In the race to bring autonomous robots into the home, Sunday Robotics says it has solved one of the field’s toughest problems: getting a robot to work in homes and handle objects it has never seen before. On Thursday, the Bay Area-based startup unveiled ACT-2, a new artificial intelligence model that powers Memo, its wheeled
In the race to bring autonomous robots into the home, Sunday Robotics says it has solved one of the field’s toughest problems: getting a robot to work in homes and handle objects it has never seen before.
On Thursday, the Bay Area-based startup unveiled ACT-2, a new artificial intelligence model that powers Memo, its wheeled home robot. Sunday said Memo successfully folded laundry more than 99% of the time when tested in unfamiliar homes and on garments it had not been specifically trained to handle.
“I think 2026 will be when the timeline for autonomous home robots will be reduced very dramatically because of this advancement,” Sunday Robotics CEO and co-founder Tony Zhao told Business Insider.
For decades, home robot companies have struggled to build machines that are reliable and adaptable. A robot can master a task in a controlled environment and fail in a new room or when given an unfamiliar object, such as folding a scarf when it has been trained to fold jeans. Sunday says ACT-2 can carry over what you learn in one setting to the next, potentially avoiding the costly process of retraining Memo for each home.
Sunday raised $165 million earlier this year at a valuation of $1.15 billion.
On Sunday he proposed a new robotics standard
On Sunday he also proposed a new industry standard to measure progress in robotics. Called “Solution,” it aims to distinguish reliable capabilities from flashy demonstrations that often omit how many tries a robot needed or the conditions under which it was tested.
“Each demo is a different robot, environment, and object, and it’s really hard to know if we’re making progress,” Zhao said. “It’s like comparing apples to oranges.”
Under Sunday’s framework, companies would clearly indicate what a robot can do, where it was tested and how much additional training or human assistance it requires in each new environment.
Sunday considers folding clothes to be Memo’s first Solve capability.
To achieve that level of reliability, Sunday trains ACT-2 in two stages. First, you learn basic physical skills from people performing everyday tasks while wearing gloves equipped with sensors that Sunday developed in-house. The gloves cost about $200 to make and mirror the shape and sensor layout of Memo’s hands, allowing human movements to be translated more directly into the robot’s movements.
Sunday’s internal fleet of robots then allows the model to learn from its mistakes. With its initial knowledge, the robot can learn new skills and improve its performance in a matter of minutes.
“Memo’s performance in our office transfers almost perfectly to his performance in the wild,” Zhao said.
He added that the company has spent the last few months testing the model in employee homes and Airbnbs to see how well it works in unfamiliar environments.
Sunday competes with other domestic robots
Zhao, who left Stanford’s computer science Ph.D. schedule to build on Sunday, and co-founder Cheng Chi founded the company with a small team in a Silicon Valley hacker house in 2024. They chose to focus on the home because, unlike a factory, it is messy and unpredictable. Building a robot that can handle that, Zhao said, is the clearest path to physical artificial general intelligence, a term for AI capable of performing a wide range of real-world tasks as well or better than humans.
The Sunday Memo robot. Sunday Robotics
Since then, Sunday has grown to more than 100 employees. Conviction’s Sarah Guo, who wrote the company’s first check, previously told Business Insider that she backed the founders because they were “completely expert researchers” with “a real commitment to creating products that deploy and an Elon-style religion for delivering a mass-market product.”
Sunday’s development comes as several companies prepare to install robots in homes. Y Combinator-backed Weave Robotics plans to start shipping Isaac 1, a $7,999 wheeled robot that folds laundry, in California this fall. 1X aims to start shipping its $20,000 NEO humanoid around the same time, while Tesla is working to bring Optimus into homes.
Sunday plans to place Memo in homes through a beta program this fall. Zhao declined to say how many houses would participate.
Memo will operate autonomously in homes, Zhao said, with a remote operator intervening only when customers need help, similar to the remote assistance used by Waymo’s self-driving vehicles. Unlike many robotics companies, Sunday doesn’t plan to use those interventions to collect training data in customers’ homes.
Sunday developed gloves equipped with sensors that mirror the shape and sensor layout of Memo’s hands. Sunday Robotics
“Being completely autonomous is the best way to build trust,” Zhao said. “We’re not trying to introduce a teleoperator into your home to collect your data so we can improve our model.”
Sunday previously demonstrated an earlier model, ACT-1, wiping down a table, loading a dishwasher and making a shot of espresso. The company wants ACT-2 to eventually make those capabilities more reliable, starting with laundry. It’s learning how to vacuum, organize toys, close zippers and make coffee.
Those tasks, Sunday said, are still not reliable enough.
Do you have any advice? Contact Rya Jetha via email at rjetha@businessinsider.com or sign in rjetha.07. Use a personal email address and non-work device; here is our guide to share information securely.