CN113815533A - Forward ADAS and automatic parking fusion controller - Google Patents
Forward ADAS and automatic parking fusion controller Download PDFInfo
- Publication number
- CN113815533A CN113815533A CN202010566469.7A CN202010566469A CN113815533A CN 113815533 A CN113815533 A CN 113815533A CN 202010566469 A CN202010566469 A CN 202010566469A CN 113815533 A CN113815533 A CN 113815533A
- Authority
- CN
- China
- Prior art keywords
- image processing
- vpu
- processing unit
- mcu microprocessor
- fusion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 29
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 title claims abstract description 10
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 title claims abstract description 10
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 title claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 66
- 230000006870 function Effects 0.000 claims abstract description 20
- 238000004891 communication Methods 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000012546 transfer Methods 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 description 10
- 230000008447 perception Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/806—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for aiding parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/408—Radar; Laser, e.g. lidar
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a forward ADAS and automatic parking integrated controller, which comprises an ECU embedded electronic controller, wherein the ECU embedded electronic controller consists of an MCU microprocessor and a VPU image processing unit, the MCU microprocessor and the VPU image processing unit are in communication connection through an SPI communication protocol, sensor data are fused and distributed to the VPU image processing unit for carrying out, meanwhile, the sensor data are returned through a redefined SPI communication protocol, and the fused data are returned to the MCU microprocessor for decision control. And the graphics processing cores and the hardware accelerators in the VPU image processing unit are redistributed, and the two graphics processing cores are distributed to two core functional blocks of sensor data fusion and target selection for operation. The redefined system architecture transfers the sensor data fusion part work originally executed by the MCU to the VPU for processing, thereby liberating the computing power of the MCU to realize the track computation and control functions of parking control and greatly reducing the cost.
Description
Technical Field
The invention relates to the technical field of intelligent driving assistance of automobiles by an electronic information technology, in particular to a forward ADAS and an automatic parking fusion controller which are applied to an intelligent driving assistance system of an automobile to assist a driver in vehicle control and driving.
Background
The advanced driving assistance system utilizes various sensors or sensing systems arranged on a vehicle to collect environmental data inside and outside the vehicle at the first time and carries out technical processing such as identification, detection and tracking of static and dynamic objects, so that the vehicle can detect the danger possibly occurring at the fastest time, and a driver is reminded or even intervenes in vehicle control to avoid the danger. The automatic parking system is a comfortable and safe system which utilizes a sensing system of equipment around the vehicle, such as an ultrasonic radar or a look-around camera to identify the surrounding environment, the dynamic object and the static object of the vehicle, so as to extract the coordinate information of the available parking space around the vehicle, and control the speed and the steering of the vehicle by combining the obstacle information which possibly appears on the path through path planning according to the current coordinate position of the vehicle, thereby leading the vehicle to park in the target parking space.
The advanced driving auxiliary system (forward) is controlled by a single domain controller in real time, the automatic parking system is controlled by another single controller, the cost of the whole vehicle factory is high, the research and development cost is high, the selection and installation cost of terminal customers is high, the hardware platform and the development resource system of the two systems cannot be communicated with each other at present, the advanced driving auxiliary system and the automatic parking system can be divided into three main functions of perception, decision and control, the development of the advanced driving auxiliary system depends on integrated visual suppliers in the perception field, such as visual perception chip providers of anaglyph (Mobiley), horizon and the like, and the perception fusion function is integrated into another embedded control MCU for being carried out, because the fusion algorithm requires higher computing resources, the computing capacity of the mainstream embedded MCU occupies more, after the single MCU platform finishes perception fusion calculation, redundant calculation force only can support the final decision and control part of the vehicle, and ultrasonic radar information fusion and vehicle control required by the automatic parking system are not high in calculation force requirement, but cannot be realized on the same MCU, and still need a new MCU platform to realize, so that two hardware platforms and a large amount of bottom layer development work are caused; the cost is high, the development cost is increased, and the whole car factory needs to invest more single-piece cost, research and development cost and extra engineering resources to develop two sets of systems.
Disclosure of Invention
Technical problem to be solved
The invention aims to provide a forward ADAS and automatic parking fusion controller, a redefined system architecture and aims to transfer the sensor data fusion part work originally executed by an MCU into a VPU for processing, thereby liberating the computing power of the MCU for realizing the track calculation and control functions of parking control, realizing two functions of intelligent driving assistance and full-automatic parking on one embedded controller and greatly reducing the cost.
(II) technical scheme
In order to achieve the purpose, the invention provides the following technical scheme: the forward ADAS and automatic parking integrated controller comprises an ECU embedded electronic controller, wherein the ECU embedded electronic controller consists of an MCU microprocessor and a VPU image processing unit, the MCU microprocessor and the VPU image processing unit are in communication connection through an SPI communication protocol, sensor data are fused and distributed to the VPU image processing unit for conducting, meanwhile, the sensor data are returned through a redefined SPI communication protocol, and the fused data are returned to the MCU microprocessor for conducting decision control.
As a further improvement of the invention, the graphics processing core and the hardware accelerator in the VPU image processing unit are redistributed, and the two graphics processing cores are distributed to two core functional blocks of sensor data fusion and target selection for operation.
(III) advantageous effects
Compared with the prior art, after the technical scheme is adopted, the invention has the beneficial effects that:
1. the invention transplants the sensor data fusion to the image processing unit instead of the traditional way on the embedded microcontroller, realizes the forward intelligent driving auxiliary function and the full-automatic parking function on one ECU embedded electronic controller, judges the current vehicle motion state through the signal provided by the whole vehicle electronic framework, and schedules the awakening and activation of the forward and parking functions.
2. The invention successfully integrates the two systems into the same ECU embedded electronic controller, realizes the functions of the two systems by using the cost of a single system, can save the part cost of about 200 plus 300 RMB for a single vehicle, is calculated by the sales number of 20-30 ten thousand in the whole life cycle of a half passenger vehicle, can save the cost of more than 5000 ten thousand RMB for whole vehicle enterprises and the development cost of more than 500 ten thousand of each vehicle type, and creates more values for vehicle factory customers and terminal consumers.
Drawings
FIG. 1 is a system architecture diagram of an embodiment provided by the present invention;
FIG. 2 is a functional block diagram of an embodiment provided by the present invention;
FIG. 3 is a flow chart of the operation of an embodiment provided by the present invention;
FIG. 4 is a diagram of an example of image processing by a VPU image processing unit in an embodiment provided by the present invention;
description of reference numerals:
1. an ECU embedded electronic controller; 2. an MCU microprocessor; 3. a VPU image processing unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-4, an embodiment of the present invention is shown: the forward ADAS and automatic parking fusion controller comprises an ECU embedded electronic controller 1, an MCU microprocessor 2 and a VPU image processing unit 3, wherein the ECU embedded electronic controller 1 consists of the MCU microprocessor 2 and the VPU image processing unit 3, the MCU microprocessor 2 and the VPU image processing unit 3 are in communication connection through an SPI (serial peripheral interface) communication protocol, sensor data are fused and distributed to the VPU image processing unit 3 to be processed, meanwhile, the sensor data are returned through a redefined SPI communication protocol, the fused data are returned to the MCU microprocessor 2 to be subjected to decision control, a graphic processing core and a hardware accelerator inside the VPU image processing unit 3 are redistributed, and the two graphic processing cores are distributed to two core function blocks, namely sensor data fusion and target selection, for operation. Referring to fig. 4, the image processing algorithm inside the VPU image processing unit 3 is optimized, thereby releasing the computational power of the image processing core for the sensor data fusion and target selection computation functions.
Referring to fig. 2-3, the working principle and process of the present embodiment are as follows:
1. by redefining the system architecture, the communication protocol and the function distribution, the sensor data fusion part originally executed by the MCU microprocessor 2 is transferred to the VPU image processing unit 3 for processing, and the data transmission protocol between the MCU microprocessor 2 and the VPU image processing unit 3 is redefined, so that the MCU microprocessor 2 transmits the millimeter wave radar or ultrasonic radar data to the VPU image processing unit 3;
2. inside the VPU image processing unit 3, image identification data processed by the other 6 image processing cores and radar data transmitted from the MCU microprocessor 2 are fused through two processor cores in 8 image processing cores of the VPU image processing unit 3, and finally target data after fusion is returned to the MCU microprocessor 2 for decision control, so that sensor fusion work originally processed by the MCU microprocessor 2 is successfully transferred to the VPU image processing unit 3 to be carried out, the calculation power of the MCU microprocessor 2, which is close to 500DMIPS, is released, the calculation power is successfully used for processing track calculation and control of full-automatic parking, and meanwhile, two sets of system functions of forward intelligent driving assistance and full-automatic parking are successfully realized in the ECU embedded electronic controller 1.
In this embodiment, to implement the core release of the VPU image processing unit 3, a visual processing chip needs to be customized by a co-operator with the visual processing chip, the image processing efficiency of a hardware accelerator is optimized, redundant visual processing loads in a visual processing algorithm are removed by a large amount of accumulated intelligent driving scene data according to the actual environment in china, meanwhile, traffic participants perform algorithm optimization according to the road route in china, so as to improve the visual processing efficiency, part of the calculation power of the calculation core optimized in the visual processing chip is released, then, by the above method, the perception fusion function occupying a large amount of calculation resources of the main control MCU microprocessor 2 is transplanted to the visual processing chip, and an information interaction database between the visual processing chip and the MCU microprocessor 2 is newly customized, and the received main control radar signal is transmitted to the visual processing chip, after the perception fusion is completed, the fused target object information is fed back to the main control MCU microprocessor 2 for decision and control, and a data communication framework between the two chips is reestablished, so that the calculation load of the main control MCU microprocessor 2 is greatly reduced, the part of calculation resources are used for the track calculation and control functions of automatic parking, comprehensive judgment is carried out through interaction with the whole vehicle electronic framework through the whole vehicle energy mode and the current use state, the required fusion information is output to the decision and control function module for vehicle control, and the technical innovation of two function integration is realized.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (3)
1. The forward ADAS and automatic parking fusion controller comprises an ECU embedded electronic controller, and is characterized in that the ECU embedded electronic controller consists of an MCU microprocessor and a VPU image processing unit, the MCU microprocessor and the VPU image processing unit are in communication connection through an SPI communication protocol, sensor data are fused and distributed to the VPU image processing unit for carrying out, meanwhile, the sensor data are returned through a redefined SPI communication protocol, and the fused data are returned to the MCU microprocessor for decision control.
2. The forward ADAS and auto park fusion controller of claim 1, wherein the VPU image processing unit is configured to redistribute the graphics processing cores and the hardware accelerators, and assign the two graphics processing cores to the two core function blocks for sensor data fusion and target selection.
3. The forward ADAS and automated parking fusion controller of claim 1, wherein the workflow is:
by redefining a system architecture, a communication protocol and function distribution, transferring the sensor data fusion part originally executed by the MCU into the VPU image processing unit for processing, and redefining a data transmission protocol between the MCU microprocessor and the VPU image processing unit, so that the MCU microprocessor transmits millimeter wave radar or ultrasonic radar data to the VPU image processing unit;
in the VPU image processing unit, image recognition data processed by the other 6 image processing cores and radar data transmitted from the MCU microprocessor are fused through two processor cores in 8 image processing cores of the VPU image processing unit, and finally target data after fusion is returned to the MCU microprocessor for decision control, so that sensor fusion work originally processed by the MCU microprocessor is successfully transferred to the VPU image processing unit to be carried out, the calculation power of the MCU microprocessor is released, the calculation power is successfully used for processing track calculation and control of full-automatic parking, and meanwhile, two sets of system functions of forward intelligent driving assistance and full-automatic parking are realized in the ECU embedded electronic controller.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010566469.7A CN113815533B (en) | 2020-06-19 | 2020-06-19 | Forward ADAS and automatic parking fusion controller |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010566469.7A CN113815533B (en) | 2020-06-19 | 2020-06-19 | Forward ADAS and automatic parking fusion controller |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113815533A true CN113815533A (en) | 2021-12-21 |
CN113815533B CN113815533B (en) | 2023-04-07 |
Family
ID=78911620
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010566469.7A Active CN113815533B (en) | 2020-06-19 | 2020-06-19 | Forward ADAS and automatic parking fusion controller |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113815533B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114609953A (en) * | 2022-04-13 | 2022-06-10 | 中国第一汽车股份有限公司 | Fuse vehicle control ware system and vehicle |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104853972A (en) * | 2012-11-16 | 2015-08-19 | 英特尔公司 | Augmenting ADAS features of vehicle with image processing support in on-board vehicle platform |
US20170021839A1 (en) * | 2015-03-02 | 2017-01-26 | Surya Kiran Satyavolu | Methods and systems of algorithmically controlling automotive functions |
CN106740630A (en) * | 2016-12-06 | 2017-05-31 | 惠州市德赛西威汽车电子股份有限公司 | Automobile external active safety airbag control system and method based on ADAS and IVI |
CN107958224A (en) * | 2017-12-14 | 2018-04-24 | 智车优行科技(北京)有限公司 | The upper image preprocessing system and methods based on ISP of ADAS |
CN110568852A (en) * | 2019-10-12 | 2019-12-13 | 深圳市布谷鸟科技有限公司 | Automatic driving system and control method thereof |
-
2020
- 2020-06-19 CN CN202010566469.7A patent/CN113815533B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104853972A (en) * | 2012-11-16 | 2015-08-19 | 英特尔公司 | Augmenting ADAS features of vehicle with image processing support in on-board vehicle platform |
US20170021839A1 (en) * | 2015-03-02 | 2017-01-26 | Surya Kiran Satyavolu | Methods and systems of algorithmically controlling automotive functions |
CN106740630A (en) * | 2016-12-06 | 2017-05-31 | 惠州市德赛西威汽车电子股份有限公司 | Automobile external active safety airbag control system and method based on ADAS and IVI |
CN107958224A (en) * | 2017-12-14 | 2018-04-24 | 智车优行科技(北京)有限公司 | The upper image preprocessing system and methods based on ISP of ADAS |
CN110568852A (en) * | 2019-10-12 | 2019-12-13 | 深圳市布谷鸟科技有限公司 | Automatic driving system and control method thereof |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114609953A (en) * | 2022-04-13 | 2022-06-10 | 中国第一汽车股份有限公司 | Fuse vehicle control ware system and vehicle |
CN114609953B (en) * | 2022-04-13 | 2024-03-26 | 中国第一汽车股份有限公司 | Fusion vehicle control controller system and vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN113815533B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107614349B (en) | Controller of vehicle and control method for vehicle | |
CN108170126B (en) | Control system and automobile | |
CN110568852A (en) | Automatic driving system and control method thereof | |
CN110519703A (en) | A kind of mine car Unmanned Systems | |
US10197412B2 (en) | Electric vehicle charging | |
CN113479195A (en) | Method for automatic valet parking and system for carrying out said method | |
JP2019137185A (en) | Vehicle control system, vehicle control method, and program | |
US20200271456A1 (en) | Method for the generation of a merged free-space map, electronic control device and storage medium | |
CN115116257A (en) | Vehicle scheduling method, device, equipment and medium based on edge cloud service | |
CN113815533B (en) | Forward ADAS and automatic parking fusion controller | |
Elshaer et al. | Autonomous car implementation based on CAN bus protocol for IoT applications | |
CN111752273A (en) | Unmanned walking system and method for electric crawler excavator | |
CN115691183A (en) | Vehicle-road cooperative driving method and system based on end edge cloud cooperative computing | |
CN115344939A (en) | Automatic driving virtual test system based on human, vehicle and environment modeling | |
CN103021187B (en) | A kind of car alarming method and car-mounted terminal based on car networking technology | |
CN112677996A (en) | Vehicle driving system and vehicle | |
CN113665577A (en) | Method for operating a motor vehicle | |
WO2020250519A1 (en) | Outside environment recognition device | |
CN114827954A (en) | Vehicle energy-saving method | |
CN115314526A (en) | System architecture, transmission method, vehicle, medium and chip for self-parking position identification | |
CN112861771A (en) | ADAS domain control method based on S32K series chips | |
US11987266B2 (en) | Distributed processing of vehicle sensor data | |
CN108549380A (en) | A kind of servomechanism based on Beidou navigation technology | |
CN110667599A (en) | Control device, control unit, control method, and storage medium | |
CN205801097U (en) | A kind of automobile automatic backing system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20221115 Address after: Building 20, Lane 1000, Zhangheng Road, Pudong New Area, Shanghai 200000 Applicant after: MOTOVIS TECHNOLOGY (SHANGHAI) CO.,LTD. Address before: Room 7092, dinglou, 555 Dongchuan Road, Minhang District, Shanghai 200241 Applicant before: SHANGHAI NETCAR TECH LTD. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |