Matic Robot Vacuum Ditches Lidar for 5-Camera Vision, NVIDIA Chip, and Voice Control
Aiden_Tech_Ai · x · 2026-08-14
Matic has introduced its intuitive home robot vacuum, adopting Tesla's pure vision approach by ditching traditional Lidar. Instead, it uses 5 cameras paired with an NVIDIA chip for on-device inference.
- Semantic Recognition: Instead of merely detecting obstacles, it identifies specific items like charging cables, toys, or pet waste, and cleans them accordingly.
- Multimodal Interaction: The new Cues feature supports voice and gesture controls. Users can point at a spill and say "clean this," prompting the robot to locate it in 3D space and handle the task autonomously.
- Background: Backed by $115M in funding and 9 years of R&D, the robot understands 75 languages and is designed to be accessible for everyone from 5-year-olds to 80-year-olds.
More from Embodied
- DynaRobotics CEO Lindon Gao on running deployment and research feedback loops together — micoolcho · 2026-10-16
- AutoAgent0: VLM-powered agentic runtime lifts long-tail driving success by 28.3pp — yining_hong · 2026-10-16
- CarryOn: dual-loop harness adds personalization and safe recovery to frozen VLA robots — Zixuan Wang · 2026-10-16
- FoveaVLA replaces wrist cameras with learned foveation, hitting 70.8% success — Haoyu_Xiong_ · 2026-10-16
- Musk teases two-way Grok x Optimus integration: Grok in the bot, bot in Grok — beffjezos · 2026-10-16
- SimVTA uses simulator-rendered video to post-train driving world action models with RL — OpenDriveLab · 2026-10-16