Answer extracted from the Business Wars podcast — listen to the full episode below.
Why is laundry folding such a difficult task for humanoid robots compared to other warehouse tasks?
Robots excel at repetitive tasks on rigid surfaces, but laundry presents a fundamentally different challenge: an average T-shirt is a wobbly noodle that requires real hard thinking about where to grab it. While robots have solved picking items from bins and sealing boxes, the variability inherent in folding laundry—every garment is different, every wrinkle is unpredictable—remains one of the hardest problems in warehouse automation.
The gap between success and failure in robotics often comes down to predictability. Robots love rigid structures and consistent patterns. A bin-picking task has clear parameters: locate the object, calculate the grip angle, execute the same motion thousands of times. A sealed box follows predictable physics. But a shirt in a laundry bin exists in a state of constant chaos—fabric bunched in unpredictable ways, sleeves tangled with other garments, moisture affecting texture and weight distribution.
As explained in the Business Wars episode, this variability problem scales across the entire task. Even if a robot could successfully identify and grab a single T-shirt, the next step—understanding how to fold it correctly—involves hundreds of micro-decisions that humans make intuitively but that robots must compute explicitly. Fabric drapes differently depending on material composition, size, and initial position. What works for cotton may fail for polyester. The spatial reasoning required is orders of magnitude more complex than the rigid-world problems robots have already solved.
"The world is already made for humans. So if you want to automate what people do in the world that we have now, you need something that is roughly shaped like a human that has the same reach as a human."
Christopher Mims — Tech Reporter, Wall Street Journal. Mims is the author of How to AI: Cut Through the Hype, Master the Basics, Transform Your Work and Arriving Today: From Factory to Front Door, Why Everything Has Changed About How and What We Buy. He has spent time with Colin Angle, the founder of iRobot, and has observed robotics developments across multiple countries, including China.
The laundry-folding barrier illustrates a broader lesson about automation: some tasks that seem simple to humans are computationally simple for robots, while others that appear straightforward are surprisingly hard. Folding clothes sits at the intersection of computer vision, spatial reasoning, and tactile feedback—three domains where robots still struggle with real-world variability. Christopher Mims discusses how this gap between human intuition and machine capability has shaped the robotics industry's focus on more tractable problems.
The failure to solve laundry folding has real economic consequences. Garment handling is labor-intensive across warehouses, dry cleaning facilities, and retail operations. If robots could master this task, the automation potential would be enormous. Yet year after year, the problem persists as one of the last great frontiers in warehouse robotics. The episode explores how iRobot and other companies have grappled with these kinds of unsolved problems throughout the robotics industry's evolution.
See also
Why is a humanoid robot design preferred over specialized robots for specific tasks?
The world is already made for humans, so if you want to automate what people do, you need something roughly shaped like a human with the same reach. A universal humanoid design adapts to existing human environments rather than requiring the world to change around specialized machines.
What institutional knowledge is lost when manufacturing is outsourced away from domestic designers and engineers?
When designers and engineers who create a device have direct access to the people manufacturing it, there is a feedback loop between factory floor and design team. This loop is crucial for innovation; outsourcing it breaks the chain of learning that drives continuous improvement.