Intelligent vehicle control device, system and control method

Abstract

The application provides a kind of intelligent vehicle control device, system and control method, the device includes image processing unit, wireless communication unit and fusion processing unit, data interaction is carried out between each unit through system bus, and image processing unit and fusion processing unit are connected with vehicle bus through independent bus interface;Image processing unit is used to obtain, process the data collected by intelligent sensor, and carries out data interaction with fusion processing unit;Wireless communication unit is used to realize the wireless communication between device and external equipment, and the information obtained is uploaded to fusion processing unit through system bus;Fusion processing unit is used to fuse the data obtained by image processing unit, wireless communication unit data and vehicle data to obtain vehicle control instruction.The application has good expansibility and flexibility, and the reliability and safety of the system are improved by realizing data interaction through system bus.

Description

Technical Field

[0001] This invention relates to the fields of intelligent driving and autonomous driving technology, specifically to an intelligent vehicle control device, system, and control method. Background Technology

[0002] With global economic development and technological advancements, the mining industry is undergoing a profound transformation, with automation and intelligentization becoming key driving forces. Specialized vehicles such as electric-wheeled mining trucks and wide-body mining trucks are increasingly used in mining transportation. These vehicles typically operate in extremely harsh environments, with complex terrain and variable weather conditions. Coupled with the need for long-term continuous operation, this places extremely high demands on vehicle reliability and safety. To further improve mining transportation efficiency, reduce labor costs, and minimize safety hazards caused by human error, achieving intelligent or unmanned driving of specialized vehicles has become an inevitable trend in the industry.

[0003] However, existing unmanned driving control systems have revealed some shortcomings when facing the unique working conditions of mines. First, due to the complexity of the mining environment, traditional unmanned driving control devices alone cannot meet the system's requirements for scalability, safety, and reliability. Second, the special nature of the mining environment limits the ability to rely solely on a single vehicle for environmental perception, especially in obstacle detection, where this approach may not guarantee the overall safety of the unmanned driving system. Furthermore, the need for multi-vehicle collaborative operation is increasingly prominent, requiring vehicles to possess efficient information exchange capabilities to enable effective coordination and control among unmanned vehicles, thereby ensuring the safe operation of the entire system.

[0004] In existing technologies, the design of processing units and external sensor interfaces is relatively fixed, making it difficult to adapt to the needs of different types of mining vehicles, resulting in poor system scalability and flexibility. More importantly, current systems struggle to achieve effective redundancy design, directly impacting overall system reliability. Furthermore, obstacle recognition based on data from a single type of sensor is not ideal, easily leading to recognition errors and consequently affecting the safety performance of autonomous vehicles. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an intelligent vehicle control device, system and control method with high scalability, flexibility and reliability to meet the intelligent or unmanned driving needs of special vehicles in mining environments.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0007] An intelligent vehicle control device includes a GPU image processing unit, a WLU wireless communication unit, and an FPU fusion processing unit. These units interact via a system bus. The GPU image processing unit and the FPU fusion processing unit are connected to the vehicle bus via independent bus interfaces. The GPU image processing unit acquires and processes data collected by intelligent sensors and interacts with the FPU fusion processing unit. The WLU wireless communication unit enables wireless communication between the device and external devices and uploads the acquired information to the FPU fusion processing unit via the system bus. The FPU fusion processing unit fuses the acquired data from the image processing unit, the wireless communication unit, and the vehicle data to obtain vehicle control commands.

[0008] As a further improvement to the method of the present invention: the GPU image processing unit includes an image computing and processing module and a first monitoring module. The image processing module includes a camera interface for connecting to an external camera, an Ethernet interface for connecting to other vehicle-mounted devices, and a CAN interface for connecting to the vehicle bus. The first monitoring module is used to monitor the operating environment and status of the image computing and processing module and provides a fault protection mechanism.

[0009] As a further improvement to the method of the present invention: the FPU fusion processing unit includes: a fusion computing processing module, a second monitoring module, a data interaction module, and a bus expansion module. The fusion computing processing module includes an Ethernet interface for connecting with other vehicle-mounted devices and sensors. The data interaction module is used to exchange intermediate and final results of data processing between the fusion computing processing module and the image computing processing module. The bus expansion module is provided with an interface for receiving vehicle status information and sharing the received information to the fusion computing processing module through the data interaction module. The second monitoring module is used to supervise the operating environment and status of the fusion computing processing module and provide a fault protection mechanism.

[0010] As a further improvement to the method of the present invention: the FPU fusion processing unit includes multiple fusion processing sub-units, and the fusion processing sub-units synchronize their states through the system bus and the vehicle CAN bus. When the state information obtained by the system bus and the vehicle CAN bus is inconsistent, the result synchronized by the system bus is selected first.

[0011] As a further improvement to the method of the present invention: the plurality of fusion processing subunits are configured as master control devices and slave control devices according to preset device addresses, wherein the master control device has a higher priority than the slave control device. The master control device performs bidirectional data interaction with the vehicle drive-by-wire chassis, and the slave control device listens to the data of the vehicle bus of the vehicle drive-by-wire chassis. The plurality of fusion processing subunits perform self-tests periodically and exchange their self-test results and current status through the system bus and the vehicle CAN bus. When the master control device fails to complete the status interaction on time or the self-test is abnormal, the slave control device automatically upgrades to the master control device and takes over the control of the vehicle.

[0012] As a further improvement to the method of the present invention: the WLU wireless communication unit includes multiple wireless communication sub-units. Each wireless communication sub-unit establishes an independent communication link with the ground control equipment or other wireless equipment to receive wireless communication data. After copying the received wireless communication data, it sends it to each fusion processing sub-unit through a designated channel. Each fusion processing sub-unit selectively processes one copy of the communication data.

[0013] The present invention further provides an intelligent vehicle control system, comprising:

[0014] Intelligent vehicle control device;

[0015] Multiple sensing sensors are used to collect data on the vehicle's surrounding environment and are connected to the GPU image processing unit and FPU fusion processing unit through the corresponding interfaces of the intelligent vehicle control device.

[0016] Satellite navigation system signal receiving device, used to provide vehicle positioning information;

[0017] The ground server interacts with the WLU wireless communication unit of the intelligent vehicle control device via wireless communication to exchange vehicle operation management and safety monitoring data.

[0018] The drive-by-wire chassis, including the ECU (Electronic Control Unit) / steering controller, is connected to the intelligent vehicle control device via a CAN bus.

[0019] The present invention further provides an intelligent vehicle control method, comprising:

[0020] Step S1: The WLU wireless communication unit receives the generated vehicle route information and shares the received vehicle route information to the fusion computing processing module through the data interaction module of the FPU fusion processing unit;

[0021] Step S2: The GPU image processing unit acquires sensor data and shares the acquired sensor data with the fusion computing processing module through the data interaction module of the FPU fusion processing unit;

[0022] Step S3: The data interaction module of the FPU fusion processing unit shares the data obtained from the vehicle drive-by-wire chassis CAN bus to the fusion computing processing module.

[0023] Step S4: The fusion computing and processing module of the FPU fusion processing unit generates control commands based on the vehicle running route information, sensor data, and data information on the vehicle drive-by-wire chassis CAN bus. The commands are then sent to the vehicle drive-by-wire chassis CAN bus through the data interaction module and the bus expansion module, thereby realizing the control of vehicle operation.

[0024] As a further improvement to the method of the present invention: the FPU fusion processing unit includes multiple fusion processing sub-units. The multiple fusion processing sub-units simultaneously synchronize their states and interact with processed data through two different communication methods, the system bus and the vehicle CAN bus, so as to realize hot standby redundancy of the autonomous vehicle control function.

[0025] As a further improvement to the method of the present invention: when the status information obtained by the system bus and the vehicle CAN bus is inconsistent, the result of the system bus synchronization shall be given priority.

[0026] Compared with the prior art, the advantages of the present invention are as follows:

[0027] 1. The intelligent vehicle control device of the present invention includes a GPU image processing unit, a WLU wireless communication unit, and an FPU fusion processing unit. These units interact with each other via a system bus. Simultaneously, the GPU image processing unit and the FPU fusion processing unit are connected to the vehicle bus through independent bus interfaces. The FPU fusion processing unit processes the acquired data from the image processing unit, the wireless communication unit, and the vehicle data, thereby generating more accurate and comprehensive vehicle control commands, improving the accuracy of obstacle recognition and the quality of environmental perception in the intelligent vehicle.

[0028] 2. This invention can support the access of various types of sensors and multimodal obstacle recognition based on multi-source sensor data, and has good sensor data synchronization and obstacle recognition effects.

[0029] 3. This invention further achieves heterogeneous system redundancy for the autonomous driving controller by using redundant data interaction transmission methods between two different buses—the system bus and the vehicle bus—and a redundancy switching mechanism adapted to heterogeneous communication media. This greatly improves system reliability and ensures the continuity of autonomous driving operations. Simultaneously, the processing unit supports redundant vehicle-to-ground wireless communication, effectively improving the reliability of vehicle-to-ground wireless communication, thereby enhancing the reliability of the autonomous driving system. Attached Figure Description

[0030] Figure 1This is a schematic diagram of the basic components of the intelligent vehicle control device in an embodiment of the present invention.

[0031] Figure 2 This is a schematic diagram of the control redundancy system in an embodiment of the present invention.

[0032] Figure 3 This is a schematic diagram of wireless communication redundancy in an embodiment of the present invention.

[0033] Figure 4 This is a schematic diagram of the system and data processing layering in an embodiment of the present invention.

[0034] Figure 5 This is a schematic diagram of the vehicle-mounted system composition according to an embodiment of the present invention. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0036] like Figure 1 As shown, the intelligent vehicle control device in this embodiment includes: a GPU image processing unit, a WLU wireless communication unit, and an FPU fusion processing unit. These units interact with each other via a system bus and also have a time synchronization interface. The GPU image processing unit and the FPU fusion processing unit are connected to the vehicle bus via independent bus interfaces. The GPU image processing unit acquires and processes data collected by intelligent sensors and interacts with the FPU fusion processing unit. The WLU wireless communication unit enables wireless communication between the device and external devices and uploads the acquired information to the FPU fusion processing unit via the system bus. The FPU fusion processing unit fuses the acquired data from the image processing unit, the wireless communication unit, and the vehicle data to obtain vehicle control commands.

[0037] In this embodiment, the GPU image processing unit includes an image computing and processing module and a first monitoring module. The image processing module includes a camera interface for connecting to an external camera, an Ethernet interface for connecting to other vehicle-mounted devices, and a CAN interface for connecting to the vehicle bus. The first monitoring module is used to monitor the operating environment and operating status of the image computing and processing module, as well as for fault protection and status recovery. It monitors and alarms for events exceeding the allowed operating environment requirements of the computing and processing module, and determines whether a fault has occurred based on the operating status of the computing and processing module, taking corresponding measures for fault recovery and fault protection.

[0038] In this embodiment, the FPU fusion processing unit includes: a fusion computing processing module, a second monitoring module, a data interaction module, and a bus expansion module. The fusion computing processing module includes an Ethernet interface for connecting with other vehicle-mounted devices and sensors. The data interaction module is used to exchange the results of data processing between the fusion computing processing module and the image computing processing module. The bus expansion module has an interface for receiving vehicle status information and shares the received information to the fusion computing processing module through the data interaction module. The second monitoring module is used to monitor the operating environment and operating status of the fusion computing processing module, as well as its fault protection and status recovery. It monitors and alarms for events exceeding the allowed operating environment requirements of the computing processing module, and determines whether a fault has occurred based on the operating status of the computing processing module, taking corresponding measures for fault recovery and fault protection.

[0039] Specifically, environmental sensing devices such as lidar and millimeter-wave radar primarily connect to the intelligent vehicle control device via the Ethernet and CAN interfaces of the FPU fusion processing unit. When the number of FPU fusion processing unit interfaces is insufficient, connection to the intelligent vehicle control device can also be achieved through the system bus. The vehicle chassis's drive-by-wire CAN bus connects to the CAN interface of the FPU fusion processing unit. Furthermore, the data interaction module expands the system bus through data exchange between ports, while also supporting data sharing between the FPU fusion processing unit, GPU image processing unit, and WLU wireless communication unit in a peer-to-peer manner, effectively improving system scalability and data processing efficiency.

[0040] In this embodiment, multiple fusion processing subunits are configured as master and slave devices according to preset device addresses, with the master device having a higher priority than the slave device. The master device performs bidirectional data interaction with the vehicle's drive-by-wire chassis, while the slave device monitors the data on the vehicle bus of the drive-by-wire chassis. The multiple fusion processing subunits perform self-tests periodically and exchange their self-test results and current status through the system bus and the vehicle CAN bus. When the master device fails to complete the status interaction on time or the self-test is abnormal, the slave device automatically becomes the master device and takes over the control of the vehicle.

[0041] like Figure 2 As shown in the illustration, in a specific application embodiment, the control redundancy of the FPU fusion processing unit is explained using two fusion processing subunits, A-series and B-series, as examples. The A-series and B-series fusion processing subunits simultaneously synchronize their states and exchange processing data through two different communication methods: the system bus and the vehicle bus. This effectively avoids single-point failures in the control function from affecting the normal operation of the system. The detailed control redundancy method is as follows:

[0042] Step 1: After the system powers on, initialize the A-series and B-series FPU fusion processing units and configure them as master and slave devices according to the preset device addresses. By default, the A-series FPU unit is the master control device;

[0043] Step 2: After initialization, the A-series and B-series FPU fusion processing units assign their respective priorities on the vehicle CAN bus based on the current master-slave status. On the vehicle CAN bus, the master control device has a higher priority than the slave control device.

[0044] Step 3: When the device is in master control mode, it has the authority to exchange data bidirectionally with the vehicle's drive-by-wire chassis. When the device is in slave control mode, it listens to the data of the vehicle bus of the vehicle drive-by-wire chassis.

[0045] Step 4: During operation, the A-series and B-series FPU fusion processing units periodically perform self-tests. These self-tests periodically check the critical task execution time, program execution space, and the correctness of the processing chip's calculations within the fusion computing module. This comprehensive assessment determines whether the processing unit is operating abnormally. After each self-test, the self-test results and master-slave status are exchanged via the system bus and vehicle CAN bus. The self-test results and master-slave status exchanged via the system bus are given priority in the interaction process.

[0046] Step 5: During the periodic self-test, the master device and slave device monitor the status of the processing module through their respective monitoring modules. When the monitoring module detects that the critical task of the processing module has timed out, the program running space is abnormal, or the processing chip is abnormal, it stops outputting control commands to the vehicle CAN bus.

[0047] Step 6: When there is only one main control device in the A-series and B-series FPU fusion processing units, the main control FPU fusion processing unit interacts with the drive-by-wire chassis through the vehicle bus to exchange vehicle control data and realize vehicle control.

[0048] Step 7: If the master control device fails to complete the result and status interaction with the slave control device in Step 4 within the predetermined period, or if the master control device malfunctions during self-test, the slave control device automatically upgrades to the master control device. It then exchanges data with the drive-by-wire chassis via the vehicle bus and takes over control of the vehicle.

[0049] In this embodiment, the WLU wireless communication unit includes multiple wireless communication sub-units. Each wireless communication sub-unit establishes an independent communication link with the ground control equipment or other wireless equipment to receive wireless communication data. After copying the received wireless communication data, it sends it to each fusion processing sub-unit through a designated channel. Each fusion processing sub-unit selectively processes one copy of the communication data.

[0050] like Figure 3As shown, in a specific application embodiment, the WLU wireless communication unit includes an A-series WLU wireless communication subunit and a B-series WLU wireless communication subunit. When the system is working, the ground control station and other wireless devices simultaneously interact with the A-series and B-series WLU wireless communication subunits. The A-series and B-series WLU wireless communication subunits copy the received wireless communication data into two copies and send them to the A-series FPU fusion processing subunit and the B-series FPU fusion processing subunit respectively through the first channel and the second channel. After receiving the data from the A-series and B-series WLU wireless communication subunits from the two channels, the data interaction module of the A-series FPU fusion processing subunit forwards the data to the fusion processing module. After receiving the data from any one of the two WLU wireless communication subunits from the two channels, the fusion processing module of the A-series FPU data fusion processing subunit discards the received data from the other WLU unit. The received WLU data is processed to achieve redundancy between the A-series and B-series WLU wireless communication subunits and the A-series FPU fusion processing subunits. The B-series FPU fusion processing subunits are processed in the same way as the A-series FPU fusion processing subunits to achieve wireless communication redundancy.

[0051] In summary, the intelligent vehicle control device in this embodiment can be divided into three layers: a communication extension layer, a system data interaction layer, and a data processing layer, such as... Figure 4 As shown. The communication extension layer is used to extend the external CAN bus and wireless communication, specifically including a bus extension module and a wireless communication extension module. It communicates with the ECU (Electronic Control Unit) / steering controller of the vehicle chassis and with navigation satellites, mobile communication ground base stations, etc., for wireless communication. The system data interaction layer is used for data interaction between modules within the device, ensuring smooth data flow between functional units. The system data interaction layer includes multiple fusion / image processing modules and a monitoring module, used to process data from different sensors and monitor the system's operating status. The data processing layer includes a fusion computing processing unit, a graphics computing processing unit, and a wireless communication unit. The fusion computing processing unit, graphics computing processing unit, and wireless communication unit are interconnected through the system bus and have a time synchronization interface to ensure the accuracy and timeliness of data processing. In this embodiment, the FPU fusion processing unit includes multiple fusion processing sub-units. These sub-units synchronize their status through the system bus and the vehicle CAN bus. When the status information obtained from the system bus and the vehicle CAN bus is inconsistent, the result synchronized by the system bus is prioritized.

[0052] In this embodiment, the intelligent vehicle control system includes:

[0053] Intelligent vehicle control device;

[0054] Multiple sensing sensors are used to collect data on the vehicle's surrounding environment and are connected to the GPU image processing unit and FPU fusion processing unit through the corresponding interfaces of the intelligent vehicle control device.

[0055] Satellite navigation system signal receiving device, used to provide vehicle positioning information;

[0056] The ground server interacts with the WLU wireless communication unit of the intelligent vehicle control device via wireless communication to exchange vehicle operation management and safety monitoring data, including global path planning for vehicle operation, satellite navigation correction, fleet formation and vehicle operation status, early warning of the surrounding environment, control and other data.

[0057] The drive-by-wire chassis, including the ECU (Electronic Control Unit) / steering controller, is connected to the intelligent vehicle control device via a CAN bus.

[0058] like Figure 5 As shown, the intelligent vehicle control system mainly consists of intelligent vehicle control devices and sensing sensors, and provides a drive-by-wire chassis, human-machine interaction / remote debugging expansion interface. It also provides interfaces with other third-party onboard devices. Main components include:

[0059] A CAN communication interface for the vehicle chassis, supporting the connection of the vehicle chassis's ECU and steering controller;

[0060] Wireless interface between navigation satellites and mobile communication ground base stations;

[0061] Reserved expansion interfaces for human-computer interaction display devices and third-party devices;

[0062] At the same time, it obtains the power required for operation from the vehicle's power supply.

[0063] In this embodiment, the intelligent vehicle control method includes:

[0064] Step S1: The WLU wireless communication unit receives the generated vehicle route information and shares the received vehicle route information to the fusion computing processing module through the data interaction module of the FPU fusion processing unit;

[0065] Step S2: The GPU image processing unit acquires sensor data and shares the acquired sensor data with the fusion computing processing module through the data interaction module of the FPU fusion processing unit;

[0066] Step S3: The data interaction module of the FPU fusion processing unit shares the data obtained from the vehicle drive-by-wire chassis CAN bus to the fusion computing processing module.

[0067] Step S4: The fusion computing and processing module of the FPU fusion processing unit generates control commands based on the vehicle running route information, sensor data, and data information on the vehicle drive-by-wire chassis CAN bus. The commands are then sent to the vehicle drive-by-wire chassis CAN bus through the data interaction module and the bus expansion module, thereby realizing the control of vehicle operation.

[0068] In a specific application embodiment, the following steps are used to control the intelligent vehicle:

[0069] Step 1: When the onboard system is working, the overall vehicle route is generated by the ground control system and transmitted to the WLU wireless communication unit via 4G / 5G mobile communication, LoRa, or other wireless communication methods. The WLU wireless communication unit then shares this route with the fusion computing module of the FPU fusion processing unit through the data interaction module.

[0070] Step 2: Smart sensors such as cameras, LiDAR, and millimeter-wave radar are expanded through external interfaces of the FPU fusion processing unit and GPU image processing unit.

[0071] Step 3: The fusion computing module of the FPU fusion processing unit and the image computing processing module of the GPU image processing unit interact with the data interaction module of the unit fused by the FPU to process the raw data of LiDAR, millimeter-wave radar, and camera before and after the key events of sensor processing by the GPU image processing unit, as well as the feature value data with time information after the raw data of LiDAR, millimeter-wave radar, and camera are processed by the algorithm.

[0072] Step 4: Vehicle data on the vehicle's drive-by-wire chassis CAN bus, including but not limited to speed, steering angle, cylinder, braking, truck bed, lights, position, and status switching, enters the data interaction module through the FPU fusion processing unit bus expansion module and is shared with the FPU unit fusion computing processing module for processing.

[0073] Step 5: After the FPU unit fusion processing module processes the data obtained from the WLU unit, GPU unit, LiDAR, millimeter-wave radar, and vehicle drive-by-wire chassis, it generates control commands for the vehicle.

[0074] Step 6: Control commands are sent to the vehicle's drive-by-wire chassis CAN bus via the data interaction module and bus expansion module. This enables control of vehicle speed, steering, truck bed lifting, lights, etc.

[0075] In this embodiment, the FPU fusion processing unit includes multiple fusion processing sub-units. These multiple fusion processing sub-units simultaneously perform state synchronization and data processing interaction through two different communication methods: the system bus and the vehicle bus, in order to achieve hot standby redundancy of the autonomous vehicle control function.

[0076] In this embodiment, when the status information obtained by the system bus and the vehicle CAN bus is inconsistent, the result of the system bus synchronization is given priority.

[0077] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent vehicle control device, characterized in that, include: The device comprises a GPU image processing unit, a WLU wireless communication unit, and an FPU fusion processing unit. These units interact via a system bus. The GPU image processing unit and the FPU fusion processing unit are connected to the vehicle bus through independent bus interfaces. The GPU image processing unit acquires and processes data collected by intelligent sensors and interacts with the FPU fusion processing unit. The WLU wireless communication unit enables wireless communication between the device and external devices and uploads the acquired information to the FPU fusion processing unit via the system bus. The FPU fusion processing unit fuses the acquired data from the image processing unit, the wireless communication unit, and the vehicle data to obtain vehicle control commands. The FPU fusion processing unit includes: a fusion computing processing module, a second monitoring module, a data interaction module, and a bus expansion module. The fusion computing processing module includes an Ethernet interface for connecting with other vehicle-mounted devices and sensors. The data interaction module is used to exchange the processing results of the fusion computing processing module and the image computing processing module on the collected data. The bus expansion module is provided with an interface for receiving vehicle status information and sharing the received information to the fusion computing processing module through the data interaction module. The second monitoring module is used to monitor the operating environment and status of the fusion computing processing module and provides a fault protection mechanism. The FPU fusion processing unit includes multiple fusion processing sub-units. The fusion processing sub-units synchronize their states through the system bus and the vehicle CAN bus. When the state information obtained by the system bus and the vehicle CAN bus is inconsistent, the result synchronized by the system bus is selected first. The multiple fusion processing subunits are configured as master and slave devices according to preset device addresses, with the master device having a higher priority than the slave device. The master device performs bidirectional data interaction with the vehicle's drive-by-wire chassis, while the slave device monitors the data on the vehicle bus of the drive-by-wire chassis. The multiple fusion processing subunits perform self-tests periodically and exchange their self-test results and current status through the system bus and the vehicle CAN bus. When the master device fails to complete the status interaction on time or the self-test is abnormal, the slave device automatically becomes the master device and takes over the control of the vehicle.

2. The intelligent vehicle control device according to claim 1, characterized in that, The GPU image processing unit includes an image computing and processing module and a first monitoring module. The image processing module includes a camera interface for connecting to an external camera, an Ethernet interface for connecting to other vehicle-mounted devices, and a CAN interface for connecting to the vehicle bus. The first monitoring module is used to monitor the operating environment and status of the image computing and processing module and provides a fault protection mechanism.

3. The intelligent vehicle control device according to claim 1, characterized in that, The WLU wireless communication unit includes multiple wireless communication sub-units. Each wireless communication sub-unit establishes an independent communication link with the ground control equipment or other wireless equipment to receive wireless communication data. After copying the received wireless communication data, it sends it to each fusion processing sub-unit through a designated channel. Each fusion processing sub-unit selectively processes one copy of the communication data.

4. An intelligent vehicle control system, characterized in that, include: The intelligent vehicle control device according to any one of claims 1 to 3; Multiple sensing sensors are used to collect data on the vehicle's surrounding environment and are connected to the GPU image processing unit and FPU fusion processing unit through the corresponding interfaces of the intelligent vehicle control device. Satellite navigation system signal receiving device, used to provide vehicle positioning information; The ground server interacts with the WLU wireless communication unit of the intelligent vehicle control device to exchange vehicle operation management and safety monitoring data via wireless communication. The drive-by-wire chassis, including the ECU (Electronic Control Unit) / steering controller, is connected to the intelligent vehicle control device via a CAN bus.

5. A method for controlling an intelligent vehicle, characterized in that, include: Step S1: The WLU wireless communication unit receives the generated vehicle route information and shares the received vehicle route information to the fusion computing processing module through the data interaction module of the FPU fusion processing unit; Step S2: The GPU image processing unit acquires sensor data and shares the acquired sensor data with the fusion computing processing module through the data interaction module of the FPU fusion processing unit; Step S3: The data interaction module of the FPU fusion processing unit shares the data obtained from the vehicle drive-by-wire chassis CAN bus to the fusion computing processing module. Step S4: The fusion computing and processing module of the FPU fusion processing unit generates control commands based on the vehicle running route information, sensor data, and data information on the CAN bus of the vehicle drive-by-wire chassis. The commands are then sent to the CAN bus of the vehicle drive-by-wire chassis through the data interaction module and the bus expansion module, thereby realizing the control of vehicle operation. The FPU fusion processing unit includes: a fusion computing processing module, a second monitoring module, a data interaction module, and a bus expansion module. The fusion computing processing module includes an Ethernet interface for connecting with other vehicle-mounted devices and sensors. The data interaction module is used to exchange the processing results of the fusion computing processing module and the image computing processing module on the collected data. The bus expansion module is provided with an interface for receiving vehicle status information and sharing the received information to the fusion computing processing module through the data interaction module. The second monitoring module is used to monitor the operating environment and status of the fusion computing processing module and provides a fault protection mechanism. The FPU fusion processing unit includes multiple fusion processing sub-units. These multiple fusion processing sub-units simultaneously perform state synchronization and data processing interaction through two different communication methods: the system bus and the vehicle CAN bus, in order to achieve hot standby redundancy of the autonomous vehicle control function. When the status information obtained by the system bus and the vehicle CAN bus is inconsistent, the result synchronized by the system bus shall be given priority.

Images