Skip to content
K = 0.731

Qianli Technology Introduces AI-Powered 4D Radar with a 10 TOPS NPU

1 reports 1 reporting sources 9 hours agoNew

Understand the event

AI overview

Qianli Technology has introduced an AI-powered 4D millimeter-wave radar with a 10 TOPS neural processing unit and three operating modes: processing data locally, transmitting raw data to a vehicle’s central computer, or doing both in parallel. The radar uses data-driven models in signal processing and perception, including point-cloud detection, angle estimation, point-cloud enhancement, and target tracking and classification. Qianli also incorporates algorithms into antenna-array and waveform design to reduce reliance on manually defined rules and thresholds. According to Qbit, compared with Qianli’s previous DSP-based 4D radar, the new radar delivers 10 times the point-cloud density, a 40% improvement in detection range and a 12-fold improvement in spatial angular resolution.

Generated by AI from reports · Updated 1 hours ago

Latest development10/27 18:40 (UTC+8)
Yin Qi’s Qianli Technology introduces AI-powered 4D radar with a 10 TOPS NPU量子位

Read next

More changes in today’s briefingIntroducing GPT-6.1 Terra

Report timeline

Follow the reports to explore different sides of the event.

10/27
  1. 量子位
    Yin Qi’s Qianli Technology introduces AI-powered 4D radar with a 10 TOPS NPU

    Qianli Technology, led by Yin Qi, has introduced a 4D millimeter-wave radar with a 10 TOPS NPU and data-driven models spanning signal processing through perception. It supports local processing, raw-data transmission to central vehicle computing, or both in parallel. The report states that, compared with Qianli’s previous DSP-based 4D radar, point-cloud density increases 10-fold, detection range improves 40%, and spatial angular resolution improves 12-fold.

Keep up with AI, one email a day

Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.