Pras Velagapudi, CTO of Agility Robotics, discusses deploying its Digit humanoid robot in logistics and manufacturing and shares lessons from customer deployments, including a GXO facility.
Velagapudi says customer value depends on much more than a robot performing a task: deployments also require integration, servicing, reliability, safety, validation, and a viable return on investment. At a GXO facility, Digit has worked full shifts for over a year, unloading an autonomous mobile robot and placing items on a conveyor. The task involves loads of about 30 pounds.
Velagapudi describes humanoids as one part of a broader automation system. He argues they are most useful when a task requires moving and handling objects at the same time, such as transferring items between conveyors, pallets, and mobile robots. For tasks that do not need mobile manipulation, he points to robot arms and mobile robots as suitable options.
Agility progressed from handling bins to cases and pallets, using lessons from simpler tasks to improve perception, grasping, and reliability for harder ones. Velagapudi also lays out a safety path: begin with restricted work zones, advance to robots that sense people and limit their function, and eventually enable people and robots to share a task. He says home use will take longer because a robot must reliably identify what it is handling, not just perform a known action such as folding a towel.
Customer KPIs include security, integration, reliability, and safe operation, alongside task completion. In a parts-washing workflow, the robot did not need to move faster because the machine took about a minute to run; avoiding dropped boxes of expensive components mattered more. In another deployment, changing the robot's motions cut cycle time by about 20% without changing hardware or the facility.
Velagapudi treats AI as an engineering tool whose value can be tested against deployment cost and task performance. Agility compared a learned reinforcement-learning balance controller with its model-based controller using physical disturbance tests. The learned controller was rolled out when test results showed it outperforming the existing approach.
Briefs summarise talks and interviews; timestamps open the video at that moment. Claims in a talk are the speaker's own.
Jonathan Hurst, co-founder of Agility Robotics, discusses Digit’s warehouse work, product development, safety, and the company’s path toward going public with a TechCrunch host at Disrupt 2026.
Peggy Johnson, CEO of Agility Robotics, discusses Digit 5’s safety, capabilities, and path to wider use with John Koetsier on NEXT.
Jonathan Hurst, co-founder of Agility Robotics, discusses the Digit 5 humanoid robot, its workplace uses and safety approach with Greg Nibler on FOX 12 Now in Oregon.
Pras Velagapudi, CTO of Agility Robotics, explains how the company approaches data security across its robots, cloud services, and customer deployments.
Daniel Diaz, chief business officer at Agility Robotics, joins John Koetsier on NEXT with John Koetsier to discuss Digit V5, commercial deployments, and working safely alongside people.
Agility Robotics co-founder and chief robot officer Jonathan Hurst joins John Furrier on theCUBE at MACHINA in Paris to discuss Digit’s path to commercial use, human-centered workflows, robot learning, and safety.
