ACT-2 Achieves High Success Rate Folding Clothes in Homes
tonyzzhao · x · 2026-07-17
Sunday Robotics' Memo/ACT-2 has sparked significant discussion. The core message is that this robotic model reported a 99.1% success rate across nine types of clothing, handling sizes from XXS to 8XL under varying lighting, surfaces, and starting positions, all without specific in-home demonstrations or fine-tuning.
Its key breakthrough lies in its ability to learn a new behavior and generalize it to unseen environments with just one fine-tuning example. The system also exhibited emergent capabilities, such as:
- Picking up dropped garments
- Adjusting garment orientation
- Making finer folding corrections
- Replanning when a human interrupts the task
The post also noted that the median time for a successful fold is approximately 2 minutes.
Related event: Sunday Robotics Unveils ACT-2 Preview for Home Robots(17 posts)→
More from Embodied
- Robot learning researcher joins Mila to work on physical AI and RL — pcastr · 2026-10-27
- Full teardown: inside Zmotor's 32mm linear actuator for humanoids — MarwaEldiwiny · 2026-10-27
- Full Teardown of a Zmotor Linear Actuator Used in China's Humanoid Robots — MarwaEldiwiny · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- First unboxing shots of Apple's foldable "iPhone Duo" surface — chrisfirst · 2026-10-27
- Bedrock Robotics Raises $600M Series C as Autonomous Excavators Do Paid Work on US Job Sites — davidpattersonx · 2026-10-27