Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

UWB chip and method for executing machine learning algorithm in chip

A technology of machine learning and on-chip execution, applied in neural learning methods, biological neural network models, electrical components, etc., can solve problems such as increased positioning delay and inability to perform machine learning calculations in real time, so as to reduce processing delay and positioning Effects of delay, real-time positioning, and high-precision positioning

Active Publication Date: 2022-04-12
杭州优智联科技有限公司
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, in the current implementation process, the time for the ARM processor to read the CIR memory will be much longer than the time for transmitting the UWB data frame, which limits the entire UWB communication system to only process data offline, and cannot perform machine learning calculations in real time. thus increasing the positioning delay

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • UWB chip and method for executing machine learning algorithm in chip
  • UWB chip and method for executing machine learning algorithm in chip
  • UWB chip and method for executing machine learning algorithm in chip

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention.

[0022] see figure 1 , which shows a schematic diagram of an exemplary UWB chip and peripheral circuit architecture in the current conventional solution. figure 1 It includes a UWB chip 100, an ARM processor 200, and a PC 300 for performing off-line neural network calculations. For the UWB chip, as shown by the dotted line box, it includes a receiving path part 11, a transmitting path part 12 and an SPI interface 13 for data transmission with the outside of the chip.

[0023] for figure 1 The receiving path part 11 shown in , based on the signal flow direction of the received signal, may include in turn: a receiving end antenna 110, a receiving end RF front-end circuit 111, an ADC 112, a correlator 113, a preamble detector 114, and an SFD detector 115 , PHR&PSDU decoder 116, C...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention discloses a UWB chip and method for executing a machine learning algorithm in the chip. The UWB chip comprises a neural network calculation part and an ARM processing core. Wherein the neural network calculation part is configured to read CIR data in an existing CIR memory on the UWB chip, and the UWB chip is configured to store the CIR data in the CIR memory. According to the CIR data, a trained neural network algorithm is used for calculation, and a non-line-of-sight NLOS decision value and correction data of a target corresponding to a UWB receiving signal are obtained; and the ARM processing core is configured to correct timestamp data transmitted from an existing timestamp calculation unit on the UWB chip according to the NLOS decision value and correction data transmitted by the neural network calculation part so as to obtain a corrected timestamp.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of Ultra Wide Band (UWB, Ultra Wide Band) chip design, and in particular to a UWB chip and method for executing machine learning algorithms on-chip. Background technique [0002] At present, the UWB radio frequency chip includes two parts: the receiving path and the transmitting path. For the receiving path part, after the receiving end antenna receives the UWB wireless signal, the UWB wireless signal is amplified and downloaded through the receiving end RF front-end circuit. Operations such as frequency conversion; then, the UWB wireless signal that has been amplified, down-converted, etc. is converted from an analog signal to a digital signal through an analog-to-digital converter (ADC, Analog-to-Digital Converter), and sent to the receiving demodulator. In the receiving demodulator, the data passes through the correlator, preamble detector, frame start delimiter (SFD, StartFrame Deli...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04W64/00G06N3/04G06N3/08
Inventor 不公告发明人
Owner 杭州优智联科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com