Narwal unveils Flow 2 with AI pet and object monitoring at CES 2026

· Source: Dataconomy · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Internet of Things (IoT) & Connected Devices, Robotics & Autonomous Systems · Depth: Fundamental Awareness, quick

Summary

Narwal unveiled its new Flow 2 smart robot vacuum at CES 2026, featuring advanced AI capabilities for pet and object monitoring. The Flow 2 uses two 1080p RGB cameras with a 136-degree field of view to map indoor areas and identify an unlimited number of objects through onboard and cloud-based AI processing. It includes specialized modes like pet care, which monitors pets and enables two-way audio, baby care for quiet operation near cribs and misplaced toy detection, and AI floor tag mode to recognize and avoid valuable items like jewelry. The vacuum also offers four cleaning modes, hot-water mop washing, and re-mopping of dirty areas. Narwal also introduced the U50 handheld vacuum with UV-C sterilization and a cordless vacuum with a 50-minute runtime and a 60-day auto-empty station.

Key takeaway

For AI Product Managers developing smart home devices, consider integrating multi-camera systems and hybrid local/cloud AI for comprehensive object recognition. Your product could offer specialized modes like pet or baby care to enhance user value beyond basic automation, providing features such as two-way audio or valuable item protection. This approach can differentiate your offerings in a competitive market.

Key insights

AI-powered robot vacuums can offer advanced object recognition and specialized care modes for pets and infants.

Principles

Method

Utilize dual 1080p RGB cameras for 136-degree indoor mapping. Employ local AI for initial object identification, offloading to cloud processing if local match fails.

In practice

Topics

Best for: Computer Vision Engineer, AI Product Manager, General Interest, Product Manager, Tech Journalist

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Dataconomy.