The Unbound Factory

Humanoid robots have long captured our imagination. Interest has skyrocketed along with the perception that robots are getting closer to taking on a wide range of labor-intensive tasks. What is driving this vision is not a preference for the human form but a recognition that humans are generalists—adaptable, quick to learn, and effortlessly retaskable. 

This stands in contrast with decades of industrial automation, which have led to enormous gains in productivity by narrowing the scope of solutions to well-bounded tasks. However, designing systems that can scale economically to address the high diversity and stiff requirements of industrial labor tasks remains a significant open challenge. 

Join us as we reflect on what we’ve learned by observing factory floors, and why we’ve grown convinced that chasing generalization in manipulation—both in hardware and behavior—isn’t just interesting, but necessary. We’ll discuss AI research threads we’re exploring at Boston Dynamics to push this mission forward, and highlight opportunities our field should collectively invest more in to turn the humanoid vision, and the reinvention of manufacturing, into a practical, economically viable product.