Aaron McCall of Toyota Research Institute discusses robotics research, practical limits and emerging applications with the Automated Podcast host, alongside examples from robotics teams and research groups.
McCall says TRI’s diffusion policy lets robots learn complex behaviors through imitation without task-specific code. Its reliability is still developing: he cites applications where occasional failure may be acceptable, while noting it is not yet suited to settings that demand 99.9% uptime. Early uses could help gather the data needed to improve performance.
TRI gathers problems from Toyota, industry partners, universities and broader social needs to guide its research. For home assistance, McCall gives the example of helping someone with arthritis keep cooking by cutting an apple. He says Japan’s aging population already creates pressing needs in labor and elder care.
McCall says a microwave task succeeds around 40 to 50% of the time, with results improving as training data grows. He describes dexterity as difficult because robots must handle varied objects and situations, and says research teams need to match problems to current capabilities and potential impact. TRI aims to show both successful robot behaviors and their failure cases; McCall advocates for sharing bloopers.
The examples span an expressive lamp from Apple, Agility’s stability testing, Disney’s character-like robot, social robots for older adults and a research system for robotic stitches. McCall appreciates non-humanoid forms such as a lamp as a potentially approachable way to bring interaction into homes. The discussion also highlights the need to test safety and gather reactions from people who might use or encounter these systems.
Readers chose a RAI Institute project with an unusual mobile robot as the poll winner. McCall sees research demonstrations as a way to develop capabilities and collect feedback on where they might be useful, while simulation helps teams explore failure cases before testing on costly hardware. He says TRI is exploring manufacturing and logistics applications with Toyota for 2026.
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.
Jonathan Hurst, chief robot officer and co-founder at Agility Robotics, explains the software stack for humanoid robots operating in human environments.
Pras Velagapudi, CTO of Agility Robotics, explains how the company approaches data security across its robots, cloud services, and customer deployments.
Ankur Saxena, investment director at TDK Ventures, discusses humanoid robotics and physical AI with John Koetsier on NEXT with John Koetsier.
