Robot Talk · 7 Nov 2025 · 30m · Episode 132
Anthony Jules, CEO and co-founder of Robust.AI, discusses the design and deployment of Carter, an AI-driven collaborative mobile robot for warehouses. Jules explains how Carter uses cameras instead of LIDAR to achieve semantic understanding, allowing it to navigate safely alongside humans and empower floor associates rather than replace them. He details the company's 'fleet learning' strategy, where data from individual robots is aggregated in the cloud to improve AI models offline, ensuring consistent productivity for clients like DHL without disrupting live operations.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Engineering & simulation
The AI system uses camera inputs to provide semantic understanding of the environment, allowing the robot to identify people, shelves, pallets, and forklifts for navigation.
“it only uses cameras, it doesn't use LIDAR. It has a semantic understanding of what's around it. So Carter knows when a person is nearby, it knows what a shelf looks like, it knows what a palette looks like.”
Speaker 2 · Hear it at 12:50
Engineering & simulation
AI algorithms process control signals to manipulate the robot's motors, creating a 'force feedback' effect that makes a heavy physical object feel weightless when a human pulls its handle.
“And when you grab onto that handle, we do some magic in the controls and AI to make all of the mass disappear so you can now move this, this thing that's 100 to 300 kilos in total mass.”
Speaker 2 · Hear it at 12:50
companies scaling up
Other shows on the same ground, closest first.
Steve Crowe, Gene Demaitre, and Mike Oitzman of The Robot Report recap RoboBusiness 2024, highlighting the launch of Robust AI's Carter Pro AMR and keynotes from Rodney Brooks and Sergey Levine. The hosts discuss the industry's shift toward practical utility, noting the prominence of outdoor robotics and the cooling of humanoid hype, while also reviewing the Startup Pavilion winner, Robotics 88. They emphasize the value of networking and the transition from novelty to profitable automation solutions in the warehouse sector.
AJ Mayer, CEO of the Boston-based Pickle Robot Company, explains how his startup uses reinforcement learning and deep neural networks to automate loading and unloading trucks with their 'Dill' robot, targeting brownfield logistics facilities rather than fully automated warehouses. He details the 'supervisor ratio' business model, where human operators handle the 2% of edge cases the robot cannot manage, and discusses the challenges of selling to enterprise customers during the pandemic. The episode also features Dave Niewinski from Clearpath Robotics, who discusses the strategic benefits of supporting ROS on Windows 10 for their Unmanned Ground Vehicles (UGVs), highlighting easier IT integration, cloud connectivity via Azure, and lower barriers to entry for corporate clients.
Chris Luecke and Jake Hall interview leaders from Plus One Robotics, IDS Imaging, Calvary Robotics, CMES Robotics, Lincode Labs, KUKA, and Locus Robotics at the A3 Vision Show and AMRL Conference in Boston. The guests discuss the persistent 'technology hesitancy' in warehouse automation, the critical role of machine vision in enabling mobile robots to operate in unstructured environments, and the workforce shortages driving adoption. They also share insights on market entry strategies, AI deployment for quality inspection, and the cultural differences between scaling a startup and operating within an enterprise.
John Santagate, Vice President of Robotics at Körber Supply Chain, discusses the integration of mobile robots in warehouses, highlighting the shift toward serving SMBs and the emerging viability of autonomous forklifts and humanoids like Agility Robotics' Digit. Peter Chen, Co-Founder and CEO of Covariant, explains their robotics foundation model approach, detailing how they leverage data from customers like Autogroup to improve AI performance and offer a simplified 'Covariant One' as-a-service pricing model. The episode covers the strategic decisions behind partnering with vendors like Locust Robotics and KUKA, and the economic arguments for Robotics as a Service (RAS) over traditional Capex models in warehouse automation.
Amir Bousani, CEO of RGO Robotics, and Jacob Petersen, Chief Commercial Officer of Wheel.Me Robotics, discuss how advanced perception engines enable autonomous mobile robots (AMRs) to operate in dynamic environments. They explain that Wheel.Me chose to integrate RGO’s software rather than building perception in-house to accelerate time-to-market and reduce costs. The conversation highlights the industry shift toward vision-based AI to solve deployment bottlenecks, such as long commissioning times and localization failures in changing warehouses. Additionally, the episode covers the recent unveiling of Collaborative Robotics' Proxie mobile manipulator and Mobile Industrial Robots' MC 600, signaling a surge in mobile manipulation products.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Robot Talk. The episode itself belongs to its publisher.