自主家居助理機械人
Sunday Robotics的Memo可處理從未見過的物件
Sunday Robotics 旗下的 Memo 有別於其他家用機械人,毋須透過人手遠端操作即可學習,並能勝任最具挑戰性的任務之一——處理從未見過的物件。這家初創公司近日發布了驅動 Memo 的全新人工智能模型 ACT-2,據 Sunday Robotics 表示,在陌生家居環境及未經特定訓練的衣物上進行測試時,Memo 摺疊衣物的成功率超過 99%。Sunday Robotics 行政總裁兼聯合創辦人 Tony Zhao 向 Business Insider 表示:「我認為由於這項突破,2026 年將會是自主家用機械人發展時間表大幅縮短的一年。」
機械人能夠摺疊如圍巾般又長又軟的物件,與它只曾接受牛仔布訓練是兩碼子事;為展示 Memo 的最新能力,Sunday Robotics 發布了一段長達近三小時的影片,記錄機械人摺疊衣物的過程。
英文原文
Sunday Robotics' Memo sets itself apart as an autonomous robot for the home that doesn't need to learn through human teleoperation, and it capably tackles one of the most challenging tasks—handling objects it has never seen before. The startup recently unveiled ACT-2, a new AI model that powers Memo, and according to Sunday Robotics, Memo folded laundry successfully 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 shrinks in a very drastic way because of this breakthrough," Sunday Robotics CEO and cofounder Tony Zhao told Business Insider.
It's one thing for a robot to be able to fold something long and flimsy like a scarf when it's been trained on denim, and to show off Memo's newfound capabilities, Sunday Robotics released a video that's nearly three hours long of the robot folding laundry.
- 來源
- Trend Hunter
- 發布
- 2026-07-17
- 品類
- Robots
- 出處
- businessinsider, sunday.ai