Method and system for wireless data transmission

Abstract

A method for wireless data transmission and reconstruction includes receiving data from a vehicle, extracting key frames from the data, and encoding the key frames of the data into a potential space using an encoder of a variable autoencoder to generate compressed data. The method also includes transmitting the compressed data from the vehicle to a remote server. The method includes generating data points from the compressed data using a decoder of the variable autoencoder, wherein the data points characterize data received from the vehicle.

Description

Technical Field

[0001] The present disclosure relates to a system and method for wireless data transmission. Background Art

[0002] This introduction generally presents the background of the present disclosure. The work of the presently designated inventors, to the extent it is described in this introduction and to the extent that it may not qualify as prior art at the time of filing, is neither expressly nor impliedly admitted as prior art to the present disclosure.

[0003] The robustness of wireless communication applications depends on the quality and bandwidth of the network environment. Unstable and highly interfered network environments may lead to data loss and transmission errors. Wireless data transmission that requires high bandwidth may lead to large delays and data inconsistency problems. Therefore, it is necessary to develop a method and system for wireless data transmission that can handle high bandwidth transmission while preventing or at least minimizing delays and data inconsistency problems. Summary of the invention

[0004] The present disclosure describes a method for wireless data transmission and reconstruction. The method includes receiving data from a vehicle, extracting key frames from the data, and encoding the key frames of the data into a latent space using an encoder of a variable autoencoder to generate compressed data. The method also includes transmitting the compressed data from the vehicle to a remote server. The method includes generating data points from the compressed data using a decoder of the variable autoencoder, wherein the data points represent the data received from the vehicle. The method described in this paragraph improves wireless data transmission technology by minimizing the bandwidth required to transmit data from the vehicle to the remote server, thereby minimizing latency issues.

[0005] In some aspects of the present disclosure, the data from the vehicle includes sensor data collected by sensors of the vehicle. The keyframe serves as an input to an encoder of a variable autoencoder. The method may also include extracting the keyframe from the sensor data collected by the sensors of the vehicle. The remote server may sample the compressed data at equal time intervals. The discriminator discriminates between data points and sensor data generated by a decoder of the variable autoencoder. The method may include compensating for delays in data points generated by a decoder of the variable autoencoder. To this end, the method includes uniformly interpolating and extrapolating samples in a latent space, which helps minimize the effects of unstable delays. The encoder may be configured as a first neural network that maps sensor data to a latent space. The sensor data is in an input space. The decoder may be configured as a second neural network that maps compressed data to an input space.

[0006] The present disclosure also describes a system for wireless data transmission. The system includes a remote server in communication with a vehicle. The remote server includes a processor and a tangible, non-transitory machine-readable medium. The processor of the remote server is programmed to perform the above method.

[0007] The present disclosure also describes a tangible, non-transitory machine-readable medium including machine-readable instructions, which, when executed by a processor, cause the processor to perform the above method.

[0008] Further areas of applicability of the present disclosure will become apparent from the detailed description provided hereinafter.It should be understood that the detailed description and specific examples are intended for illustration purposes only and are not intended to limit the scope of the present disclosure.

[0009] The above features and advantages and other features and advantages of the presently disclosed systems and methods are apparent from the detailed description, including the claims and exemplary embodiments, when taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The present disclosure will be more fully understood from the detailed description and accompanying drawings, in which:

[0011] Figure 1 A schematic diagram of a system for wireless data transmission.

[0012] Figure 2 is a flow chart of a method for wireless data transmission. DETAILED DESCRIPTION

[0013] Reference will now be made in detail to several examples of the present disclosure as illustrated in the accompanying drawings. Whenever possible, the same or similar reference numerals are used in the drawings and description to refer to the same or similar parts or steps.

[0014] refer to Figure 1 , a system 100 for wireless data transmission includes one or more vehicles 10 and one or more remote servers 102 in wireless communication with the vehicles 10. As non-limiting examples, the remote server 102 may be a cloud server or an edge server. Each of the vehicles 10 generally includes a body 12 and a plurality of wheels 14 coupled to the body 12. The vehicle 10 may be an autonomous vehicle. In the described embodiment, the vehicle 10 is depicted as a sedan in the illustrated embodiment, but it should be understood that other vehicles may also be used, including trucks, coupes, sport utility vehicles (SUVs), recreational vehicles (RVs), etc.

[0015] The vehicle 10 also includes one or more sensors 24 coupled to the vehicle body 12. The sensors 24 sense observable conditions of the external environment and / or the internal environment of the vehicle 10. As non-limiting examples, the sensors 24 may include one or more cameras, one or more light detection and ranging (LIDAR) sensors, one or more proximity sensors, one or more cameras, one or more ultrasonic sensors, one or more thermal imaging sensors, and / or other sensors. Each sensor 24 is configured to generate a signal indicating a sensed observable condition (i.e., sensor data) of the external environment and / or the internal environment of the vehicle 10. The signal represents the sensor data collected by the sensor 24.

[0016] The vehicle 10 includes a vehicle controller 34 that communicates with the sensor 24. The vehicle controller 34 includes at least one vehicle processor 44 and a vehicle non-transitory computer-readable storage device or medium 46. The vehicle processor 44 can be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor in multiple processors associated with the vehicle controller 34, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally a device for executing instructions. The vehicle readable storage device or medium 46 can include volatile and non-volatile storage devices such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables when the vehicle processor 44 is powered off. The vehicle computer readable storage device or medium 46 may be implemented using a variety of memory devices, such as a programmable read only memory (PROM), an electrical PROM (EPROM), an electrically erasable PROM (EEPROM), flash memory, or other electrical, magnetic, optical, or combination memory devices capable of storing data, some of which represents executable instructions for use by the vehicle controller 34 in controlling the vehicle 10. The vehicle controller 34 may be programmed to perform the method 200 (described in detail below). Figure 2 ) at least a portion of.

[0017] The instructions may include one or more separate programs, each of which includes an ordered list of executable instructions for implementing logical functions. When the instructions are executed by the vehicle processor 44, the vehicle processor 44 receives and processes signals from sensors, executes logic, calculations, methods and / or algorithms for automatically controlling components of the vehicle 10, and generates control signals based on the logic, calculations, methods and / or algorithms to automatically control components of the vehicle 10. Although Figure 11 , a single vehicle controller 34 is shown, but embodiments of the vehicle 10 may include multiple vehicle controllers 34 that communicate via a suitable communication medium or combination of communication mediums and cooperate to process sensor signals, execute logic, calculations, methods and / or algorithms, and generate control signals to automatically control features of the vehicle 10. The vehicle controller 34 is part of the system 100 for wireless data transmission.

[0018] The vehicle 10 also includes one or more vehicle transceivers 26 that communicate with the vehicle controller 34 to allow the vehicle 10 to wirelessly transfer data to and from other entities (e.g., a remote server 102). As non-limiting examples, the vehicle transceiver 26 can send and / or receive data from other vehicles ("V2V" communication), infrastructure ("V2I" communication), remote systems at a remote call center (e.g., General Motors' ON-STAR), and / or personal electronic devices (e.g., mobile phones). In some embodiments, the vehicle transceiver 26 is part of a wireless communication system that is configured to communicate via a wireless local area network (WLAN) using the IEEE 802.11 standard or by using cellular data communications. However, additional or alternative communication methods, such as dedicated short-range communication (DSRC) channels, are also considered within the scope of the present disclosure. A DSRC channel refers to a one-way or two-way short-range to medium-range wireless communication channel designed specifically for automotive use and a set of corresponding protocols and standards.

[0019] As described above, the vehicle 10 communicates wirelessly with the remote server 102. To this end, the remote server 102 includes one or more server transceivers 126. As a non-limiting example, the server transceiver 126 can send and / or receive data from other vehicles ("V2V" communication), infrastructure ("V2I" communication), and / or personal electronic devices (e.g., mobile phones). In some embodiments, the server transceiver 126 is part of a wireless communication system that is configured to communicate via a wireless local area network (WLAN) using the IEEE 802.11 standard or by using cellular data communications. However, additional or alternative communication methods, such as dedicated short-range communication (DSRC) channels, are also considered to be within the scope of the present disclosure. A DSRC channel refers to a one-way or two-way short-range to medium-range wireless communication channel designed specifically for automotive use and a set of corresponding protocols and standards.

[0020] The remote server 102 also includes a server controller 134 that communicates with the server transceiver 126. The server controller 134 includes at least one server processor 144 and a server non-transitory computer-readable storage device or medium 146. The server processor 144 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 server controller 134, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally a device for executing instructions. The server readable storage device or medium 146 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 server processor 144 is powered off. The server computer readable storage device or medium 146 may be implemented using a variety of storage devices, such as a programmable read-only memory (PROM), an electrical PROM (EPROM), an electrically erasable PROM (EEPROM), flash memory, or other electrical, magnetic, optical, or combination memory devices capable of storing data, some of which represents executable instructions, for use by the server controller 134 in controlling the remote server 102. The server controller 134 may be programmed to perform the method 200 described in detail below ( Figure 2 ). Although Figure 1 1 , a single server controller 134 is shown, but embodiments of the remote server 102 may include multiple server controllers 134 that communicate via a suitable communication medium or combination of communication mediums and collaborate to process sensor signals, perform logic, calculations, methods and / or algorithms, and generate control signals to automatically control features of the remote server 102. The server controller 134 is part of the system 100 for wireless data transmission.

[0021] Figure 2 1 is a flow chart of a method 200 for wireless data transmission. The method 200 begins at box 202. At box 202, the sensor 24 of the vehicle 10 collects sensor data. As described above, the sensor 24 senses observable conditions of the external environment and / or the internal environment of the vehicle 10. Therefore, the sensor data collected by the sensor 24 indicates observable conditions of the external environment and / or the internal environment of the vehicle 10. The vehicle 10 may also collect other types of data, such as location data collected through a global positioning system (GPS). The method 200 then proceeds to box 204.

[0022] At block 204, the vehicle controller 34 extracts key frames from the data collected by the vehicle 10 (e.g., sensor data collected by the sensors 24 of the vehicle 10) to minimize the data transmission load and thereby generate key frame data. The term "key frame" refers to a frame that defines the start and end points of a smooth transition. The method 200 then continues to block 206.

[0023] At box 206, the vehicle controller 34 uses the encoder of the variable autoencoder to encode the key frame of the data (e.g., sensor data) collected from the vehicle 10 into the latent space. Therefore, the key frame is used as the input of the encoder. Encoding the key frame generates compressed data. The sensor data is in the input space. The latent space is a low-dimensional space relative to the input space to minimize the burden of data transmission. The encoder of the variable autoencoder is a first neural network that maps the sensor data (or other data from the vehicle 10) to the latent space. The encoder of the variable autoencoder has been previously trained in box 205.

[0024] Box 205 represents the incremental encoder training process. The encoder of the variable autoencoder iterates the update step based on a batch of newly captured sensor data. The trained encoder characterizes the features of the sensor data (such as vehicle characteristics, important events, driving behavior and surrounding traffic conditions).

[0025] After frame 206, method 200 continues to frame 208. At frame 208, the compressed data (as encoded by the encoder of the variable autoencoder) is transmitted from vehicle 10 to remote server 102 via one or more networks. Vehicle transceiver 26 and server transceiver 126 are used to wirelessly transmit data from vehicle 10 to remote server 102. Method 200 then continues to frame 210.

[0026] At block 210, the remote server 102 samples the compressed data at equal time intervals in the latent space according to the timestamp to compensate for the time delay. The time interval may be less than the data receiving frequency to compensate for the time delay. The method 200 may interpolate the sampled compressed data to account for missing data. In addition, the method 200 may use extrapolation to predict future data. The method 200 then proceeds to block 212.

[0027] At box 212, the remote controller 134 uses the pre-trained decoder of the variable autoencoder to reconstruct the sensor data (or other data) from the vehicle 10 based on the compressed data (in the latent space) generated by the encoder. In other words, the decoder of the variable autoencoder generates data points representing the sensor data (or other data) from the vehicle 10. The decoder is a second neural network that maps the compressed data to the input space. At box 211, the decoder can be trained using the sensor data (or other data) from the vehicle 10 and the decoder optimizer. Then, at box 213, the decoder of the variable autoencoder is trained using the sensor data (or other data) from the vehicle 10. At box 211, the parameters of the decoder are updated to generate more accurate frame data for testing against the discriminator. At box 213, the discriminator discriminates between the data points generated by the decoder and the sensor data (or other data) from the vehicle 10. Then the method 200 continues to box 214.

[0028] At box 214, the remote server 102 uses the decoder as described above to reconstruct the sensor data (or other data) from the vehicle 10. Next, the method 200 continues to box 216. At box 216, the remote server 102 uses a time compensation model to compensate for the delay between different frame data due to unstable network conditions. Therefore, the remote server 102 can regenerate fully time-continuous sensor data with the help of a variable autoencoder. The regenerated sensor data may be useful in downstream applications such as sensor fusion, target recognition, and decision making.

[0029] The drawings are in simplified form and are not drawn to exact scale. Directional terms such as top, bottom, left, right, upward, above, above, below, below, rear, and front may be used with respect to the drawings for convenience and clarity only. These directional terms and similar directional terms should not be construed as limiting the scope of the present disclosure in any way.

[0030] Embodiments of the present disclosure are described herein. However, it should be understood that the disclosed embodiments are merely examples, and other embodiments may take various alternative forms. The drawings are not necessarily drawn to scale; certain features may be enlarged or minimized to show the details of a particular component. Therefore, the specific structural and functional details disclosed herein should not be interpreted as restrictive, but only as a representative basis for teaching those skilled in the art to adopt the currently disclosed systems and methods in various ways. As will be understood by those of ordinary skill in the art, the various features shown and described with reference to any of the accompanying drawings may be combined with the features shown in one or more other figures to produce embodiments that are not explicitly shown or described. The combination of the features shown provides a representative embodiment of a typical application. However, for a particular application or implementation, various combinations and modifications of features consistent with the teachings of the present disclosure may be desirable.

[0031] Embodiments of the present disclosure may be described herein in terms of functional and / or logical block components and various processing steps. It should be understood that such block components may be implemented by multiple hardware, software, and / or firmware components configured to perform specified functions. For example, an embodiment of the present disclosure may employ various integrated circuit components, such as memory elements, digital signal processing elements, logic elements, lookup tables, etc., which may perform various functions under the control of one or more microprocessors or other control devices. In addition, it should be understood by those skilled in the art that embodiments of the present disclosure may be practiced in conjunction with multiple systems, and the systems described herein are merely exemplary embodiments of the present disclosure.

[0032] For the sake of brevity, technologies related to signal processing, data fusion, signaling, control, and other functional aspects of the system (and the various operating components of the system) may not be described in detail herein. In addition, the connecting lines shown in the various figures contained herein are intended to represent example functional relationships and / or physical couplings between the various elements. It should be noted that alternative or additional functional relationships or physical connections may exist in the embodiments of the present disclosure.

[0033] This description is merely illustrative in nature and is in no way intended to limit the present disclosure, its application or use. The broad teachings of the present disclosure can be implemented in many forms. Therefore, although the present disclosure includes specific examples, the true scope of the present disclosure should not be so limited, as other modifications will become apparent upon studying the drawings, the specification and the appended claims.

Claims

1. A method for wireless data transmission and reconstruction, comprising: receiving data from the vehicle; extracting key frames from the data; encoding the keyframes of the data into a latent space by an encoder of a variable autoencoder to generate compressed data; transmitting the compressed data from the vehicle to a remote server; as well as Data points are generated from the compressed data by a decoder of the variable autoencoder, wherein the data points represent the data received from the vehicle.

2. The method according to claim 1, wherein: The data from the vehicle includes sensor data collected by sensors of the vehicle.

3. The method according to claim 2, wherein: The keyframes serve as input to the encoder of the variable autoencoder, and the method includes extracting the keyframes from the sensor data collected by the sensors of the vehicle.

4. The method according to claim 3, wherein: The remote server samples the compressed data at equal time intervals.

5. The method according to claim 4 further comprises updating a plurality of parameters of the decoder of the variable autoencoder by a discriminator.

6. The method of claim 5, further comprising compensating for delays in the data points generated by the decoder of the variable autoencoder.

7. The method according to claim 6, wherein: The encoder is a first neural network that maps the sensor data into the latent space, the sensor data is in an input space, and the decoder is a second neural network that maps the compressed data into the input space.

8. A tangible, non-transitory machine-readable medium comprising machine-readable instructions that, when executed by a processor, cause the processor to: receiving sensor data collected by vehicle sensors; encoding the sensor data into a latent space by an encoder of a variational autoencoder to generate compressed data; transmitting the compressed data from the vehicle to a remote server; as well as Data points are generated from the compressed data by a decoder of the variable autoencoder, wherein the data points represent the sensor data collected by the sensor of the vehicle.

9. The tangible, non-transitory machine-readable medium of claim 8, wherein: The tangible, non-transitory machine-readable medium also includes machine-readable instructions that, when executed by the processor, cause the processor to extract key frames from the sensor data to generate key frame data.

10. The tangible, non-transitory machine-readable medium of claim 9, wherein: The key frames serve as input to the encoder of the variable autoencoder.

Images