System and method for sensing an environment
A system and corresponding method sense an environment. The system comprises a wireless transmitter device that transmits a wireless signal through the environment. The system further comprises a plurality of wireless receivers that each 1) receive the wireless signal at a distinct location within the environment via at least one respective antenna and 2) generate a channel state information (CSI) packet indicating a state of a wireless communications channel associated with the wireless signal. The system still further comprises a computing device and classifier. The computing device processes the CSI packets from the plurality of wireless receivers and generates a CSI dataset as a function of the CSI packets processed. The classifier determines at least one class for the CSI dataset. The system and corresponding method improve robustness of sensing operations, such as robustness of Wi-Fi sensing operations to noise and interference.
1 . A system for sensing an environment, comprising:
a wireless transmitter device configured to transmit a wireless signal through the environment;
a plurality of wireless receiver devices each configured to 1) receive the wireless signal at a distinct location within the environment via at least one respective antenna and 2) generate a channel state information (CSI) packet indicating a state of a wireless communications channel associated with the wireless signal, the distinct location being distinct from a location of the wireless transmitter device;
a computing device configured to process the CSI packets from the plurality of wireless receiver devices and generate a CSI dataset as a function of the CSI packets processed, wherein the computing device is further configured to process the CSI packets by removing a subset of information from the CSI packets based on a measured value of the subset; and
a classifier configured to determine at least one class for the CSI dataset.
2 . The system of claim 1 , wherein at least one receiver device of the plurality of wireless receiver devices includes a plurality of respective antennas including the at least one respective antenna.
3 . The system of claim 2 , wherein the at least one receiver device of the plurality of wireless receiver devices is further configured to generate the CSI packet as a function of the wireless signal as received at each of the plurality of respective antennas.
4 . The system of claim 2 , wherein the CSI packet generated by the at least one wireless receiver device of the plurality of wireless receiver devices indicates the state of the wireless communications channel at a plurality of distinct spatial points in the environment, each distinct spatial point of the distinct spatial points corresponding to a respective one of the plurality of respective antennas.
5 . The system of claim 1 , wherein the CSI packets indicate the state of the wireless communications channel at a plurality of distinct points in time and frequency.
6 . The system of claim 1 , wherein at least one wireless receiver device of the plurality of wireless receiver devices is configured to generate a plurality of CSI packets of the CSI packets, each CSI packet of the plurality of CSI packets indicating the state of the wireless communications channel at a distinct point in time and frequency.
7 . The system of claim 1 , wherein the classifier is trained via a training dataset and a few-shot learning (FSL) process.
8 . The system of claim 1 , wherein the classifier is further configured to determine the at least one class based on at least one previous class that was determined for a prior CSI dataset obtained at an earlier point in time relative to the CSI dataset.
9 . The system of claim 1 , wherein the at least one class includes classes corresponding to at least one of i) no movement within the environment, and ii) movement of an object within the environment.
10 . The system of claim 1 , wherein the at least one class includes classes corresponding to at least one of i) no persons within the environment, ii) a person walking within the environment, iii) a person running within the environment, iv) a person jumping within the environment, and v) a person respiring within the environment.
11 . The system of claim 1 , wherein the computing device includes the classifier, wherein the computing device is further configured to collect the CSI packets from multiple receivers of the plurality of wireless receiver devices, simultaneously, and to align, in time and frequency domains, data from the CSI packets collected from the multiple receivers, and wherein the wireless transmitter device, the computing device, and the multiple receivers are located at different locations of the environment.
12 . The system of claim 1 , wherein, to process the CSI packets, the computing device is further configured to perform singular value decomposition (SVD) on CSI data of the CSI packets.
13 . A method for sensing an environment, the method comprising:
transmitting, by a wireless transmitter device, a wireless signal through the environment;
at each wireless receiver of a plurality of wireless receiver devices, 1) receiving the wireless signal at a distinct location within the environment via at least one respective antenna and 2) generating a channel state information (CSI) packet indicating a state of a wireless communications channel associated with the wireless signal, the distinct location being distinct from a location of the wireless transmitter device;
processing, by a computing device, the CSI packets from the plurality of wireless receiver devices, wherein processing the CSI packets includes removing a subset of information from the CSI packets based on a measured value of the subset;
generating, by the computing device, a CSI dataset as a function of the CSI packets processed; and
determining, by a classifier, at least one class for the CSI dataset generated.
14 . The method of claim 13 , wherein at least one wireless receiver of the plurality of wireless receiver devices includes a plurality of respective antennas including the at least one respective antenna and wherein the method further comprises, at the at least one wireless receiver, generating the CSI packet as a function of the wireless signal as received at each of the plurality of respective antennas.
15 . The method of claim 14 , wherein the CSI packet generated by the at least one wireless receiver of the plurality of wireless receiver devices indicates the state of the wireless communications channel at a plurality of distinct spatial points in the environment, each distinct spatial point of the distinct spatial points corresponding to a respective one of the plurality of respective antennas.
16 . The method of claim 13 , wherein the CSI packets indicate the state of the wireless communications channel at a plurality of distinct points in time and frequency.
17 . The method of claim 13 , further comprising generating, by at least one wireless receiver of the plurality of wireless receiver devices, a plurality of CSI packets of the CSI packets, each CSI packet of the plurality of CSI packets indicating the state of the wireless communications channel at a distinct point in time and frequency.
18 . The method of claim 13 , wherein the method further comprises:
training the classifier via a training dataset and a few-shot learning (FSL) process; and
determining the at least one class based on at least one previous class that was determined by the classifier for a prior CSI dataset obtained at an earlier point in time relative to the CSI dataset.
19 . The method of claim 13 , wherein the at least one class includes classes corresponding to at least one of i) no movement within the environment, and ii) movement of an object within the environment.
20 . The method of claim 13 , wherein the at least one class includes classes corresponding to at least one of i) no persons within the environment, ii) a person walking within the environment, iii) a person running within the environment, iv) a person jumping within the environment, and v) a person respiring within the environment.
21 . A non-transitory computer-readable medium for sensing an environment, the non-transitory computer-readable medium having encoded thereon a sequence of instructions which, when loaded and executed by at least one processor, causes the at least one processor to:
process channel state information (CSI) packets received from a plurality of wireless receiver devices, each wireless receiver of the plurality of wireless receiver devices having 1) received a wireless signal at a distinct location within the environment via at least one respective antenna and 2) generated a CSI packet of the CSI packets received, the CSI packet indicating a state of a wireless communications channel associated with the wireless signal, the wireless signal transmitted through the environment, the distinct location being distinct from a location of the wireless transmitter device, wherein processing the CSI packets includes removing a subset of information from the CSI packets based on a measured value of the subset;
generate a CSI dataset as a function of the CSI packets processed; and
determine at least one class for the CSI dataset generated.
22 . The method of claim 13 , wherein the computing device includes the classifier and wherein the method further comprises:
collecting, by the computing device, the CSI packets from multiple receivers of the plurality of wireless receiver devices, simultaneously; and
aligning, in time and frequency domains by the computing device, data from the CSI packets collected from the multiple receivers, wherein the wireless transmitter device, the computing device, and the multiple receivers are located at different locations of the environment.
23 . The method of claim 13 , wherein the processing of the CSI packets includes performing singular value decomposition (SVD) on CSI data of the CSI packets.