Robotics researcher: Embodied AI progress must push performance, not just cost

GlenBerseth · x · 2026-09-16

Robotics researcher Glen Berseth argues that recent embodied AI progress is only along one axis: cost. Real gains need performance — more object variety, robustness to the wild, multi-robot/human-robot interaction, real-time control, and better hardware. He points to self-driving cars as the clearest example: decades of effort, still hard, because they require real-time closed-loop feedback rather than cheaper static perception + planning.

Related event: Robotics researcher: foundation models only cut costs, performance is the real bottleneck(10 posts)→

Original post →

More from AGI Musings

AGI Musings channel →