DJI Launches ROMO 2 Robot Vacuums With AI Cleaning
DJI announced in a press release the international launch of its ROMO 2 robot vacuum and mop series on September 3. The lineup includes the ROMO P2 and ROMO A2, with availability beginning in September through the DJI store and authorized retailers.
ROMO 2 uses AI to identify areas, debris and liquids, then adjust suction, mopping and route priorities. Its LiDAR guided robotic arm moves through a 123 degree arc, while the obstacle detection system can identify objects as thin as 2 mm, including cables, mats, glass and mirrors.
The system provides up to 36,000 Pa of suction and can cross single obstacles up to 4 cm high or two level obstacles up to 8.5 cm high. Its self cleaning base uses four water jets and a 16 mm debris suction port, with up to 365 days of operation without maintenance under DJI's test conditions. A full charge takes 2.5 hours with 55 W charging.
Users can disable the camera and microphone through the DJI Home app and request deletion of personal data. A local data mode is planned for the fourth quarter of 2026. Prices start at EUR 1,199 for ROMO A2 and EUR 1,299 for ROMO P2, while the ROMO Clean More Pack starts at EUR 1,349.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Robotics Brief or Daily AI Brief.
Also, consider following us on social media:
More from Robotics
Oct 27 Swarmer Buys Vataga Drone Technology and Hires 15 Staff Oct 27 Tensor and Münchner Taxi Zentrum Plan Up to 500 Robotaxis in Germany Oct 27 Physical Intelligence Seeks $20 Billion Valuation in Funding Talks Oct 27 Machenta raises $40 million for robot learning model Oct 27 MoSense Raises About RMB 100 Million for Robot Electronic SkinRobotics Brief
Weekly coverage of AI-driven robotics advances in industrial automation, autonomous vehicles, and robotic systems.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
E-Home Starts AI Home Service Robot Project in China
URC Robotics Develops X40 Autonomous Floor Cleaning Robot
RoboParty launches open source RP1 humanoid robot
DJI Launches Dock 4 With 25 Second Battery Swaps
RoboParty Unveils RP1 Open Source Humanoid Robot
Daily AI Brief: the AI news that matters, in your inbox.