tasks like interacting with customers.

The robots run on Nvidia’s Jetson edge AI and robotics platform. The company is also developing AI-based systems for warehouse logistics with robots that sort and pick packages.

“We want to deploy robots to industries that support humans’ everyday life,” said Jin Tomioka, CEO of Telexistence. “The first space we’re tackling this is through convenience stores — a huge network that supports daily life, especially in Japan, but is facing a labour shortage.”

Telexistence will begin deploying its TX SCARA restocking robots this month and aims to bring the autonomous machines to additional FamilyMart locations, as well as other major convenience store chains in Japan and the US, in the coming years.

TX SCARA runs on a track and includes multiple cameras to scan each shelf, using AI to  identify drinks that are running low and plan a path to restock them. The AI system can successfully restock beverages automatically more than 98% of the time.

In the rare cases that the robot misjudges the placement of the beverage or a drink topples over, Telexistence has remote operators on standby, who can quickly address the situation by taking manual control through a VR system that uses the GPUs for video streaming.

TX SCARA’s cloud system maintains a database of product sales based on the name, date, time and number of items stocked by the robots during operation. This allows the AI to prioritize which items to restock first based on past sales data.

The system uses multiple AI models, with an object-detection model identifies the types of drinks in a store to determine which one belongs on which shelf. This is combined with another model that helps detect the movement of the robot’s arm, so it can pick up a drink and accurately place it on the shelf between other products. A third model is for anomaly detection: recognizing if a drink has fallen over or off the shelf. One more detects which drinks are running low in each display area.

The Telexistence team used custom pre-trained neural networks as their base models, adding synthetic and annotated real-world data to fine-tune the neural networks for their application. Using a simulation environment to create more than 80,000 synthetic images helped the team augment their dataset so the robot could learn to detect drinks in any colour, texture or lighting environment.

Telexistence further optimized its AI models using half-precision (FP16) instead of single-precision floating-point format (FP32).

For AI model training, the team relied on an Nvidia DGX Station. The robot itself uses two Jetson embedded modules: the AGX Xavier for AI processing at the edge, and the Jetson TX2 module to transmit video streaming data.

On the software side, the team uses the JetPack SDK for edge AI and the TensorRT SDK for high-performance inference. “Without TensorRT, our models wouldn’t run fast enough to detect objects in the store efficiently,” said Pavel Savkin, chief robotics automation officer at Telexistence.

www.nvidia.com

Related Nvidia articles

Other articles on eeNews Europe

 

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News

Share:

Linked Articles
10s