Memo Home Robot to Launch Beta
CyberRobooo · x · 2026-07-17
This update covers the new generation "Brain" for the home robot Memo, along with Sunday Robotics's progress on ACT-2.
Key takeaways:
- The biggest hurdle for home robots is the instability and complexity of real-world environments: messy clothes, lighting changes, children playing, and vast environmental differences.
- Last November, ACT-1 drew attention for its zero-teleop training and robust generalization.
- The new ACT-2 further proves that by scaling up pre-training, lab improvements can transfer more reliably to unseen new homes.
- The author cites the following results: a 99.1% zero-shot success rate for folding 9 types of clothing across various unseen environments.
- Beyond folding, the system exhibits more emergent capabilities: obstacle/disturbance recovery, perturbation resistance, and whole-body manipulation.
- Memo can also handle more tasks: vacuuming, organizing toys, zipping zippers, flipping pants, making coffee, etc.
- The plan is to enter household Beta testing this fall. It will initially remain a premium-priced product, but the author believes it could eventually expand to scenarios like hotels and Airbnb rentals.
Related event: Sunday Robotics Unveils ACT-2 Preview for Home Robots(17 posts)→
More from Embodied
- Hugging Face Teases Agentic Training Environments with OpenEnv for August Launch — mervenoyann · 2026-07-22
- NVIDIA shows 22 SIGGRAPH papers and Omniverse tools for robot simulation — facontidavide · 2026-07-22
- Nothing phone mockup turns a film joke into a modular design meme — ZeYanjie · 2026-07-22
- Lightwheel AI Launches SimReadyGen: Text-to-Physics-Accurate Robot Sim Assets — ZeYanjie · 2026-07-22
- Humanoid robot sorting packages in a warehouse sparks debate over job loss — MonaJalal_ · 2026-07-22
- NVIDIA pushes OpenUSD as the common layer for simulation and physical AI — MonaJalal_ · 2026-07-22