{"id":564841,"date":"2023-01-19T12:03:23","date_gmt":"2023-01-19T17:03:23","guid":{"rendered":"https:\/\/www.therobotreport.com\/?p=564841"},"modified":"2023-01-20T09:48:58","modified_gmt":"2023-01-20T14:48:58","slug":"soft-robotics-mgripai-uses-simulation-to-train-in-nvidia-isaac-sim","status":"publish","type":"post","link":"https:\/\/www.therobotreport.com\/soft-robotics-mgripai-uses-simulation-to-train-in-nvidia-isaac-sim\/","title":{"rendered":"Soft Robotics mGripAI uses simulation to train in NVIDIA Isaac Sim"},"content":{"rendered":"
\"Soft

Soft Robotics grippers can move items that might be damaged by classic mechanical grippers. | Credit: Soft Robotics<\/p><\/div>\n

Robots are finally getting a grip. <\/p>\n

Developers have been striving to close the gap on robotic gripping for the past several years, pursuing applications for multibillion-dollar industries. Securely gripping and transferring fast-moving items on conveyor belts holds vast promise for businesses. <\/p>\n

Soft Robotics<\/a>, a Bedford, Mass. startup, is harnessing NVIDIA Isaac Sim<\/a> to help close the sim-to-real gap<\/a> for a handful of robotic gripping applications. One area is perfecting gripping for pick and placement of foods for packaging. <\/p>\n

Food packaging and processing companies are using the startup’s mGripAI system which combines soft grasping with 3D Vision and AI to grasp delicate foods such as proteins, produce, and bakery items without damage.<\/p>\n

“We\u2019re selling the hands, the eyes and the brains of the picking solution,\u201d said David Weatherwax, senior director of software engineering at Soft Robotics. <\/p>\n

Unlike other industries that have adopted robotics, the $8 trillion food market has been slow to develop robots to handle variable items in unstructured environments, says Soft Robotics. <\/p>\n

The company, founded in 2013, recently landed $26 million in Series C funding<\/a> from Tyson Ventures, Marel and Johnsonville Ventures.<\/p>\n

Companies such as Tyson Foods and Johnsonville are betting on the adoption of robotic automation to help improve safety and increase production in their facilities. Both companies rely on Soft Robotics technologies. <\/p>\n

Soft Robotics is a member of the NVIDIA Inception<\/a> program, which provides companies with GPU support and AI platform guidance. <\/p>\n

Getting a grip with synthetic data<\/b><\/h2>\n

Soft Robotics develops unique models for every one of its gripping applications, each requiring specific data sets. And picking from piles of wet, slippery chicken and other foods can be a tricky challenge. <\/p>\n

Utilizing Omniverse<\/a> and Isaac Sim, the company can create 3D renderings of chicken parts with different backgrounds, like on conveyor belts or in bins and with different lighting scenarios. <\/p>\n

The company taps into Isaac Replicator<\/a> to develop synthetic data, generating hundreds of thousands of images per model and distributing that among an array of instances in the cloud. Isaac Replicator<\/a> is a set of tools, APIs, and workflows for generating synthetic data using Isaac Sim.<\/p>\n