The Manufacturing Executive · 8 Oct 2024 · 34m · Episode 226
Dr. Ariyan Kabir and Dr. SK Gupta, co-founders of GrayMatter Robotics, explain how their company automates high-mix, high-variability manufacturing by using AI to handle part-to-part variations that traditional robots cannot. They describe a subscription-based business model that includes hardware, software, and remote support, allowing smaller manufacturers to access automation without large capital expenditures. The guests detail how AI enables robots to autonomously program themselves, optimize process recipes, and monitor health to ensure reliability in applications like sanding and grinding. They also highlight the sustainability benefits of their technology, including significant reductions in consumable waste and energy consumption.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Engineering & simulationGMR AI software package
The AI scans a part to build a model and autonomously programs the robot, eliminating the need for human programming.
“So that means you need AI so that You can just scan the part, build a model of the part and then use that model to program the robot, right? So this planning aspect, we need AI because without the AI, Robot cannot autonomously program themselves.”
Speaker 4 · Hear it at 15:37
Engineering & simulationGMR AI software package
The AI allows the robot to adjust its plan on the fly based on sensory signals during execution to handle part-to-part variations safely.
“So all the data that it is seen, it can adjust the plan on the fly based upon whatever sensory signal it's getting. Because remember, we are using now sensors to monitor the process, it's not open look control, we get used in traditional mass production provides, right? So, this entire execution needs AI so that you can adopt, you can react, you can adjust things.”
Speaker 4 · Hear it at 15:37
Engineering & simulationGMR process pro
The AI enables the robot to autonomously conduct experiments to discover optimal process recipes (force, speed) for new materials, rather than copying human constraints.
“So robot could discover the optimal process recipe for performing an operation. Remember. A lot of people, when they copy recipe from human to the robot, they are unnecessarily putting constraints on what force Human applies. We don't care, right? The robot can apply significantly higher courses. Robot can go much faster. Robot is significantly more consistent. So robot could develop its own optimized recipes.”
Speaker 4 · Hear it at 15:37
Quality & testGMR Guardian
Proprietary AI technologies monitor process health and sandpaper wear to predict failures and take preventive actions autonomously.
“In GMR Guardian, we use certain AI technologies, proprietary AI technologies to enable the robot to determine when something can go wrong and take preventive actions on its own autonomously. In certain cases, it can also notify an end user or our remote support engineers who can intervene and prevent something bad from happening.”
Speaker 3 · Hear it at 11:55
early-stage companies
Other shows on the same ground, closest first.
Rajat Bhageria, Founder & CEO of Chef Robotics, explains how his company uses robotics and AI to address labor shortages in food manufacturing by automating the high-mix assembly (plating) stage. He details the strategic decision to launch in stealth mode to perfect the product with early enterprise customers like Amy's Kitchen, focusing on a 'robotics-as-a-service' model that aligns incentives through recurring revenue rather than upfront capital expenditure. Bhageria contrasts this approach with failed competitors who targeted fast-casual restaurants or used rigid dispensers, arguing that AI-driven flexibility is essential for handling the thousands of ingredient variations in modern food production.
Kim, CEO of Rapid Robotics, explains how the company pivoted from custom manufacturing automation to end-of-line boxing and palletizing using generative AI to solve labor shortages and handle high SKU variability. She details the development of Rapid ID, which allows robots to identify and handle diverse objects without extensive programming, contrasting this with the limitations of traditional robotics in brownfield environments. Kim also shares her background in the toy industry at Hasbro and how that experience informs her approach to scaling the company and supporting US manufacturing reshoring.
Rajad, CEO of Chef Robotics, explains how his company uses AI-powered robots to automate food assembly in high-volume manufacturing facilities, addressing labor shortages by handling thousands of ingredient variations. He details the pivot from targeting fast-casual restaurants to food manufacturing, the use of imitation learning and diffusion policies to teach robots new tasks, and the 'robotics as a service' business model. Rajad also discusses the challenges of market education, the hardware design of their 6-degree-of-freedom collaborative robots, and his skepticism regarding the near-term viability of general-purpose humanoid robots compared to specialized automation.
Dave Coleman, Chief Product Officer and Founder of Picknik Robotics, discusses the deployment of AI-powered robotics in unstructured commercial environments beyond traditional manufacturing. He outlines a framework of four generations of robotics technology, arguing for a hybrid approach that combines classical controls with machine learning subsystems to ensure safety and reliability. The hosts analyze recent industry news, including the World Humanoid Olympics in China, IFR market data, and Apple's $100 billion American manufacturing program.
Steve Crowe and Mike Oitzman discuss recent robotics news, including Waymo's role in a robbery and MIT's 'super limbs' for astronauts, before featuring interviews with Ling, CEO of OTSAW Robotics, and Etienne Lacroix, CEO of Vention. Ling explains how OTSAW pivoted to UVC disinfection robots during the pandemic and launched the highly configurable Camello Plus, utilizing an online configurator to gather market data and drive modular production. Etienne Lacroix details Vention's platform strategy to democratize industrial automation by combining hardware and software, reducing integration risks for small and mid-sized enterprises through productized 'Lego-like' components and cloud-based machine learning.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by The Manufacturing Executive. The episode itself belongs to its publisher.