CN219172410U - A vehicle-mounted intelligent computing device, a control system, and an intelligent driving vehicle - Google Patents

Abstract

Embodiments of the present invention provide a vehicle-mounted intelligent computing device, a control system, and an intelligent driving vehicle, wherein the vehicle-mounted intelligent computing device includes: an external interface module, an AI computing module, a fusion computing module, and a regulation and positioning module; the external interface module includes Several interfaces; the fusion calculation module is connected to the vehicle sensor device through the first interface; the regulation and positioning module is connected to the vehicle positioning device and the vehicle control unit through the second interface; the fusion calculation module is connected to the AI calculation module and the regulation and positioning module respectively. It can improve the computing efficiency of intelligent driving and reduce hardware costs.

Description

A vehicle-mounted intelligent computing device, a control system, and an intelligent driving vehicle

technical field

The utility model relates to the technical field of intelligent driving, in particular to a vehicle-mounted intelligent computing device, a control system and an intelligent driving vehicle.

Background technique

Rail-based electric locomotives are an important carrier for industrial and mining enterprises to transport goods in the park. After the traditional locomotive is electrified, it can achieve "zero pollution" in the whole process of locomotive operation in industrial and mining enterprises, and the new rail electric locomotive has undergone system upgrades and optimizations in terms of battery system, vehicle control and motor drive system. Electric locomotives need to observe the driving environment manually, and carry out manual driving control according to the environmental conditions and driving tasks. There are problems such as manual misjudgment, high vehicle driving and operating costs, and low driving efficiency.

In order to solve the above problems, the intelligent driving technology of electric locomotives has become one of the research hotspots in the industry. Since intelligent driving technology needs to process massive amounts of data and perform complex logic operations, it requires large computing power support. Vehicle-mounted intelligent computing equipment needs to process all sensor data at the same time, and make decisions and executions based on the processing results. This method requires high chip computing power, and vehicle-mounted intelligent computing equipment requires excellent structural design and functional design.

Therefore, how to provide a vehicle-mounted intelligent computing device, a control system, and an intelligent driving vehicle to improve the computing efficiency of intelligent driving and reduce hardware costs has become an urgent problem to be solved.

Utility model content

Aiming at the defects in the prior art, this embodiment provides a vehicle-mounted intelligent computing device, a control system, and an intelligent driving vehicle.

The utility model provides a vehicle-mounted intelligent computing device, comprising: an external interface module, an AI computing module, a fusion computing module, and a regulatory positioning module;

Wherein, the external interface module includes several interfaces;

The fusion calculation module is connected with the vehicle sensor device through the first interface;

The regulatory positioning module is connected with the vehicle positioning device and the vehicle control unit through the second interface;

The fusion calculation module is connected with the AI calculation module and the regulatory positioning module respectively.

Optionally, the vehicle-mounted intelligent computing device provided by the present invention also includes: a redundant computing module;

The redundant calculation module is respectively connected with the AI calculation module and the regulatory positioning module.

Optionally, the vehicle-mounted intelligent computing device provided by the present invention also includes: a monitoring and management module;

The monitoring and management module is respectively connected with the external interface module, AI computing module, fusion computing module and regulatory positioning module.

Optionally, in the vehicle-mounted intelligent computing device provided by the present invention, the external interface module includes: at least one of LVDS interface, ETH interface, CAN bus interface, UART interface, DI interface and AI interface.

Optionally, in the vehicle-mounted intelligent computing device provided by the utility model, the AI computing module adopts an AI chip;

The fusion computing module and the regulatory positioning module use the RK3588 chip.

Optionally, the monitoring and management module of the vehicle-mounted intelligent computing device provided by the present invention adopts a TC397 chip.

The utility model also provides a vehicle-mounted intelligent control system, including the above-mentioned vehicle-mounted intelligent computing equipment, vehicle-mounted sensor equipment, vehicle-mounted positioning equipment and a vehicle control unit.

Optionally, in the vehicle-mounted intelligent control system provided by the present invention, the vehicle-mounted sensor equipment includes: at least one of a camera, a laser radar sensor and a millimeter-wave radar sensor.

Optionally, in the vehicle-mounted intelligent control system provided by the utility model, the vehicle-mounted positioning device adopts GNSS/IMU combined navigation device.

The utility model also provides an intelligent driving vehicle, which is equipped with the vehicle-mounted intelligent control system.

In the vehicle-mounted intelligent computing device, control system and intelligent driving vehicle provided by the embodiment of the utility model, three computing modules with different functions are designed in the vehicle-mounted intelligent computing device: AI computing module, fusion computing module and regulatory positioning module, through the external interface module Control the source of data, and deliver the data required for intelligent driving to different computing modules for processing, effectively reducing the demand for computing power of a single module, reducing hardware costs, and adopting the method of dividing the overall computing task into multiple sub-modules. The task is processed by different computing modules at the same time, which can effectively improve the computing efficiency of intelligent driving.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings show some embodiments of the utility model, and those skilled in the art can also obtain other drawings according to these drawings without creative work.

Fig. 1 is a schematic structural diagram of a vehicle-mounted intelligent computing device provided by an embodiment of the present invention;

Fig. 2 is the overall design architecture diagram of the intelligent computing unit provided by the embodiment of the present invention;

Fig. 3 is a schematic diagram of the core structure of the AI chip provided by the embodiment of the present invention;

Fig. 4 is the overall design architecture diagram of the fusion computing module provided by the embodiment of the present invention;

Fig. 5 is the overall design architecture diagram of the regulatory positioning module provided by the embodiment of the present invention;

FIG. 6 is an overall design architecture diagram of the redundant computing module provided by the embodiment of the present invention;

Fig. 7 is the overall design architecture diagram of the monitoring and management module provided by the embodiment of the utility model;

FIG. 8 is a schematic diagram of the communication architecture of the vehicle-mounted intelligent computing device provided by the embodiment of the present invention;

Fig. 9 is a schematic diagram of the data flow of the intelligent driving of the electric locomotive provided by the embodiment of the present invention;

FIG. 10 is a schematic diagram of a multi-sensor fusion positioning architecture provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the utility model more clear, the technical solutions in the embodiments of the utility model will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the utility model. Obviously, the described The embodiments are some embodiments of the present utility model, but not all embodiments. Based on the embodiments of the present utility model, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of the present utility model.

Figure 1 is a schematic structural diagram of the vehicle-mounted intelligent computing device provided by the embodiment of the utility model. As shown in Figure 1, the utility model provides a vehicle-mounted intelligent computing device, including: external interface module, AI computing module, fusion computing module and regulatory control positioning module;

Wherein, the external interface module includes several interfaces;

The fusion calculation module is connected with the vehicle sensor device through the first interface;

The regulatory positioning module is connected with the vehicle positioning device and the vehicle control unit through the second interface;

The fusion calculation module is connected with the AI calculation module and the regulatory positioning module respectively.

Specifically, the vehicle-mounted intelligent computing device provided by the embodiments of the present invention can be divided into an external interface module, an AI computing module, a fusion computing module, and a regulatory positioning module according to the hardware composition structure.

Wherein, the external interface module includes several interfaces; it can be connected with vehicle-mounted equipment according to different buses. It can be understood that in order to realize intelligent driving, the interface needs to be connected to the vehicle sensor equipment, the vehicle positioning device and the vehicle control unit. The specific equipment type and the bus type required for the interface can be set according to actual needs, and the utility model does not make any comment on this. limited.

The external interface module transmits the data collected by the vehicle sensor to the fusion calculation module through the first interface. The fusion computing module includes middleware and drivers for processing vehicle-mounted sensor data. After obtaining the vehicle-mounted sensor data, pre-processing, perception, fusion and prediction can be performed on the data through the preset running perception algorithm (for example, the front-end camera processing and lidar pre-processing).

The fusion computing module is connected to the AI computing module, and the AI computing module can be directly dispatched for AI computing. The AI calculation module includes an AI chip, which is responsible for AI-related calculations, and can run target detection algorithms based on video analysis to detect and identify target objects such as electric locomotive tracks, front vehicle rears, obstacles and pedestrians.

The external interface module transmits the data collected by the on-board positioning device to the regulation and positioning module through the second interface. After the regulation and positioning module obtains the data collected by the vehicle positioning device, it can run the preset regulation and control algorithm and positioning algorithm. In addition, the regulatory positioning module is connected with the fusion computing module, which can be used as a time synchronization master to realize the synchronization of different sensor data (for example, to perform camera and lidar frame synchronization).

It should be noted that the "first" and "second" in the first interface module and the second interface module are only used as text to distinguish interfaces, and do not contain actual meanings.

It can be understood that the utility model only limits the specific connection modes of the above-mentioned external interface module, fusion computing module, AI computing module and regulatory positioning module, so that technicians can more conveniently realize intelligent driving-related development under this hardware configuration.

In addition, the vehicle control unit is the unit that executes intelligent decision-making control (such as starting, accelerating, braking, parking avoidance, steering and lighting changes, etc.) in the vehicle. In the practical application of the present invention, the specific equipment types and control methods included in the vehicle control unit can be set according to the vehicle type and actual needs, which is not limited in the present invention.

For example, after obtaining the data collected by the on-board sensor according to the external interface module, according to the regulation and positioning module, the fusion calculation module and the AI calculation module, it is determined that the intelligent decision is to turn on the left turn signal and turn left. At this time, the vehicle control unit activates the left turn steering Lights, and make the steering gear work, so that the front wheels of the vehicle have an angle to achieve the effect of turning left.

The specific implementation steps of the method mentioned in the embodiment are only used as a specific example to assist in explaining the practical application of the present invention. The utility model only provides reference, and the specific algorithm adopted by the module and the realized function It can be set according to actual needs. In addition, the type of chip used in the module can be selected according to actual needs, which is not limited by the present invention.

Taking the rail electric locomotive as an example, using the on-board computing equipment provided by the utility model, combined with software algorithms, can realize the intelligent perception, intelligent positioning, route navigation planning and intelligent decision-making control (such as starting, accelerating, braking, parking avoidance) of the electric locomotive , steering and lighting changes, etc.), through reasonable matching and design of various device modules and modules, solve the problems of peripheral access, environmental perception, regulatory positioning and decision-making control that are not real-time, accurate and intelligent in the current manual driving of electric vehicles. Realize efficient and low-cost unmanned intelligent driving of electric locomotives. In scenarios such as the transportation of molten iron in iron and steel plants, it can liberate people from high-intensity and high-risk working environments, reduce the overall cost of manpower input by 30%, improve the efficiency of cargo transportation, and improve the competitiveness of related enterprises as a whole .

The vehicle-mounted intelligent computing device provided by the embodiment of the utility model, according to the principle of edge computing, is designed in the vehicle-mounted intelligent computing device with three computing modules with different functions: AI computing module, fusion computing module and regulatory positioning module, which are controlled by the external interface module The source of data, the data required for intelligent driving is delivered to different computing modules for processing, which effectively reduces the demand for computing power of a single module, reduces hardware costs, and adopts the method of dividing the overall computing task into multiple sub-tasks At the same time, the way of processing by different computing modules can effectively improve the computing efficiency of intelligent driving.

Optionally, the vehicle-mounted intelligent computing device provided by the present invention also includes: a redundant computing module;

The redundant calculation module is respectively connected with the AI calculation module and the regulatory positioning module.

Specifically, the utility model can also add a redundant computing module to provide more redundant computing power to share the pressure of the fusion computing module and the regulatory positioning module, such as sensor pre-processing, fusion computing, etc.

The vehicle-mounted intelligent computing device provided by the embodiment of the utility model further enhances the computing capability of the vehicle-mounted intelligent computing device and improves computing efficiency by setting redundant computing modules for performance supplementation and sharing the computing pressure of the fusion computing module and the regulatory positioning module.

Optionally, the vehicle-mounted intelligent computing device provided by the present invention also includes: a monitoring and management module;

The monitoring and management module is respectively connected with the external interface module, AI computing module, fusion computing module and regulatory positioning module.

Specifically, the utility model can also add a monitoring and management module, which is responsible for power management and status monitoring of the entire vehicle-mounted intelligent computing device, real-time monitoring of the operating status of the module, such as information such as the voltage and temperature of the monitoring module, and determining whether there is a hardware failure .

The vehicle-mounted intelligent computing device provided by the embodiment of the utility model also monitors the modules in the vehicle-mounted intelligent computing device by setting a monitoring management module, so as to ensure that each module can operate normally and give an alarm in time when an abnormal situation occurs.

Optionally, in the vehicle-mounted intelligent computing device provided by the present invention, the external interface module includes: at least one of LVDS interface, ETH interface, CAN bus interface, UART interface, DI interface and AI interface.

Specifically, Fig. 2 is an overall design architecture diagram of the intelligent computing unit provided by the embodiment of the present invention. As shown in Fig. 2, considering that in practical applications, the interfaces used by various sensor devices, positioning devices and vehicle control units are inconsistent .

The external interface module of the utility model includes: at least one of LVDS interface, ETH interface, CAN bus interface, UART interface, DI interface and AI interface.

The external interface module supports access to the electric vehicle camera device through the LVDS (Low Voltage Differential Signaling, low voltage differential signal) interface; supports the access to the lidar device through the standard ETH (ethernet, Ethernet) interface; supports the CAN bus interface (Controller Area Network, controller area network) or standard ETH interface to access millimeter-wave radar equipment; support access to GNSS (Global Navigation Satellite System, Global Navigation Satellite System) through CAN bus interface or UART (Universal Asynchronous Receiver/Transmitter, Universal Asynchronous Receiver Transmitter Interface) )/IMU (Inertial Measurement Unit, Inertial Navigation Measurement Unit) integrated navigation equipment; it supports docking with the vehicle control unit of the electric locomotive through CAN bus interface and DI (digital input)/AI (DC analog input) interface.

It can be understood that, when the utility model is actually applied, the type and quantity of the specific interfaces included can be set according to actual needs, and the utility model does not limit this.

In the vehicle-mounted intelligent computing device provided by the embodiment of the utility model, the external interface module is provided with several interfaces, the number and type of the interfaces can be set, and the peripheral device access capability is provided, so as to facilitate data transmission between different computing modules and peripheral devices.

Optionally, in the vehicle-mounted intelligent computing device provided by the utility model, the AI computing module adopts an AI chip;

The fusion computing module and the regulatory positioning module use the RK3588 chip.

Specifically, Fig. 3 is a schematic diagram of the core structure of the AI chip provided by the embodiment of the utility model. As shown in Fig. 3, the AI computing module is a high-energy-efficiency AI chip, which is an independent and controllable storage-computing integrated chip made in China, with a computing power of 288TOPS@ INT8, memory GDDR6, memory bandwidth 128GB/s, 16 real-time video stream codecs, PCIe4.0X8, X4, EPMode, TDP power consumption 15~30W. In addition, other AI chips can also be used, which is not limited in the present invention.

Fig. 4 is the overall design architecture diagram of the fusion computing module provided by the embodiment of the utility model, and Fig. 5 is the overall design architecture diagram of the regulation and positioning module provided by the embodiment of the utility model, as shown in Fig. 4-5, the fusion computing module and the regulation The control positioning module is realized based on the chip RK3588. Here, the fusion computing module chip is marked as RK3588-A, and the regulatory positioning module is marked as RK3588-B. The English letter suffix here is only used to distinguish the chip from the text part, and does not contain the actual meaning.

In actual application, the fusion computing module (RK3588-A) chip is designed with 8 ARM CortexACores, 4 of which are CortexA76, the main frequency can reach 2256MHz, and the remaining 4 are CortexA55, the main frequency can reach 1800MHz. The total computing power of 8 cores can reach about 100KDMIPS. In addition, RK3588 also has 3 ARM Cortex-M0MCUs, 4 ARM Ali-G610MP4GPUs, and an ISP that can process 48MPixels image data.

The fusion computing module (RK3588-A) is mainly responsible for running perception algorithm applications, including camera pre-processing, lidar pre-processing, perception, fusion, prediction, and the middleware and drivers on which these applications depend. The peripheral part is connected to multiple GMSL2 cameras and lidar. At the same time, the fusion computing module (RK3588-A) is the only main chip that can directly dispatch high-energy-efficiency AI chips for reasoning operations, and the interaction mode is through the PCI-E channel.

The external communication interface of the fusion computing module (RK3588-A) is used as follows:

1. Transmit monitoring data with the monitoring management module (TC397) through one UART. The monitoring management module (TC397) will monitor the working status of the fusion computing module (RK3588-A), such as hardware failure, voltage, temperature, etc.

2. Connect to PCI-Eswitch, and transmit data related to algorithm model calculation with high-energy-efficiency AI chip through PCI-E, including: algorithm model, sensor data, and calculation results.

3. Communicate with the high-energy-efficiency AI chip through SPI to read the working status of the high-energy-efficiency AI chip, especially when the PCI-E communication is abnormal, the possible cause of the failure can be obtained.

4. Connect to the Ethernet switch through RGMII, and can send and receive sensor data and business data within the domain.

Fusion computing module (RK3588-A) external storage: 1. External 16GB DDR4, as the program running memory. 2. External 64GBeMMC, storage system software and algorithm program. 3. An NVMe solid-state drive with an external M.2 interface is used to store sensor data and log files.

The regulatory control positioning module (RK3588-B) chip design has 8 ARM CortexACores, 4 of which are CortexA76, the main frequency can reach 2256MHz, and the remaining 4 are CortexA55, the main frequency can reach 1800MHz. The total computing power of 8 cores can reach about 100KDMIPS. In addition, RK3588 also has 3 ARM Cortex-M0MCUs, 4 ARM Ali-G610MP4GPUs, and an ISP that can process 48MPixels image data.

The regulatory positioning module (RK3588-B) is mainly responsible for running pure CPU computing applications, including positioning, planning and control, as well as the middleware and drivers that these applications depend on. The peripheral part is connected to multiple lidars and 1 integrated navigation.

The external communication interface of the regulation and positioning module (RK3588-B) is used as follows:

1. Transmit monitoring data with the monitoring management module (TC397) through one UART. The monitoring management module (TC397) will monitor the working status of the regulatory positioning module (RK3588-B), such as hardware failure, voltage, temperature, etc.

2. Connected to PCI-Eswitch, it can perform large-scale data transmission with other RK3588, such as lidar point cloud data.

3. Obtain positioning sensor data through UART connection combination navigation.

4. Connect the integrated navigation through PPS, obtain GPS time, and provide timebase for intra-domain time synchronization.

5. Connect to the Ethernet switch through RGMII, and can send and receive sensor data and business data within the domain.

Regulatory positioning module (RK3588-B) external storage: 1. External 16GB DDR4, as the program running memory. 2. External 64GBeMMC, storage system software and algorithm program. 3. An external NVMe solid state drive with 512GBM.2 interface is used to store sensor data and log files.

Figure 6 is a diagram of the overall design architecture of the redundant computing module provided by the embodiment of the utility model. c.

In actual application, the redundant computing module (RK3588-C) chip is designed with 8 ARM CortexACores, 4 of which are CortexA76, the main frequency can reach 2256MHz, and the remaining 4 are CortexA55, the main frequency can reach 1800MHz. The total computing power of 8 cores can reach about 100KDMIPS. In addition, RK3588 also has 3 ARM Cortex-M0MCUs, 4 ARM Ali-G610MP4GPUs, and an ISP that can process 48MPixels image data.

The redundant computing module (RK3588-C) is used in the Max version of the intelligent computing unit for performance supplementation. It can share the computing pressure of the fusion computing module (RK3588-A)/B, such as splitting the post-fusion and lidar point cloud pre-processing to the redundant computing module (RK3588-C).

The external communication interface of the redundant computing module (RK3588-C) is used as follows:

1. Transmit monitoring data with the monitoring management module (TC397) through one UART. The monitoring management module (TC397) will monitor the working status of the redundant computing module (RK3588-C), such as hardware failure, voltage, temperature, etc.

2. Connected to PCI-Eswitch, it can perform large-scale data transmission with other RK3588, such as lidar point cloud data.

3. Connect to the Ethernet switch through RGMII, and can send and receive sensor data and business data within the domain.

Redundant computing module (RK3588-C) external storage: 1. External 16GB DDR4, as program running memory. 2. External 64GBeMMC, storage system software and algorithm program. 3. An external NVMe solid state drive with 512GBM.2 interface is used to store sensor data and log files.

The vehicle-mounted intelligent computing device provided by the embodiment of the utility model, according to the principle of edge computing, designs AI computing module (AI chip), fusion computing module and regulatory control positioning module (RK3588) in the vehicle-mounted intelligent computing device to calculate three different functions The module controls the data source through the external interface module, and delivers the data required for intelligent driving to different computing modules for processing, effectively reducing the demand for computing power of a single module, reducing hardware costs, and adopting the overall The calculation task is divided into multiple sub-tasks and processed by different calculation modules at the same time, which can effectively improve the calculation efficiency of intelligent driving.

Optionally, the monitoring and management module of the vehicle-mounted intelligent computing device provided by the present invention adopts a TC397 chip.

Specifically, FIG. 7 is an overall design architecture diagram of the monitoring and management module provided by the embodiment of the present invention. As shown in FIG. 7 , the monitoring and management module adopts a TC397 chip.

In actual application, the monitoring and management module (TC397) uses 1-way UART and AI chip with high energy efficiency ratio, integrated computing module (RK3588-A), regulation and positioning module (RK3588-B), redundant computing module (RK3588-C) Connect, transmit monitoring data, and monitor the status information of each module, such as hardware failure, voltage, temperature, etc.

The vehicle-mounted intelligent computing device provided by the embodiment of the utility model also uses a TC397 chip to set a monitoring and management module to monitor the modules in the vehicle-mounted intelligent computing device to ensure that each module can operate normally and give an alarm in time when abnormal conditions occur.

Combined with the specific examples of the utility model, the actual application of the utility model will illustrate the data flow of the intelligent driving of the electric locomotive and the communication architecture of the vehicle-mounted intelligent computing equipment.

Figure 8 is a schematic diagram of the communication architecture of the vehicle-mounted intelligent computing device provided by the embodiment of the utility model. The UART interface communicates to obtain the working status information of each module.

2) The intelligent computing unit uses the FAKRA interface to communicate with the electric locomotive camera, uses the Ethernet1000baseT1/Tx interface to communicate with the laser radar, and uses the UART or CAN bus to communicate with the GNSS&IMU integrated navigation to obtain the sensory data of each sensor.

3) The intelligent computing unit uses the CAN bus or Ethernet1000baseT1/Tx interface to communicate with the vehicle control unit of the electric locomotive, and transmits the former's perception, regulation and decision-making information to the latter in real time.

4) The AI computing module, fusion computing module, regulatory control positioning module, and redundant computing module communicate through PCI-ESwitch and EthernetSwitch.

Fig. 9 is a schematic diagram of the intelligent driving data flow of the electric vehicle provided by the embodiment of the utility model, as shown in Fig. 9, 1) Sensor data acquisition: the fusion calculation module acquires the video stream of the camera through the GMSL interface, and acquires the laser radar data through the Ethernet interface.

2) Sensor data preprocessing: The fusion computing module performs preprocessing (denoising, smoothing, brightness conversion, etc.) on the camera video stream and the lidar point cloud respectively.

3) Target perception and recognition: call the AI chip with high energy efficiency ratio, and use its model algorithm and AI computing power to detect and recognize the rear of the vehicle in front, the track, pedestrians, obstacles, etc.

4) Electric locomotive positioning: The regulatory positioning module performs multi-sensor fusion positioning calculation on GNSS+IMU integrated navigation data to obtain high-precision positioning data of electric locomotives.

5) Intelligent driving prediction: The fusion calculation module analyzes the behavior patterns of other traffic participants based on the vehicle position and surrounding environment model provided by the target perception and recognition data and the high-precision positioning data of the electric vehicle, and evaluates its future performance within a certain period of time. Trajectory direction, so as to improve the ability of the intelligent driving system to make decisions and plans in complex scenarios.

6) Intelligent driving planning control: path planning undertakes the upper-layer perception prediction results, including three parts: route finding, behavior decision-making, and motion planning. The electric locomotive control module combines path planning information, vehicle body properties, and dynamic calculation of external physical factors to convert it into decision-making data for locomotive control, and transmits the relevant control decision-making data to the vehicle control unit of the electric locomotive through the CAN bus to realize electric locomotive control. Specific controls for accelerator, brake, direction, etc.

It should be noted that the above solution is only used as a specific example to illustrate the practical application of the present utility model, and is not intended as a limitation of the present utility model.

The utility model also provides a vehicle-mounted intelligent control system, including the above-mentioned vehicle-mounted intelligent computing equipment, vehicle-mounted sensor equipment, vehicle-mounted positioning equipment and a vehicle control unit.

Specifically, the vehicle-mounted intelligent control system provided by the present invention is loaded on the vehicle, collects environmental data and location data through vehicle-mounted sensor equipment and vehicle-mounted positioning equipment, and the vehicle-mounted intelligent computing device processes the collected data and performs route navigation planning and intelligent decision-making control ( Such as starting, accelerating, braking, parking avoidance, steering and lighting changes, etc.), the intelligent control of the vehicle is realized through the vehicle control unit. The specific structure and functions of the vehicle-mounted intelligent computing unit are as described above, and will not be repeated here.

The vehicle-mounted intelligent control system provided by the embodiment of the utility model includes a vehicle-mounted intelligent computing device, a vehicle-mounted sensor device, a vehicle-mounted positioning device, and a vehicle control unit. In the vehicle-mounted intelligent computing device, three AI computing modules, a fusion computing module, and a regulatory positioning module are designed. Computing modules with different functions obtain the data of vehicle-mounted sensing devices and vehicle-mounted positioning devices through external interface modules, and control the data source, and deliver the data required for intelligent driving to different computing modules for processing, and control the data through vehicle control The unit realizes intelligent driving. It effectively reduces the demand for computing power of a single module, reduces hardware costs, and adopts the method of dividing the overall computing task into multiple sub-tasks to be processed by different computing modules at the same time, which can effectively improve the computing efficiency of intelligent driving.

Optionally, in the vehicle-mounted intelligent control system provided by the present invention, the vehicle-mounted sensor equipment includes: at least one of a camera, a laser radar sensor and a millimeter-wave radar sensor.

Specifically, the vehicle sensor device includes: at least one of a camera, a laser radar sensor and a millimeter wave radar sensor. The external interface module can be connected with the above-mentioned on-board sensors through CAN bus interface, standard ETH interface, UART interface, LVDS interface and other standard interfaces to obtain sensing data.

In practical applications, the specific types and quantities of on-board sensors can be set according to actual needs, which is not limited by the present invention.

The vehicle-mounted intelligent control system provided by the embodiment of the utility model realizes the acquisition of perception data around the vehicle by setting at least one vehicle-mounted sensor device, transmits the data to the calculation module through the external interface module, and performs data processing to realize the intelligence of the surrounding environment of the vehicle. Perceptual recognition provides data support for intelligent driving.

Optionally, in the vehicle-mounted intelligent control system provided by the utility model, the vehicle-mounted positioning device adopts GNSS/IMU combined navigation device.

Specifically, FIG. 10 is a schematic diagram of the multi-sensor fusion positioning architecture provided by the embodiment of the present invention. As shown in FIG. 10 , the vehicle-mounted positioning equipment adopts GNSS/IMU combined navigation equipment, and obtains positioning satellite signals through GNSS. According to the real-time dynamic difference (Real -Time Kinematic, RTK) technology, supplemented by the differential signal of the ground reference reference station, to achieve high-precision positioning. Measure the three-axis acceleration and three-axis angular velocity of the electric locomotive itself through INS (Inertial Navigation System, inertial navigation system), and perform dead reckoning to achieve high-precision positioning.

In practical applications, high-precision positioning of electric vehicles can be achieved through the SLAM (Simultaneous Localization and Mapping) technology that performs feature matching on real-time lidar point clouds and pre-stored maps. Based on the regulation and control positioning module (RK3588-B), the positioning data of the three sensors are fused and calculated to achieve higher precision positioning of the electric locomotive. Combined with the acquired environmental perception data, intelligent perception recognition and high-precision fusion positioning are performed on the surrounding environment of the electric locomotive, and the on-board intelligent control is realized through a reliable decision-making control algorithm.

The vehicle-mounted intelligent control system provided by the embodiment of the utility model realizes acquisition of vehicle position information by setting a GNSS/IMU combined navigation device, realizes high-precision positioning, and provides data support for intelligent driving.

The utility model also provides an intelligent driving vehicle, which is equipped with the vehicle-mounted intelligent control system.

Its specific implementation is consistent with the control method described above, and will not be repeated here.

In the vehicle-mounted intelligent computing device provided by the embodiment of the utility model, three computing modules with different functions, namely, an AI computing module, a fusion computing module and a regulatory positioning module, are designed in the vehicle-mounted intelligent computing device. The data required for calculation is delivered to different computing modules for processing, which effectively reduces the demand for computing power of a single module, reduces hardware costs, and adopts the method of dividing the overall computing task into multiple sub-tasks at the same time by different computing modules The processing method can effectively improve the computing efficiency of intelligent driving.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present utility model, and are not intended to limit it; although the utility model has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions recorded in the foregoing embodiments, or to perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit of the technical solutions of the various embodiments of the present utility model. and range.

Claims (10)

1. An in-vehicle intelligent computing device, comprising: the system comprises an external interface module, an AI calculation module, a fusion calculation module and a regulation positioning module;

wherein the external interface module comprises a plurality of interfaces;

the fusion calculation module is connected with the vehicle-mounted sensor equipment through a first interface;

the gauge control positioning module is connected with the vehicle-mounted positioning equipment and the vehicle control unit through a second interface;

and the fusion calculation module is respectively connected with the AI calculation module and the regulation positioning module.

2. The in-vehicle intelligent computing device of claim 1, further comprising: a redundancy calculation module;

and the redundancy calculation module is respectively connected with the AI calculation module and the regulation positioning module.

3. The in-vehicle intelligent computing device of claim 1, further comprising: a monitoring management module;

and the monitoring management module is respectively connected with the external interface module, the AI calculation module, the fusion calculation module and the regulation positioning module.

4. The vehicle-mounted intelligent computing device of claim 1, wherein the external interface module comprises: at least one of LVDS interface, ETH interface, CAN bus interface, UART interface, DI interface and AI interface.

5. The vehicle-mounted intelligent computing device of any of claims 1-4, wherein the AI computing module employs an AI chip;

and the fusion calculation module and the regulation positioning module adopt RK3588 chips.

6. The vehicle-mounted intelligent computing device of claim 3, wherein the monitoring management module employs a TC397 chip.

7. An on-board intelligent control system comprising the on-board intelligent computing device of any one of claims 1-6, the on-board sensor device, the on-board positioning device, and the vehicle control unit.

8. The vehicle-mounted intelligent control system of claim 7, wherein the vehicle-mounted sensor apparatus comprises: at least one of a camera, a laser radar sensor and a millimeter wave radar sensor.

9. The vehicle-mounted intelligent control system of claim 7, wherein the vehicle-mounted positioning device employs a GNSS/IMU integrated navigation device.

10. An intelligent drive vehicle, characterized in that it is equipped with an on-board intelligent control system according to any one of claims 7-9.

Images