Artificial Intelligence: BMW’s Robots Powered by Nvidia AI
Robots help BMW tackle its plant logistical issues.
BMW (OTCMKTS: BMWYY) is known for allowing a high degree of customization in their cars to customers. For a car, as many as 100 different options are available, and as a result, 99% of car orders are unique to each customer. This level of customization translates into massive challenges in computing, logistics planning, and data analysis for BMW. The company has therefore deployed several robots at its factories. (Automation World)
Nvidia’s Isaac robotics platform
BMW has four types of material handling robots and a smart transport robot at its plants. Trained on Nvidia’s (NASDAQ: NVDA) Isaac robotics platform, these robots have neural networks. These are capable of “addressing perception, segmentation, and human pose estimation to perceive their environment, detect objects, navigate autonomously and move objects.”
“These robots are trained both on real and synthetic data using Nvidia graphics processing units (GPUs) to render ray-traced machine parts in a variety of lighting and occlusion conditions to augment real data.”
BMW’s army of robots
Material handling robots comprise SplitBots (stationary), PlaceBots (mobile), PickBots, and SortBots. Each has a unique role in the material handling chain inside the plant.
The Splitbots are capable of detecting and processing up to 450 types of containers. They pick up incoming, loaded plastic boxes of parts from the palette in the incoming area. They then put them onto a conveyor system for onward transmission to a warehouse.
The PlaceBots unload the parts boxes from the conveyor belt and place them on shelves.
The PickBot uses its robotic arm to pick up assorted small parts from the supply shelves.
Sortbots and their robotic manipulation arms pick up empty boxes and place them on a pallet for return to the supply area.
The autonomous Smart Transport Robot (STR) can deliver racks full of boxes. They can identify obstacles such as forklift trucks, as well as humans, to more accurately and quickly suggest alternative routes as needed. They can also learn from the environment and apply different responses to people and objects.
According to Hanns Huber, with BMW Group’s Communications Production Network, BMW engineers commenced working on the robots alongside Nvidia in 2019.
Teams from the two companies closely collaborated to customize and develop robotic solutions for BMW’s logistical problems.
“The first STR with Nvidia technology was deployed as a proof-of-technology in our logistics laboratory in Munich in May 2020,” says Huber. “The first productive test will go live by the fourth quarter of 2020.”
Related Story: Marty the Robot Hunts for Spills in Supermarket Aisles
Images source: Nvidia
Latest Alternative Investment News
Evidation Health’s Achievement platform collects everyday health data for use in innovative research and health platforms. Giving due emphasis to user privacy and controlled, permissioned health data, the platform gathers…
MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), Ava Robotics, and the Greater Boston Food Bank (GBFB) collaborated on a robotic solution to the problem of disinfecting a large area…
Alternative Investments: TrueMark Investments Launches A Structured Outcome ETF That Tracks the S&P 500 Index
TrueMark Investments has launched the TrueShares Structured Outcome (July) ETF (NYSEAMERICAN: JULZ) that offers investors exposure to the S&P 500 price index. The ETF is a “structured outcome” product, the…
The Supreme Court of India recently struck down a circular issued by the Reserve Bank of India that barred banks from serving crypto businesses such as traders, exchanges, or others….