Why home robots keep failing, and how Sunday is trying to fix it
Tony Xiao, founder of Sunday Robotics, explains to the Sources Podcast hosts how the company is developing Memo, a home robot trained with data from wearable gloves.
Claire Zau of ZAUEY visits Sunday Robotics with CEO Tony Zhao and head of product Camila to discuss Memo, a household robot that learns chores from human demonstrations.
Sunday Robotics announced a $165 million Series B investment led by Coatue, putting the company’s valuation at $1.15 billion. Co-founder Tony Zhao says Memo uses a weighted wheeled base instead of walking legs; the robot weighs 170 pounds, including a 133-pound base. The team describes the design as passively stable: if power is cut while Memo reaches outward, its arms lower without the robot falling.
Memo moves slowly because its wheel speed is deliberately capped, with the team prioritizing safe task completion over speed. The company expects demonstrations across different homes and appliances to help its model adapt to unfamiliar setups, such as a new coffee machine. In a table-clearing demonstration, Memo handles many objects and decisions, including dealing with leftover liquids before loading dishes.
The team highlights the care required to handle transparent wine glasses: Memo must judge position and grip force to avoid breaking them. Folding socks presents another challenge because fabric changes shape as it is handled and lacks fixed visual landmarks. Sunday says Memo can adjust its movements when a person pulls a sock away, using ongoing perception and replanning.
Sunday developed sensor gloves before building Memo, so people can record household demonstrations that map to the robot’s movements. The company says more than 2,000 gloves have gone to paid memory developers, and it has gathered over 10 million episodes from more than 500 homes. Glove cameras and force sensors capture views and pressure; the team reviews recordings for smooth, usable examples and discards mistakes.
Sunday says it trains only on approved demonstrations and combines that data policy with compliant hardware features such as elbows that tuck when bumped. Memo currently runs for about four hours, and the team is considering a larger base battery, a charging dock, or manual plugging. Its cameras and microphones sit beneath the hat brim, while the visible eyes are decorative.
Briefs summarise talks and interviews; timestamps open the video at that moment. Claims in a talk are the speaker's own.
Tony Xiao, founder of Sunday Robotics, explains to the Sources Podcast hosts how the company is developing Memo, a home robot trained with data from wearable gloves.
Sunday Robotics cofounder Chungchi discusses collecting household robot training data with Scott and Mara on Marwa ElDiwiny’s show.
Rock of Over The Horizon talks with robotics designers Maharad Farmani and Scott Walter, and hand surgeon Gustav Anderson, about Sunday Robotics’ Mimo and its prospects for home and commercial work.
Sunday Robotics co-founders Tony Zhao and Cheng Chi join No Priors to discuss building Memo, a general-purpose home robot, and the data, hardware, and learning systems behind it.
Tony Zhao, co-founder and CEO of Sunday Robotics, discusses training home robots with human-collected data with Brian Heater on Automated Podcast.
Scott Walter, a robotics engineer and advisor, joins Over The Horizon hosts and guests to discuss Sharpa’s Dairy Queen deployment, Mimic’s dexterous hand, and Sunday Robotics’ home laundry results.