System and method for activating a voice assistant of a vehicle

Abstract

A system for activating a voice assistant of a vehicle includes a microphone, a first wireless module, a second wireless module, and a controller in electrical communication with the microphone, the first wireless module, and the second wireless module. The controller is programmed to transmit a plurality of raw training signals on a plurality of subcarriers using the first wireless module. The controller is also programmed to receive a plurality of propagation training signals using the second wireless module. The controller is also programmed to determine a deviation between the plurality of raw training signals and the plurality of propagating training signals. The controller is also programmed to identify a motion marker based at least in part on the deviation. The controller is further programmed to activate a voice assistant of the vehicle based at least in part on the motion marker to receive a voice command using the microphone.

Description

Technical Field

[0001] The present disclosure relates to a system and method for activating a voice assistant of a vehicle. Background Art

[0002] Vehicle voice assistant functionality is used to enable a person to interact with the vehicle by providing voice commands. Motion detection systems can be used to verify that voice commands are intentional and authorized. There are currently a variety of technologies for detecting the presence of an individual in the vicinity of a vehicle. For example, one type of motion detection system may include a radar-based sensor disposed on the body of the vehicle to detect the presence of an individual. However, radar-based sensors may be obscured by objects in the environment, thereby reducing performance. There are also camera-based systems for detecting motion and presence, however, continuous video recording and / or streaming may result in increased resource usage. Touch-based motion detection mechanisms require the individual to touch the vehicle. Sound-based motion detection mechanisms may experience performance degradation in environments with high and / or changing sound intensity.

[0003] Therefore, while current voice assistants and motion detection systems achieve their intended purposes, a new and improved system and method for activating a vehicle's voice assistant is needed. Summary of the invention

[0004] According to several aspects, a system for activating a voice assistant of a vehicle is provided. The system may include a microphone, a first wireless module, a second wireless module, and a controller in electrical communication with the microphone, the first wireless module, and the second wireless module. The controller is programmed to send a plurality of original training signals on a plurality of subcarriers using the first wireless module. The controller is also programmed to receive a plurality of propagated training signals using the second wireless module. The controller is also programmed to determine deviations between the plurality of original training signals and the plurality of propagated training signals. The controller is also programmed to identify a motion marker based at least in part on the deviation. The controller is also programmed to activate the voice assistant of the vehicle to receive a voice command using the microphone based at least in part on the motion marker.

[0005] In another aspect of the present disclosure, to identify the motion signature, the controller is further programmed to determine a plurality of channel state information (CSI) values ​​based at least in part on deviations between the plurality of original training signals and the plurality of propagated training signals. To identify the motion signature, the controller is further programmed to identify the motion signature based at least in part on the plurality of channel state information (CSI) values. The motion signature includes at least one of: a low-fidelity motion signature and a high-fidelity motion signature.

[0006] In another aspect of the present disclosure, in order to identify a motion marker, the controller is further programmed to calculate a plurality of channel state information (CSI) value derivatives. At least one of the plurality of channel state information (CSI) value derivatives corresponds to each of the plurality of subcarriers. In order to identify a motion marker, the controller is further programmed to calculate a plurality of channel state information (CSI) value derivative values. Each of the plurality of channel state information (CSI) value derivative values ​​is a value of one of the plurality of channel state information (CSI) value derivatives. In order to identify a motion marker, the controller is further programmed to calculate a norm of the plurality of channel state information (CSI) value derivative values. In order to identify a motion marker, the controller is further programmed to calculate a time-averaged norm signal based at least in part on the norm. In order to identify a motion marker, the controller is further programmed to continuously compare the time-averaged norm signal with a predetermined time-averaged norm signal threshold. In order to identify a motion marker, the controller is further programmed to identify a low-fidelity motion marker in response to determining that the time-averaged norm signal is greater than or equal to a predetermined time-averaged norm signal threshold.

[0007] In another aspect of the present disclosure, in order to identify motion markers in the environment surrounding the vehicle, the controller is also programmed to use a machine learning algorithm to determine a motion classification of multiple channel state information (CSI) values. The machine learning algorithm is configured to receive multiple channel state information (CSI) values ​​as input and provide a motion classification of multiple channel state information (CSI) values ​​as output. The motion classification of the multiple channel state information (CSI) values ​​includes at least one of the following: motion toward the vehicle and motion away from the vehicle. In order to identify motion markers in the environment surrounding the vehicle, the controller is also programmed to identify a high-fidelity motion marker in response to determining that the motion classification of the multiple channel state information (CSI) values ​​is motion toward the vehicle.

[0008] In another aspect of the present disclosure, in order to activate a voice assistant of the vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to activate the microphone to receive a voice assistant keyword in response to determining that the motion signature includes a low-fidelity motion signature. In order to activate a voice assistant of the vehicle to receive a voice command using a microphone based at least in part on a motion signature, the controller is further programmed to determine the position of the key fob relative to the vehicle in response to detecting the voice assistant keyword using the microphone. In order to activate a voice assistant of the vehicle to receive a voice command using a microphone based at least in part on a motion signature, the controller is further programmed to perform a multi-factor authentication process in response to determining that the distance between the key fob and the vehicle is less than or equal to a predetermined key fob distance and the motion signature also includes a high-fidelity motion signature. In order to activate a voice assistant of the vehicle to receive a voice command using a microphone based at least in part on a motion signature, the controller is further programmed to execute the voice command received using the microphone in response to determining that the multi-factor authentication process was successfully performed.

[0009] In another aspect of the present disclosure, in order to activate a voice assistant of a vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to determine a motion classification of the key fob. The motion classification of the key fob includes at least one of: motion toward the vehicle and motion away from the vehicle. In order to activate a voice assistant of the vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to perform a multi-factor authentication process in response to determining that the distance between the key fob and the vehicle is less than or equal to a predetermined key fob distance, the motion signature also includes a high-fidelity motion signature, and the motion classification of multiple channel state information (CSI) values ​​matches the motion classification of the key fob. In order to activate a voice assistant of the vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to execute the voice command received using the microphone in response to determining that the multi-factor authentication process was successfully performed.

[0010] In another aspect of the present disclosure, the first wireless module is a first digital wireless local area network (WLAN) transceiver system configured to implement a wireless communication protocol. The second wireless module is at least one of: a second digital wireless local area network (WLAN) transceiver system configured to implement a wireless communication protocol; and a signal conversion device configured to convert signals between at least two frequency bands.

[0011] In another aspect of the present disclosure, the signal conversion device may further include a power supply, at least two antennas, and a conversion circuit in electrical communication with the power supply and the at least two antennas. The conversion circuit may include a mixer in electrical communication with the at least two antennas and an oscillator in electrical communication with the mixer.

[0012] In another aspect of the present disclosure, the conversion circuit may further include: a first amplifier in electrical communication with a first antenna of the at least two antennas and the mixer; and a second amplifier in electrical communication with the mixer and a second antenna of the at least two antennas.

[0013] In another aspect of the present disclosure, the conversion circuit may further include a first bandpass filter in electrical communication with the first amplifier and the mixer. The conversion circuit may further include a second bandpass filter in electrical communication with the mixer and the second amplifier.

[0014] According to several aspects, a method for activating a voice assistant of a vehicle is provided. The method may include sending a plurality of original training signals on a plurality of subcarriers using a first wireless module. The method may also include receiving a plurality of propagated training signals using a second wireless module. The method may also include determining deviations between the plurality of original training signals and the plurality of propagated training signals. The method may also include identifying a motion marker based at least in part on the deviations. The method may also include activating a voice assistant of the vehicle based at least in part on the motion marker to receive a voice command using a microphone.

[0015] In another aspect of the present disclosure, identifying the motion signature may further include determining a plurality of channel state information (CSI) values ​​based at least in part on deviations between a plurality of original training signals and a plurality of propagated training signals. Identifying the motion signature may further include identifying the motion signature based at least in part on a plurality of channel state information (CSI) values. The motion signature includes at least one of: a low-fidelity motion signature and a high-fidelity motion signature.

[0016] In another aspect of the present disclosure, identifying a motion signature may further include calculating a plurality of channel state information (CSI) value derivatives. At least one of the plurality of channel state information (CSI) value derivatives corresponds to each of the plurality of subcarriers. Identifying a motion signature may further include calculating a plurality of channel state information (CSI) value derivative values. Each of the plurality of channel state information (CSI) value derivative values ​​is a value of one of the plurality of channel state information (CSI) value derivatives. Identifying a motion signature may further include calculating a norm of the plurality of channel state information (CSI) value derivative values. Identifying a motion signature may further include calculating a time-averaged norm signal based at least in part on the norm. Identifying a motion signature may further include comparing the time-averaged norm signal to a predetermined time-averaged norm signal threshold. Identifying a motion signature may further include identifying a low-fidelity motion signature in response to determining that the time-averaged norm signal is greater than or equal to a predetermined time-averaged norm signal threshold.

[0017] In another aspect of the present disclosure, identifying a motion signature may further include determining a motion classification of a plurality of channel state information (CSI) values ​​using a machine learning algorithm. The machine learning algorithm is configured to receive a plurality of channel state information (CSI) values ​​as input and provide a motion classification of the plurality of channel state information (CSI) values ​​as output. The motion classification of the plurality of channel state information (CSI) values ​​includes at least one of: motion toward a vehicle and motion away from a vehicle. Identifying a motion signature may further include identifying a high-fidelity motion signature in response to determining that the motion classification of the plurality of channel state information (CSI) values ​​is motion toward a vehicle.

[0018] In another aspect of the present disclosure, activating a vehicle's voice assistant based at least in part on a motion signature to receive a voice command using a microphone may also include activating the microphone to receive a voice assistant keyword in response to determining that the motion signature includes a low-fidelity motion signature. Activating a vehicle's voice assistant based at least in part on a motion signature to receive a voice command using a microphone may also include determining a position of a key fob relative to the vehicle in response to detecting a voice assistant keyword using the microphone. Activating a vehicle's voice assistant based at least in part on a motion signature to receive a voice command using a microphone may also include performing a multi-factor authentication process in response to determining that a distance between the key fob and the vehicle is less than or equal to a predetermined key fob distance and the motion signature also includes a high-fidelity motion signature. Activating a vehicle's voice assistant based at least in part on a motion signature to receive a voice command using a microphone may also include executing a voice command received using a microphone in response to determining that a multi-factor authentication process was successfully performed.

[0019] In another aspect of the present disclosure, activating a vehicle's voice assistant based at least in part on a motion signature to receive a voice command using a microphone may also include determining a motion classification of a key fob. The motion classification of the key fob includes at least one of: motion toward the vehicle and motion away from the vehicle. Activating a vehicle's voice assistant based at least in part on a motion signature to receive a voice command using a microphone may also include performing a multi-factor authentication process in response to determining that a distance between the key fob and the vehicle is less than or equal to a predetermined key fob distance, the motion signature also includes a high-fidelity motion signature, and the motion classification of multiple channel state information (CSI) values ​​matches the motion classification of the key fob. Activating a vehicle's voice assistant based at least in part on a motion signature to receive a voice command using a microphone may also include executing a voice command received using a microphone in response to determining that the multi-factor authentication process was successfully performed.

[0020] In another aspect of the present disclosure, performing the multi-factor authentication process may further include authenticating the individual using at least one of the following: fingerprint recognition, voice recognition, and facial recognition.

[0021] According to several aspects, a system for activating a voice assistant of a vehicle is provided. The system may include a microphone configured to receive a voice command and a first wireless module. The first wireless module is a first digital wireless local area network (WLAN) transceiver system configured to implement a wireless communication protocol. The system may also include a second wireless module. The second wireless module is at least one of: a second digital wireless local area network (WLAN) transceiver system configured to implement a wireless communication protocol; and a signal conversion device configured to convert signals between at least two frequency bands. The system may also include a controller in electrical communication with the microphone, the first wireless module, and the second wireless module. The controller is programmed to send multiple original training signals on multiple subcarriers using the first wireless module. The controller is also programmed to receive multiple propagation training signals using the second wireless module. The controller is also programmed to determine the deviation between the multiple original training signals and the multiple propagation training signals. The controller is also programmed to determine multiple channel state information (CSI) values ​​based at least in part on the deviation between the multiple original training signals and the multiple propagation training signals. The controller is also programmed to identify motion markers in the multiple channel state information (CSI) values. The motion signature includes at least one of: a low-fidelity motion signature and a high-fidelity motion signature. The controller is further programmed to activate a voice assistant of the vehicle based at least in part on the motion signature to receive a voice command using the microphone.

[0022] In another aspect of the present disclosure, in order to identify a motion marker, the controller is further programmed to calculate a plurality of channel state information (CSI) value derivatives. At least one of the plurality of channel state information (CSI) value derivatives corresponds to each of the plurality of subcarriers. In order to identify a motion marker, the controller is further programmed to calculate a plurality of channel state information (CSI) value derivative values. Each of the plurality of channel state information (CSI) value derivative values ​​is a value of one of the plurality of channel state information (CSI) value derivatives. In order to identify a motion marker, the controller is further programmed to calculate a norm of the plurality of channel state information (CSI) value derivative values. In order to identify a motion marker, the controller is further programmed to calculate a time-averaged norm signal based at least in part on the norm. In order to identify a motion marker, the controller is further programmed to continuously compare the time-averaged norm signal with a predetermined time-averaged norm signal threshold. In order to identify a motion marker, the controller is further programmed to identify a low-fidelity motion marker in response to determining that the time-averaged norm signal is greater than or equal to a predetermined time-averaged norm signal threshold.

[0023] In another aspect of the present disclosure, in order to activate a voice assistant of a vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to activate the microphone to receive a voice assistant keyword in response to determining that the motion signature includes a low-fidelity motion signature. In order to activate a voice assistant of a vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to determine the position of the key fob relative to the vehicle in response to detecting the keyword using the microphone. In order to activate a voice assistant of a vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to determine a motion classification of the key fob. In order to activate a voice assistant of a vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to perform a multi-factor authentication process in response to determining that the distance between the key fob and the vehicle is less than or equal to a predetermined key fob distance, the motion signature also includes a high-fidelity motion signature, and the motion classification of the plurality of channel state information (CSI) values ​​matches the motion classification of the key fob. In order to activate a voice assistant of a vehicle based at least in part on a motion signature to receive a voice command using a microphone, the controller is further programmed to execute a voice command received using the microphone in response to determining that the multi-factor authentication process is successfully performed.

[0024] Further areas of applicability will become apparent from the description provided herein.It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.

[0026] Figure 1 is a schematic diagram of a system for activating a voice assistant of a vehicle according to an exemplary embodiment;

[0027] Figure 2 is a schematic diagram of a first wireless module according to an exemplary embodiment;

[0028] Figure 3 is a schematic diagram of a first wireless module and a second wireless module according to an exemplary embodiment;

[0029] Figure 4A is a flow chart of a method for activating a voice assistant of a vehicle according to an exemplary embodiment;

[0030] Figure 4B yes Figure 4A Continuation of the flowchart of;

[0031] Figure 5is a flow chart of a first exemplary embodiment of a method for determining a plurality of channel state information (CSI) values ​​according to an exemplary embodiment;

[0032] Figure 6 is a flow chart of a second exemplary embodiment of a method for determining a plurality of channel state information (CSI) values ​​according to an exemplary embodiment;

[0033] Figure 7 is a flow chart of an exemplary embodiment of a method for identifying low-fidelity motion markers in a plurality of channel state information (CSI) values; and

[0034] Figure 8 is a flow chart of an exemplary embodiment of a method for identifying a high-fidelity motion flag in a plurality of channel state information (CSI) values. DETAILED DESCRIPTION

[0035] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses.

[0036] The vehicle may include a voice assistant functionality that can be used to activate and / or control the vehicle's systems using voice commands. In some embodiments, the voice assistant can be configured to receive commands from a person outside the vehicle, as discussed, for example, in U.S. Patent No. 11,600,278, filed on April 19, 2021, entitled "Context-Aware Signal Conditioning for a Voice Assistant Outside a Vehicle," the entire contents of which are incorporated herein by reference. Therefore, it is necessary to distinguish between intentional / authorized use of a voice assistant and unintentional / unauthorized use of a voice assistant. Therefore, the present disclosure provides a new and improved system and method for activating a vehicle's voice assistant based on detection of presence and motion near the vehicle using wireless communication technology.

[0037] refer to Figure 1 , a system for activating a voice assistant of a vehicle is shown and is generally indicated by reference numeral 10. The system 10 is shown with an exemplary vehicle 12. Although a passenger vehicle is shown, it should be understood that the vehicle 12 may be any type of vehicle without departing from the scope of the present disclosure. The system 10 generally includes a controller 14 and a plurality of vehicle sensors 16.

[0038] The controller 14 is used to implement a method 100 for activating a voice assistant for a vehicle, as described below. The controller 14 includes at least one processor 18 and a non-transitory computer-readable storage device or medium 20. The processor 18 can be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor in a plurality of processors associated with the controller 14, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination of the above, or generally a device for executing instructions. The computer-readable storage device or medium 20 may include, for example, volatile and non-volatile storage devices in a read-only memory (ROM), a random access memory (RAM), and a keep-alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables when the processor 18 is powered off. The computer readable storage device or medium 20 may be implemented using a plurality of storage devices, such as: PROM (Programmable Read Only Memory), EPROM (Erasable PROM), EEPROM (Electrically Erasable PROM), flash memory or other electrical, magnetic, optical memory or combination storage devices capable of storing data, some of which represents executable instructions, used by the controller 14 to control various systems of the vehicle 12. The controller 14 may also be comprised of multiple controllers that are in electrical communication with each other. The controller 14 may be interconnected with additional systems and / or controllers of the vehicle 12, thereby allowing the controller 14 to access data, such as: the speed, acceleration, braking, and steering angle of the vehicle 12.

[0039] The controller 14 is in electrical communication with a plurality of vehicle sensors 16. In an exemplary embodiment, the electrical communication is established using, for example, a CAN network, a FLEXRAY network, a local area network (e.g., WiFi, Ethernet, etc.), a serial peripheral interface (SPI) network, etc. It should be understood that various additional wired and wireless technologies and communication protocols for communicating with the controller 14 are within the scope of the present disclosure.

[0040] The plurality of vehicle sensors 16 are used to obtain information about the environment 22 surrounding the vehicle 12. In an exemplary embodiment, the plurality of vehicle sensors 16 include at least a microphone 24, a global satellite navigation system (GNSS) 26, a first wireless module 28a, a second wireless module 28b, and a vehicle communication system 30.

[0041] In another exemplary embodiment, the plurality of vehicle sensors 16 further include sensors for determining performance data regarding the vehicle 12. In an exemplary embodiment, the plurality of vehicle sensors 16 further include a motor speed sensor, a motor torque sensor, an electric drive motor voltage and / or current sensor, an accelerator pedal position sensor, a coolant temperature sensor, a cooling fan speed sensor, and a transmission oil temperature sensor.

[0042] In another exemplary embodiment, the plurality of vehicle sensors 16 also include sensors for determining information about the interior environment of the vehicle 12 , such as seat occupancy sensors, cabin air temperature sensors, cabin motion detection sensors, cabin cameras, cabin microphones, etc.

[0043] In another exemplary embodiment, the plurality of vehicle sensors 16 also includes sensors for determining information about the environment 22 surrounding the vehicle 12 , such as an ambient air temperature sensor, a barometric pressure sensor, and / or a camera and / or video camera positioned to observe the environment 22 in front of the vehicle 12 .

[0044] In another exemplary embodiment, at least one of the plurality of vehicle sensors 16 is capable of measuring distances in the environment 22 surrounding the vehicle 12. In a non-limiting example, the plurality of vehicle sensors 16 include a stereo camera with distance measurement capabilities. In one example, at least one of the plurality of vehicle sensors 16 is fixed inside the vehicle 12, for example, fixed in the roof lining of the vehicle 12, with a field of view through the windshield of the vehicle 12. In another example, at least one of the plurality of vehicle sensors 16 is fixed outside the vehicle 12, for example, fixed on the roof of the vehicle 12, with a field of view of the environment 22 surrounding the vehicle 12. It should be understood that various additional types of vehicle sensors, such as LiDAR sensors, ultrasonic ranging sensors, radar sensors, and / or time of flight sensors are within the scope of the present disclosure. The plurality of vehicle sensors 16 are in electrical communication with the controller 14, as described above.

[0045] The microphone 24 is used to receive voice commands by converting sound waves into electrical signals. In an exemplary embodiment, the microphone 24 includes a unidirectional dynamic microphone (i.e., a microphone that converts sound waves into electrical signals using electromagnetic induction) that is configured to receive voice commands from a specific occupant of the vehicle 12. In another exemplary embodiment, the microphone 24 includes a plurality of micro-electromechanical systems (MEMS) microphones (e.g., a microphone having a pressure-sensitive diaphragm etched directly into a silicon wafer) configured to receive voice commands. It should be understood that other types of microphones configured to convert sound waves into electrical signals (e.g., digital and / or analog electrical signals) are also included within the scope of the present disclosure. In an exemplary embodiment, the microphone 24 is disposed inside the cabin of the vehicle 12 and is configured to receive voice commands from occupants inside the vehicle 12. In another exemplary embodiment, the microphone 24 is fixed to the outside of the vehicle 12 and is configured to receive voice commands from a person outside the vehicle 12. It should be understood that the microphone 24 can be located anywhere inside and / or outside the cabin of the vehicle 12 without departing from the scope of the present disclosure.

[0046] The global satellite navigation system (GNSS) 26 is used to determine the geographic location of the vehicle 12. In an exemplary embodiment, the global satellite navigation system (GNSS) 26 is a global positioning system (GPS). In a non-limiting example, the global positioning system (GPS) includes a global positioning system (GPS) receiver antenna (not shown) and a global positioning system (GPS) controller (not shown) in electrical communication with the global positioning system (GPS) receiver antenna. The global positioning system (GPS) receiver antenna receives signals from a plurality of satellites, and the global positioning system (GPS) controller calculates the geographic location of the vehicle 12 based on the signals received by the global positioning system (GPS) receiver antenna. In an exemplary embodiment, the global satellite navigation system (GNSS) 26 also includes a map. The map includes information about infrastructure, such as municipal boundaries, roads, railways, sidewalks, buildings, etc. Therefore, the map information is used to contextualize the geographic location of the vehicle 12. In a non-limiting example, the map is retrieved from a remote source using a wireless connection. In another non-limiting example, the map is stored in a database of the global satellite navigation system (GNSS) 26. It should be understood that various additional types of satellite-based radio navigation systems, such as the Global Positioning System (GPS), Galileo, GLONASS, and the BeiDou Satellite Navigation System (BDS) are within the scope of the present disclosure. It should be understood that the GNSS 26 can be integrated with the controller 14 (e.g., located on the same circuit board as the controller 14 or otherwise as part of the controller 14) without departing from the scope of the present disclosure.

[0047] refer to Figure 2 , which shows a schematic diagram of the first wireless module 28a. Figure 2 And continue to refer to Figure 1 , the first wireless module 28a is used to wirelessly communicate with other systems inside and / or outside the vehicle 12 (for example: the second wireless module 28b). In an exemplary embodiment, the first wireless module 28a includes a wireless control module 32 capable of implementing a wireless communication protocol that uses a training signal to perform channel state information (CSI) estimation. In a non-limiting example, the first wireless module 28a supports a wireless communication protocol in accordance with one or more of the Institute of Electrical and Electronics Engineers (IEEE) 802.11 wireless local area network (WLAN) related standards. Therefore, the first wireless module 28a is also referred to as a digital wireless local area network (WLAN) transceiver system. In an exemplary embodiment, the first wireless module 28a includes at least one wireless transceiver module 34 that electrically communicates with the wireless control module 32. At least one wireless transceiver module 34 is configured to send and receive signals on a first frequency band B1 (for example: a 2.4 GHz band). As Figure 2As shown, in another exemplary embodiment, the first wireless module 28a includes at least two wireless transceiver modules 34. The first wireless transceiver module 34a is configured to send and receive signals on a first frequency band B1. The second wireless transceiver module 34b is configured to send and receive signals on a second frequency band B2 (e.g., 5 GHz band).

[0048] In an exemplary embodiment, the first frequency band B1 and / or the second frequency band B2 are divided into a plurality of sub-frequencies (i.e., subcarriers). The data to be transmitted is divided into a plurality of data streams. Each of the plurality of data streams is modulated using one of the plurality of subcarriers for transmission. In an exemplary embodiment, a training signal for performing channel state information (CSI) estimation is sent on one or more subcarriers of each frequency band. In a non-limiting example, three subcarriers within the first frequency band B1 and / or the second frequency band B2 are used to send and / or receive training signals. In another non-limiting example, all subcarriers within the first frequency band B1 and / or the second frequency band B2 are used to send and / or receive training signals.

[0049] The second wireless module 28b is used to wirelessly communicate with other systems (e.g., the first wireless module 28a) inside and / or outside the vehicle 12. The second wireless module 28b can be implemented according to at least two exemplary embodiments. In the first exemplary embodiment, the second wireless module 28b is identical in structure and function to the first wireless module 28a described above. In the second exemplary embodiment, the second wireless module 28b is a signal conversion device configured to convert signals between the first frequency band B1 and the second frequency band B2. Figure 3 A second exemplary embodiment of the second wireless module 28b is discussed.

[0050] refer to Figure 3 , which shows a schematic diagram of a second exemplary embodiment of the first wireless module 28a and the second wireless module 28b. In the second exemplary embodiment, the second wireless module 28b includes a power supply 40, at least two antennas (ie, a first antenna 42a and a second antenna 42b) and a conversion circuit 44.

[0051] The power source 40 is used to provide power to the conversion circuit 44. In an exemplary embodiment, the power source 40 is connected to the power system of the vehicle 12, for example, the 12 volt electrical system of the vehicle 12. In another exemplary embodiment, the power source 40 is a battery. In another exemplary embodiment, the power source 40 is an energy harvesting device configured to harvest energy from, for example, radio frequency signals, light, vibrations, heat, etc., and convert the harvested energy into electrical energy. The power source 40 is in electrical communication with the conversion circuit 44. It should be understood that the power source 40 can be any device capable of providing power to the conversion circuit 44 without departing from the scope of the present disclosure.

[0052] The at least two antennas (i.e., the first antenna 42a and the second antenna 42b) are used to send and / or receive wireless communication signals. Figure 3 As shown, the first antenna 42a is used to receive wireless communication signals in the first frequency band B1, for example, wireless communication signals sent by the first wireless transceiver module 34a. Figure 3 As shown, the second antenna 42b is used to transmit wireless communication signals on the second frequency band B2, such as wireless communication signals that can be received by the second wireless transceiver module 34b. The first antenna 42a and the second antenna 42b are in electrical communication with the conversion circuit 44, as will be discussed in more detail below.

[0053] The conversion circuit 44 is used to convert wireless communication signals between the first frequency band B1 and the second frequency band B2. In an exemplary embodiment, the conversion circuit 44 includes a mixer 46, an oscillator 48, a first amplifier 50a, a second amplifier 50b, a first bandpass filter 52a and a second bandpass filter 52b. In an exemplary embodiment, the first amplifier 50a and the first bandpass filter 52a are packaged into a monolithic integrated circuit, which is called a combined amplifier with a bandpass filter (LNA+BPF) 54.

[0054] The mixer 46 is used to convert the signal received using the first antenna 42a between the first frequency band B1 and the second frequency band B2, also known as beat conversion. In an exemplary embodiment, the mixer 46 is a passive mixer including passive components (e.g., diodes). In another exemplary embodiment, the mixer 46 is an active mixer including active components (e.g., transistors). In a non-limiting example, the mixer 46 generates a signal at the mixer output of the mixer 46, which is the product of the two input signals provided to the first mixer input and the second mixer input. The first mixer input of the mixer 46 is in electrical communication with the oscillator 48. The second mixer input of the mixer 46 is in electrical communication with the first amplifier 50a. The mixer output of the mixer 46 is in electrical communication with the second bandpass filter 52b.

[0055] Oscillator 48 is used to generate an oscillating signal having a known frequency for mixer 46. In an exemplary embodiment, oscillator 48 is referred to as a local oscillator. In a non-limiting example, oscillator 48 is a crystal oscillator that generates an oscillating signal using a piezoelectric element. In another non-limiting example, oscillator 48 is a variable frequency oscillator capable of generating an oscillating signal having a variable frequency. Oscillator 48 is in electrical communication with a first mixer input of mixer 46. In an exemplary embodiment, oscillator 48 receives power from power supply 40.

[0056] The first amplifier 50a is used to amplify the signal received by the first antenna 42a. In an exemplary embodiment, the first amplifier 50a is a low noise amplifier (LNA). The low noise amplifier (LNA) is intended to amplify extremely low power signals, such as the current generated by the antenna, without significantly reducing the signal-to-noise ratio of the signal. In a non-limiting example, the first amplifier 50a also includes a filter or other electronic circuit designed to remove useless signals and / or noise from the current generated by the first antenna 42a. In a non-limiting example, the power supply 40 provides power and a DC bias signal to the first amplifier 50a. It should be understood that various additional types and / or topologies of amplifiers can be used to amplify the current generated by the first antenna 42a. The first amplifier 50a is in electrical communication with the first bandpass filter 52a and the second mixer input of the mixer 46.

[0057] The second amplifier 50b is used to amplify the signal generated by the mixer 46 for transmission by the second antenna 42b. In a non-limiting example, the power supply 40 provides power and a DC bias signal to the second amplifier 50b. It should be understood that amplifiers of various additional types and / or topologies can be used to amplify the electrical signal generated by the mixer 46 for transmission by the second antenna 42b. The second amplifier 50b is in electrical communication with the second bandpass filter 52b and the second antenna 42b.

[0058] The first bandpass filter 52a is used to filter the signal received by the first antenna 42a. In an exemplary embodiment, the first bandpass filter 52a is a passive device that uses resistance, inductance and / or capacitance to achieve bandpass filtering. In another exemplary embodiment, the first bandpass filter 52a is an active device that uses active components (e.g., operational amplifiers) to achieve bandpass filtering. The center frequency of the first bandpass filter 52a is located within the first frequency band B1, for example, at the center of the first frequency band B1. The first bandpass filter 52a is in electrical communication with the first antenna 42a and the first amplifier 50a.

[0059] The second bandpass filter 52b is used to attenuate the irrelevant frequency components introduced by the mixer 46. In an exemplary embodiment, the second bandpass filter 52b is a passive device that uses resistance, inductance and / or capacitance to achieve bandpass filtering. In another exemplary embodiment, the second bandpass filter 52b is an active device that uses active components (e.g., operational amplifiers) to achieve bandpass filtering. The center frequency of the second bandpass filter 52b is located within the second frequency band B2, for example, at the center of the second frequency band B2. The second bandpass filter 52b is in electrical communication with the mixer output of the mixer 46 and the second amplifier 50b.

[0060] Reference again Figure 1, the vehicle communication system 30 is used by the controller 14 to communicate with other systems outside the vehicle 12. For example, the vehicle communication system 30 includes the ability to communicate with vehicles ("V2V" communication), infrastructure ("V2I" communication), remote systems at remote call centers (e.g., General Motors' ON-STAR), and / or personal communication. In general, the term vehicle-to-everything communication ("V2X" communication) refers to communication between the vehicle 12 and any remote system (e.g., vehicle, infrastructure, and / or remote system). In a particular embodiment, the vehicle communication system 30 is a wireless communication system that is configured to communicate via a wireless local area network (WLAN) using the Institute of Electronics Engineers (IEEE) 802.11 standard or using cellular data communication (e.g., using GSMA standards, such as SGP.02, SGP.22, SGP.32, etc.). Therefore, the vehicle communication system 30 may also include an embedded universal integrated circuit card (eUICC) that is configured to store at least one cellular connection configuration profile, such as an embedded subscriber identity module (eSIM) profile. The vehicle communication system 30 is also configured to communicate via a personal area network (e.g., Bluetooth), near field communication (NFC), and / or any additional type of radio frequency communication. However, additional or alternative communication methods such as dedicated short-range communication (DSRC) channels and / or mobile telecommunication protocols based on the third generation partnership project (3GPP) standard are also considered to be within the scope of the present disclosure. Dedicated short-range communication (DSRC) channels refer to unidirectional or bidirectional short-range to medium-range wireless communication channels designed specifically for automotive use and a set of corresponding protocols and standards. The third generation partnership project (3GPP) refers to a partnership between multiple standard organizations that develop mobile telecommunication protocols and standards. The structure of the third generation partnership project (3GPP) standard is "version". Therefore, communication methods based on the third generation partnership project (3GPP) version 14, 15, 16 and / or future third generation partnership project (3GPP) versions are considered to be within the scope of the present disclosure. Therefore, the vehicle communication system 30 may include one or more antennas and / or communication transceivers for receiving and / or transmitting signals, such as collaborative sensing messages (CSM). The vehicle communication system 30 is configured to wirelessly transmit information between the vehicle 12 and another vehicle. In addition, the vehicle communication system 30 is configured to wirelessly transmit information between the vehicle 12 and infrastructure or other vehicles. It should be understood that the vehicle communication system 30 can be integrated with the controller 14 (e.g., integrated with the controller 14 on the same circuit board, or otherwise integrated as part of the controller 14) without departing from the scope of the present disclosure. It should also be understood that the first wireless module 28a and the second wireless module 28b can be integrated with the vehicle communication system 30 without departing from the scope of the present disclosure.

[0061] refer to Figure 4A, the method 100 for activating a voice assistant of a vehicle begins at box 102 and proceeds to box 104. At box 104, the controller 14 uses the first wireless transceiver module 34a and the second wireless transceiver module 34b to determine a plurality of channel state information (CSI) values, as will be discussed in more detail below. Within the scope of the present disclosure, the channel state information (CSI) values ​​describe how signals propagate between the first wireless transceiver module 34a and the second wireless transceiver module 34b.

[0062] More specifically, the channel state information (CSI) values ​​represent, for example, the combined effects of scattering, fading, and power attenuation. In other words, the channel state information (CSI) is an estimate of the frequency response of a transmission channel between two or more transceivers. In an exemplary embodiment, at least one of the multiple channel state information (CSI) values ​​corresponds to each of a plurality of subcarriers (i.e., sub-frequencies), as will be discussed in more detail below. In some applications, the channel state information (CSI) values ​​may be used to adjust transmission characteristics based on environmental conditions. In the present disclosure, the channel state information (CSI) values ​​are used to quantify motion in the environment 22 surrounding the vehicle 12.

[0063] In a non-limiting example, multiple channel state information (CSI) values ​​may be analyzed to identify motion markers. Within the scope of the present disclosure, a motion marker is a pattern in multiple channel state information (CSI) values ​​corresponding to the movement of a person in the environment 22 surrounding the vehicle 12. The motion marker may include at least one of the following: a low-fidelity motion marker and a high-fidelity motion marker. The low-fidelity motion marker indicates general movement or the presence of a person in the environment 22 surrounding the vehicle 12. The high-fidelity motion marker provides more specific information, such as: the position of the person relative to the vehicle 12, the type of movement of the person (e.g., walking, running, jumping, waving, etc.), the direction of movement of the person (e.g., toward the vehicle 12 or away from the vehicle 12), the speed of movement of the person, etc. The motion markers will be discussed in more detail below. After box 104, the method 100 proceeds to box 106.

[0064] At block 106 , the controller 14 determines whether a low-fidelity motion marker is identified in the plurality of channel state information (CSI) values, as will be discussed in greater detail below. Following block 106 , the method 100 proceeds to block 108 .

[0065] At block 108, if a low-fidelity motion marker was not identified at block 106, the method 100 continues to enter a standby state at block 110. If a low-fidelity motion marker was identified at block 106, the method 100 proceeds to block 112.

[0066] At box 112, the controller 14 activates the microphone 24. The microphone 24 is used to receive the voice assistant keyword. Within the scope of the present disclosure, the voice assistant keyword is a word or phrase that triggers the activation of the voice assistant when received by the microphone 24. The voice assistant keyword is sometimes also referred to as a "wake-up word". In an exemplary embodiment, the controller 14 uses a natural language processing (NLP) algorithm to analyze the sound received by the microphone 24 to identify the voice assistant keyword. After box 112, the method 100 proceeds to box 114.

[0067] At box 114, if the voice assistant keyword is not detected using microphone 24, the method 100 continues to enter the standby state at box 110. If the voice assistant keyword is detected using microphone 24, the method 100 proceeds to box 116.

[0068] At box 116, the controller 14 determines the position of the key fob relative to the vehicle 12. Within the scope of the present disclosure, a key fob is a device owned by the owner and / or operator of the vehicle 12. The key fob includes a key fob communication system, one or more key fob buttons, and a key fob controller in electrical communication with the key fob communication system and the one or more key fob buttons. Upon activation of one or more key fob buttons, the key fob controller sends a wireless transmission using the key fob communication system. In a non-limiting example, the vehicle communication system 30 is configured to receive the wireless transmission. The controller 14 is configured to take action based on the wireless transmission, such as: unlocking one or more doors of the vehicle 12, opening the trunk of the vehicle 12, activating the horn of the vehicle 12, etc.

[0069] In an exemplary embodiment, to determine the location of the key fob relative to the vehicle 12, the controller 14 uses the vehicle communication system 30. In a non-limiting example, the vehicle communication system 30 uses ranging based on a received signal strength indicator (RSSI) to determine the location of the key fob relative to the vehicle 12. In the scope of the present disclosure, the received signal strength indicator (RSSI) is a value that represents the power level of a wireless transmission received from the key fob. By correlating the received signal strength indicator (RSSI) with one or more known signal propagation characteristics (e.g., the inverse square law), the vehicle communication system 30 determines the distance between the key fob and the vehicle 12. In another non-limiting example, the vehicle communication system 30 uses ranging based on ultra-wideband (UWB) to determine the distance between the key fob and the vehicle 12 (e.g., according to the Institute of Electronic Engineers (IEEE) 802.15.4). In another non-limiting example, the vehicle communication system 30 uses personal area network communication (e.g., Bluetooth) to determine the distance between the key fob and the vehicle 12. It should be understood that any method for determining the distance between the key fob and the vehicle 12 is within the scope of the present disclosure. After frame 116 , the method 100 proceeds to frame 118 .

[0070] At box 118, the controller 14 compares the distance between the vehicle 12 and the key fob determined at box 116 to a predetermined key fob distance (e.g., five meters). If the distance between the vehicle 12 and the key fob is greater than the predetermined key fob distance, the method 100 continues to the standby state at box 110. If the distance between the vehicle 12 and the key fob is less than or equal to the predetermined key fob distance, the method 100 proceeds to box 120, as shown in FIG. Figure 4B shown.

[0071] refer to Figure 4B , showing Figure 4A . At box 120, the controller 14 determines whether a high-fidelity motion marker is identified in multiple channel state information (CSI) values. In an exemplary embodiment, a high-fidelity motion marker is identified based at least in part on a motion classification of multiple channel state information (CSI) values. Within the scope of the present disclosure, the motion classification includes, for example: motion toward the vehicle 12, motion away from the vehicle 12, gesture motion toward the vehicle 12, gesture motion away from the vehicle 12, etc. It should be understood that the motion classification may include any qualitative and / or quantitative characteristics of the motion in the environment 22 surrounding the vehicle 12. For example, in some embodiments, the motion classification includes a motion signature, which is a mathematical representation of the motion in the environment 22 surrounding the vehicle 12 (i.e., a mathematical equation, a mathematical function, a heat map, etc.). The determination of the motion classification of multiple channel state information (CSI) values ​​and the identification of high-fidelity motion markers will be discussed in more detail below. After box 120, the method 100 proceeds to box 122.

[0072] At block 122, if a high-fidelity motion marker was not identified at block 120, the method 100 proceeds to the standby state at block 110. If a high-fidelity motion marker was identified at block 120, the method 100 proceeds to block 124.

[0073] At frame 124, the controller 14 determines the motion classification of the key fob. In an exemplary embodiment, to determine the motion classification of the key fob, the controller 14 analyzes a plurality of distance measurements between the key fob and the vehicle 12. In a non-limiting example, if the distance between the key fob and the vehicle 12 is found to decrease over time, the motion classification of the key fob is motion toward the vehicle 12. In another exemplary embodiment, the controller 14 determines the motion classification of the key fob using a machine learning algorithm trained to classify motion. In a non-limiting example, the controller 14 provides a plurality of time-stamped distances between the key fob and the vehicle 12 to the machine learning algorithm. Based on the plurality of time-stamped distances, the machine learning algorithm classifies the motion of the key fob. After frame 124, the method 100 proceeds to frame 126.

[0074] At block 126, the controller 14 compares the motion classification of the plurality of channel state information (CSI) values ​​determined at block 120 with the motion classification of the key fob determined at block 124. Within the scope of the present disclosure, the motion classification of the plurality of channel state information (CSI) values ​​and the motion classification of the key fob are determined to match if they are the same (e.g., if the motion classification of the plurality of channel state information (CSI) values ​​is motion away from the vehicle 12, and the motion classification of the key fob is also motion away from the vehicle 12). If the motion classification of the plurality of channel state information (CSI) values ​​does not match the motion classification of the key fob, the method 100 proceeds to the standby state at block 110. If the motion classification of the plurality of channel state information (CSI) values ​​matches the motion classification of the key fob, the method 100 proceeds to block 128.

[0075] As discussed above with reference to blocks 124 and 126, matching the motion classification of the key fob with the motion classification of multiple channel state information (CSI) values ​​provides an additional verification / authentication step for activating the voice assistant. In some embodiments, blocks 124 and 126 may be bypassed, and the method 100 may proceed directly from block 122 to block 128. In an exemplary embodiment, the owner / operator of the vehicle 12 may choose whether to bypass blocks 124 and 126. In another exemplary embodiment, the execution of blocks 124 and 126 is dependent on the location of the vehicle 12 determined using a global satellite navigation system (GNSS) 26.

[0076] At box 128, the controller 14 performs a multi-factor authentication process. Within the scope of the present disclosure, a multi-factor authentication process is a security mechanism that requires a person to provide two or more different forms of identification (i.e., "factors"). In a non-limiting example, the first factor is considered to be the successful completion of the preceding steps of method 100 (i.e., identification of low-fidelity motion markers, identification of high-fidelity motion markers, positioning of the key fob, and motion classification of the key fob and comparison of the motion classification of the key fob with the motion classification of multiple channel state information (CSI) values). The second factor includes, for example: fingerprint recognition, voice recognition, and / or facial recognition. If the multi-factor authentication process is not successfully performed, the method 100 continues to the standby state at box 110. If the multi-factor authentication process (i.e., successful acquisition and authentication of the second factor) is successfully performed, the method 100 proceeds to box 130.

[0077] At box 130, the controller 14 executes the voice command received using the microphone 24. In an exemplary embodiment, to execute the voice command, the controller 14 modifies the operation of one or more systems and / or components of the vehicle 12. In a non-limiting example, the voice command includes an instruction to open the trunk of the vehicle 12. Therefore, to execute the voice command, the controller 14 activates the trunk latch actuator and the trunk lift actuator of the vehicle 12 to open the trunk of the vehicle 12. In another non-limiting example, the voice command includes an instruction to unlock the vehicle 12. Therefore, to execute the voice command, the controller 14 activates one or more door lock actuators of the vehicle 12 and disables the security system of the vehicle 12. It should be understood that the voice command may include various additional commands, questions, instructions, etc., and without departing from the scope of the present disclosure, the controller 14 may take various additional actions to execute the voice command.

[0078] In an exemplary embodiment, before executing the voice command at box 130, the controller 14 checks whether the voice command is authorized based at least in part on the identity of the person issuing the voice command identified using multi-factor authentication at box 128. In a non-limiting example, specific persons may be authorized to execute a limited set of voice commands. For example: a first exemplary person may be authorized to execute voice commands only for opening and closing the trunk of the vehicle 12. A second exemplary person may be authorized to execute all voice commands, including, for example: a voice command to activate a remote start function of the vehicle 12. After box 130, the method 100 proceeds to the standby state at box 110.

[0079] refer to Figure 5 , a flow chart of a first exemplary embodiment 104a of block 104 is shown. The first exemplary embodiment 104a utilizes an embodiment of the system 10, wherein the first wireless module 28a includes at least one wireless transceiver module 32 configured to send and receive signals on a first frequency band B1, and wherein the second wireless module 28b is identical in structure and function to the first wireless module 28a. The first exemplary embodiment 104a begins at block 502. At block 502, the controller 14 uses the first wireless module 28a to send a plurality of original training signals on a plurality of subcarriers. Within the scope of the present disclosure, the plurality of original training signals are known signals sent for the purpose of channel state information (CSI) value estimation. After block 502, the first exemplary embodiment 104a proceeds to block 504.

[0080] At block 504, the second wireless module 28b receives a plurality of first propagated training signals from the first wireless module 28a. The received training signals are referred to as propagated training signals because environmental characteristics cause the original training signals to change during propagation, as described above. It should be understood that in some embodiments, other devices with wireless capabilities (e.g., a smartphone or other mobile device in the vehicle 12) can perform the functions of the second wireless module 28b. After block 504, the first exemplary embodiment 104a proceeds to block 506.

[0081] At block 506, the controller 14 determines a first deviation between the plurality of original training signals and the plurality of first propagated training signals. In an exemplary embodiment, the first deviation is a difference between the plurality of original training signals and the plurality of first propagated training signals. In a non-limiting example, the first deviation is a one-dimensional vector including deviations corresponding to transmissions on each subcarrier frequency. After block 506, the first exemplary embodiment 104a proceeds to block 508.

[0082] At block 508, the controller 14 determines a plurality of channel state information (CSI) values. In an exemplary embodiment, the plurality of channel state information (CSI) values ​​are determined based at least in part on the first deviations. After block 508, the first exemplary embodiment 104a ends and the method 100 continues as described above.

[0083] refer to Figure 6 , a flow chart of a second exemplary embodiment 104b of block 104 is shown. The second exemplary embodiment 104b utilizes an embodiment of the system 10, wherein the first wireless module 28a includes at least two wireless transceiver modules 32 and is configured to send and receive signals on a first frequency band B1 and a second frequency band B2, and wherein the second wireless module 28b is a signal conversion device for performing signal conversion between the first frequency band B1 and the second frequency band B2. The second exemplary embodiment 104b begins at block 602. At block 602, the controller 14 uses the first wireless transceiver module 32a of the first wireless module 28a on the first frequency band B1 to send multiple original training signals on multiple subcarriers. Within the scope of the present disclosure, the multiple original training signals are known signals sent for the purpose of channel state information (CSI) value estimation. After block 602, the second exemplary embodiment 104b proceeds to block 604.

[0084] At block 604 , the second wireless module 28 b receives the plurality of first propagated training signals using the first antenna 42 a . After block 604 , the second exemplary embodiment 104 b proceeds to block 606 .

[0085] At block 606 , the second wireless module 28 b converts the plurality of first propagated training signals received at block 604 from the first frequency band B1 to the second frequency band B2 using the conversion circuit 44 , as described above. After block 606 , the second exemplary embodiment 104 b proceeds to block 608 .

[0086] At block 608 , the second wireless module 28 b transmits a plurality of first propagation training signals on the second frequency band B2 using the second antenna 42 b. After block 608 , the second exemplary embodiment 104 b proceeds to block 610 .

[0087] At block 610, the first wireless module 28a uses the second wireless transceiver module 32b to receive a plurality of second training signals propagated on the second frequency band B2. As described above, because the environmental characteristics cause the plurality of first training signals to change during propagation, the received training signals are referred to as a plurality of second propagated training signals. After block 610, the second exemplary embodiment 104b proceeds to block 612.

[0088] At block 612, the controller 14 determines a second deviation between the plurality of original training signals and the plurality of second propagated training signals. In an exemplary embodiment, the second deviation is a difference between the plurality of original training signals and the plurality of second propagated training signals. In a non-limiting example, the second deviation is a one-dimensional vector including deviations corresponding to transmissions on each subcarrier frequency. After block 612, the second exemplary embodiment 104b proceeds to block 614.

[0089] At block 614, the controller 14 determines a plurality of channel state information (CSI) values. In an exemplary embodiment, the plurality of channel state information (CSI) values ​​are determined based at least in part on the second deviations. After block 614, the second exemplary embodiment 104b ends and the method 100 continues as described above.

[0090] refer to Figure 7, a flow chart of an exemplary embodiment 700 of block 106 is shown. Exemplary embodiment 700 begins at block 702. At block 702, controller 14 calculates a plurality of channel state information (CSI) value derivatives. In an exemplary embodiment, the plurality of channel state information (CSI) values ​​are divided into a plurality of channel state information (CSI) value subsets, wherein each of the plurality of channel state information (CSI) value subsets corresponds to one of a plurality of subcarriers. Controller 14 calculates a time-value derivative of each of the plurality of channel state information (CSI) value subsets. Thus, each of the plurality of channel state information (CSI) value derivatives corresponds to a change in a channel state information (CSI) value of each of the plurality of subcarriers over time. Thus, the plurality of channel state information (CSI) value derivatives are also referred to as a plurality of dynamic channel state information (CSI) values. After block 702, exemplary embodiment 700 proceeds to block 704.

[0091] At block 704, the controller 14 determines a plurality of channel state information (CSI) value derivative magnitudes. The plurality of channel state information (CSI) value derivative magnitudes are also referred to as a plurality of dynamic channel state information (CSI) value magnitudes. In an exemplary embodiment, each of the plurality of channel state information (CSI) value derivatives includes a magnitude component and a phase component. To calculate the plurality of channel state information (CSI) value derivative magnitudes, the controller 14 obtains the magnitude component of each of the plurality of channel state information (CSI) value derivatives and discards the phase component. After block 704, the exemplary embodiment 700 proceeds to block 706.

[0092] At block 706, the controller 14 calculates a norm of the plurality of channel state information (CSI) value derivative magnitudes. In an exemplary embodiment, to calculate the norm, the controller 14 calculates a norm of a one-dimensional vector including the plurality of channel state information (CSI) value derivative magnitudes. In a non-limiting example, the norm is calculated as the square root of the sum of the squares of each of the plurality of channel state information (CSI) value derivative magnitudes:

[0093] Formula (1):

[0094]

[0095] Where p is the norm, C i is the i-th of a plurality of channel state information (CSI) value derivative magnitudes, and N is the total number of a plurality of channel state information (CSI) value derivative magnitudes. In an exemplary embodiment, the norm is saved in the medium 20 of the controller 14 along with previous and subsequent norms for further processing, as will be discussed in more detail below. After block 706, the exemplary embodiment 700 proceeds to block 708.

[0096] At block 708, the controller 14 calculates a time average norm signal. It should be understood that the method 100 and the exemplary embodiment 700 can be repeatedly performed so that multiple previous norms calculated at block 706 are available in the medium 20. In an exemplary embodiment, the time average norm signal is a moving average of the previous norms calculated at block 706 and stored in the medium 20. In another exemplary embodiment, the time average norm signal is a moving average of the previous norms calculated at block 706 and stored in the medium 20. It should be understood that any statistical method for smoothing short-term fluctuations in time series data is within the scope of the present disclosure. After block 708, the exemplary embodiment 700 proceeds to block 710.

[0097] At block 710, controller 14 compares the time-averaged norm signal determined at block 708 to a predetermined time-averaged norm signal threshold. In the exemplary embodiment, the predetermined time-averaged norm signal threshold is determined experimentally and may be adjusted to adjust the sensitivity of system 10. If the time-averaged norm signal remains greater than or equal to the predetermined time-averaged norm signal threshold for at least a predetermined period of time = (e.g., 2 seconds), exemplary embodiment 700 proceeds to block 712. If the time-averaged norm signal is less than or equal to the predetermined time-averaged norm signal threshold for at least a predetermined period of time, exemplary embodiment 700 proceeds to block 714.

[0098] At block 712, a low-fidelity motion flag is identified in the plurality of channel state information (CSI) values. Following block 712, exemplary embodiment 700 ends and method 100 continues as described above.

[0099] At block 714, no low-fidelity motion flag is identified in the plurality of channel state information (CSI) values. Following block 714, exemplary embodiment 700 ends and method 100 continues as described above.

[0100] refer to Figure 8 , a flow chart of an exemplary embodiment 800 of block 120 is shown. The exemplary embodiment 800 begins at block 802. At block 802, the controller 14 preprocesses a plurality of channel state information (CSI) values ​​to generate a plurality of preprocessed channel state information (CSI) values. In an exemplary embodiment, preprocessing the plurality of channel state information (CSI) values ​​includes, for example, removing abnormal data from the plurality of channel state information (CSI) values, filtering noise from the plurality of channel state information (CSI) values, normalizing the plurality of channel state information (CSI) values, performing Fourier transform on the plurality of channel state information (CSI) values, etc. After block 802, the exemplary embodiment 800 proceeds to block 804.

[0101] At block 804, the controller 14 determines a motion classification of the plurality of channel state information (CSI) values. Within the scope of the present disclosure, the motion classification includes, for example, motion toward the vehicle 12, motion away from the vehicle 12, gesture motion toward the vehicle 12, gesture motion away from the vehicle 12, etc. In an exemplary embodiment, to determine the motion classification of the plurality of channel state information (CSI) values, the controller 14 uses a machine learning algorithm trained to classify motion in the plurality of channel state information (CSI) values.

[0102] In a non-limiting example, a machine learning algorithm includes multiple layers: including an input layer and an output layer, and one or more hidden layers. The input layer receives a plurality of pre-processed channel state information (CSI) values ​​as input. The input is then passed to the hidden layer. Each hidden layer applies a transformation (e.g., a nonlinear transformation) to the data and passes the result to the next hidden layer until the last hidden layer. The output layer produces a motion classification of the plurality of channel state information (CSI) values.

[0103] To train the machine learning algorithm, an input dataset and its corresponding sports classification are used. The algorithm is trained by adjusting the internal weights between nodes in each hidden layer to minimize the prediction error. During the training process, optimization techniques (e.g., gradient descent) are used to adjust the internal weights to reduce the prediction error. The training process is repeated for the entire dataset until the prediction error is minimized, and the resulting trained model is then used to classify new input data.

[0104] After sufficient training of the machine learning algorithm, the algorithm is able to accurately and precisely determine the motion classification of multiple channel state information (CSI) values ​​based on multiple pre-processed channel state information (CSI) values. By adjusting the weights between the nodes in each hidden layer during training, the algorithm "learns" to identify patterns in the data that indicate different types of motion (e.g., motion toward the vehicle 12, motion away from the vehicle 12, gesture motion toward the vehicle 12, gesture motion away from the vehicle 12, etc.). After block 804, the exemplary embodiment 800 proceeds to block 806.

[0105] At block 806, if the motion classification of the plurality of channel state information (CSI) values ​​determined at block 804 is equal to a preselected motion classification, then exemplary embodiment 800 proceeds to block 808. Within the scope of the present disclosure, the preselected motion classification may include any motion classification, such as motion toward vehicle 12. If the motion classification of the plurality of channel state information (CSI) values ​​determined at block 804 is not motion toward vehicle 12, then exemplary embodiment 800 proceeds to block 810.

[0106] At block 808, a high-fidelity motion flag is identified among the plurality of channel state information (CSI) values. Following block 808, exemplary embodiment 800 ends and method 100 continues as described above.

[0107] At block 810, no high-fidelity motion flag is identified in the plurality of channel state information (CSI) values. Following block 810, exemplary embodiment 800 ends and method 100 continues as described above.

[0108] The system 10 and method 100 of the present disclosure have multiple advantages. Using the system 10 and method 100, the safety and performance of the voice assistant function of the vehicle 12 are improved by mitigating unauthorized and / or unintentional activation of the voice assistant function. In addition, the parameters of the system 10 and / or method 100 can be adjusted. For example: the predetermined time average norm signal threshold can be adjusted to adjust the sensitivity of the system 10 based on the environmental background. In an exemplary embodiment, the global satellite navigation system (GNSS) 26 is used to determine the location of the vehicle 12, and the controller 14 adjusts the predetermined time average norm signal threshold based on the location of the vehicle 12. In an exemplary embodiment, if the vehicle 12 is in a location where unauthorized use of the voice assistant function is more likely, such as: in a public parking lot, the sensitivity of the system 10 is increased.

[0109] The description of the present disclosure is merely exemplary in nature, and variations that do not depart from the gist of the present disclosure are intended to fall within the scope of the present disclosure. These variations should not be regarded as departing from the spirit and scope of the present disclosure.

Claims

1. A system for activating a voice assistant of a vehicle, the system comprising: microphone; A first wireless module; A second wireless module; as well as a controller in electrical communication with the microphone, the first wireless module, and the second wireless module, wherein the controller is programmed to: Using the first wireless module to send multiple original training signals on multiple subcarriers; Using the second wireless module to receive a plurality of propagation training signals; determining deviations between the plurality of original training signals and the plurality of propagated training signals; identifying a motion signature based at least in part on the deviation; and A voice assistant of the vehicle is activated based at least in part on the motion signature to receive a voice command using the microphone.

2. The system according to claim 1, wherein: In order to identify the motion signature, the controller is also programmed to: determining a plurality of channel state information (CSI) values ​​based at least in part on deviations between the plurality of original training signals and the plurality of propagated training signals; as well as The motion marker is identified based at least in part on the plurality of channel state information (CSI) values, wherein the motion marker comprises at least one of: a low-fidelity motion marker and a high-fidelity motion marker.

3. The system according to claim 2, wherein: In order to identify the motion signature, the controller is also programmed to: calculating a plurality of channel state information (CSI) value derivatives, wherein at least one of the plurality of channel state information (CSI) value derivatives corresponds to each of a plurality of subcarriers; calculating a plurality of channel state information (CSI) value derivative values, wherein each of the plurality of channel state information (CSI) value derivative values ​​is a value of one of the plurality of channel state information (CSI) value derivatives; Calculating a norm of the plurality of channel state information (CSI) value derivative values; calculating a time-averaged norm signal based at least in part on the norm; continuously comparing the time-averaged norm signal to a predetermined time-averaged norm signal threshold; and The low-fidelity motion marker is identified in response to determining that the time-averaged norm signal is greater than or equal to the predetermined time-averaged norm signal threshold.

4. The system according to claim 2, wherein: In order to identify motion markers in the vehicle's surroundings, the controller is further programmed to: determining a motion classification of the plurality of channel state information (CSI) values ​​using a machine learning algorithm, wherein the machine learning algorithm is configured to receive the plurality of channel state information (CSI) values ​​as input and provide a motion classification of the plurality of channel state information (CSI) values ​​as output, and wherein the motion classification of the plurality of channel state information (CSI) values ​​comprises at least one of: motion towards a vehicle and motion away from a vehicle; as well as The high-fidelity motion signature is identified in response to determining that the motion classification of the plurality of channel state information (CSI) values ​​is the motion toward the vehicle.

5. The system according to claim 4, wherein: To activate a voice assistant of the vehicle to receive a voice command using the microphone based at least in part on the motion signature, the controller is further programmed to: In response to determining that the motion signature includes the low-fidelity motion signature, activating the microphone to receive a voice assistant keyword; determining a position of a key fob relative to the vehicle in response to detecting the voice assistant keyword using the microphone; performing a multi-factor authentication process in response to determining that the distance between the key fob and the vehicle is less than or equal to a predetermined key fob distance and the motion signature further includes the high-fidelity motion signature; and The voice command received using the microphone is executed in response to determining that the multi-factor authentication process is successfully performed.

6. The system according to claim 5, wherein: To activate a voice assistant of the vehicle to receive a voice command using the microphone based at least in part on the motion signature, the controller is further programmed to: determining a motion classification of the key fob, wherein the motion classification of the key fob comprises at least one of: motion toward a vehicle and motion away from a vehicle; performing the multi-factor authentication process in response to determining that the distance between the key fob and the vehicle is less than or equal to the predetermined key fob distance, the motion signature further includes the high-fidelity motion signature, and the motion classifications of the plurality of channel state information (CSI) values ​​match the motion classifications of the key fob; and The voice command received using the microphone is executed in response to determining that the multi-factor authentication process is successfully performed.

7. The system according to claim 1, wherein: The first wireless module is a first digital wireless local area network (WLAN) transceiver system configured to implement a wireless communication protocol, and wherein the second wireless module is at least one of: a second digital wireless local area network (WLAN) transceiver system configured to implement a wireless communication protocol; and a signal conversion device configured to convert signals between at least two frequency bands.

8. The system according to claim 7, wherein: The signal conversion device also includes: power supply; at least two antennas; and a conversion circuit in electrical communication with the power supply and the at least two antennas, the conversion circuit comprising: a mixer in electrical communication with the at least two antennas; and An oscillator is in electrical communication with the mixer.

9. The system according to claim 8, wherein: The conversion circuit also includes: a first amplifier in electrical communication with a first of the at least two antennas and the mixer; and A second amplifier is in electrical communication with the mixer and a second one of the at least two antennas.

10. The system according to claim 9, wherein: The conversion circuit also includes: a first bandpass filter in electrical communication with the first amplifier and the mixer; and A second bandpass filter is in electrical communication with the mixer and the second amplifier.

Images