Why Humanoid Robots Still Can't Survive in the Real World

"Building robots is easier than making them function in the real world. A robot can repeat a TikTok routine on a flat surface, but the world has uneven sidewalks, slippery stairs and people that rush by. To understand the difficulty, imagine crossing a messy bedroom in the dark while carrying a bowl of soup; every movement requires constant reevaluation and recalibration."

"Artificial intelligence language models such as those that power ChatGPT don't offer an easy solution. They don't have embodied knowledge. They're like people who have read every book on sailing while always remaining on dry land: they can describe the wind and waves and quote famous mariners, but they don't have a physical sense of how to steer the boat or handle the sail."

Humanoid robots like C-3PO or Data remain uncommon despite impressive demonstrations because physical real-world environments introduce unpredictable challenges. Consumer and industrial robots handle constrained, repeatable tasks, but general-purpose humanoids must navigate uneven sidewalks, slippery stairs, and moving people. Real-world operation requires continuous reevaluation and recalibration of every movement, analogous to crossing a cluttered bedroom in the dark while carrying soup. Large language models lack embodied knowledge and cannot substitute for physical experience. Video footage of humans provides limited data because images fail to reveal precise 3D motions, and converting 2D video to accurate 3D behavior is generally very hard.

Read at www.scientificamerican.com