Machenta Unveils Instant Robot Learning from a Single Demonstration

Imperial College professor and Machenta CEO Ed Johns' team introduced Instant Robot Learning, a simulation-trained vision-demo-action foundation model that lets robots learn new tasks from a single demonstration. The team stressed steerability, ensuring the robot truly follows the demonstration rather than replaying pretrained behaviors.

2026-10-28 ~ 2026-10-29 · 2 related posts

• Robot learns new task from a single demo: Machenta unveils Vision-Demo-Action foundation model — Ed__Johns · 2026-10-28
• Machenta shows robots learning new tasks from a single demonstration — Ed__Johns · 2026-10-29