CN115857473A - Intelligent driving and ADAS simulation test method and system based on satellite positioning - Google Patents
Intelligent driving and ADAS simulation test method and system based on satellite positioning Download PDFInfo
- Publication number
- CN115857473A CN115857473A CN202211658785.2A CN202211658785A CN115857473A CN 115857473 A CN115857473 A CN 115857473A CN 202211658785 A CN202211658785 A CN 202211658785A CN 115857473 A CN115857473 A CN 115857473A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- test
- module
- group
- 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.)
- Withdrawn
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 33
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 title claims abstract description 24
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 title claims abstract description 24
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 title claims abstract description 24
- 238000010998 test method Methods 0.000 title claims abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 79
- 230000033001 locomotion Effects 0.000 claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000005457 optimization Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 14
- 230000006835 compression Effects 0.000 claims description 12
- 238000007906 compression Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 230000007774 longterm Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent driving and ADAS simulation test method and system based on satellite positioning, belonging to the technical field of intelligent driving, wherein the test method comprises the following specific steps: (1) Collecting scene information and carrying out positioning simulation on a test vehicle; (2) Collecting vehicle state information and controlling the vehicle to carry out simulated driving; (3) carrying out cascade analysis and adjustment on the vehicle running path; (4) Receiving the running state of the vehicle in real time and carrying out anomaly analysis; the method and the device can improve the detection accuracy of the fault, predict the motion state of the fault and generate a plurality of groups of standby schemes, improve the safety of the vehicle in the driving process, compress the memory with large granularity, ensure the stability of data transmission efficiency when the cloud server is connected with excessive devices, and improve the use experience.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to an intelligent driving and ADAS simulation test method and system based on satellite positioning.
Background
The intelligent driving essentially relates to cognitive engineering of attention attraction and distraction, and mainly comprises three links of network navigation, autonomous driving and manual intervention. The precondition of intelligent driving is that the selected vehicle meets the dynamic requirements of driving, the sensor on the vehicle can obtain relevant visual and auditory signals and information, and the corresponding follow-up system is controlled through cognitive calculation, the intelligent driving is an important hand for combining industrial revolution and informatization, the rapid development changes the flowing mode of people, resource elements and products, and the human life is subversively changed.
Through retrieval, chinese patent No. CN114488855A discloses an intelligent driving and ADAS simulation test method and system based on satellite positioning, and the invention greatly improves the positioning accuracy of ADAS and intelligent driving test. The test vehicle decision system can carry out testing based on complete simulation working conditions, and generates positioning simulation according to the scene of the existing test site, so that the positioning simulation cost is reduced, the flexibility is higher, but the detection accuracy of a fault object is poor, and the safety of the vehicle test process is low; in addition, the existing intelligent driving and ADAS simulation test method and system based on satellite positioning have the disadvantages that the stability of data transmission efficiency is reduced and the use experience is poor when the cloud server is connected with excessive equipment; therefore, an intelligent driving and ADAS simulation test method and system based on satellite positioning are provided.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an intelligent driving and ADAS simulation test method and system based on satellite positioning.
In order to achieve the purpose, the invention adopts the following technical scheme:
the intelligent driving and ADAS simulation test method based on satellite positioning comprises the following specific steps:
(1) Collecting scene information and carrying out positioning simulation on a test vehicle;
(2) Collecting vehicle state information and controlling the vehicle to carry out simulated driving;
(3) Carrying out cascade analysis and adjustment on the vehicle running path;
(4) And receiving the running state of the vehicle in real time and carrying out abnormity analysis.
The method is characterized in that the positioning simulation in the step (1) comprises the following specific steps:
the method comprises the following steps: the information acquisition module collects image information of a test site and performs image segmentation on the acquired image information according to a display scale;
step two: converting each group of image information into a frequency space through Fourier forward transformation, analyzing and extracting high-frequency components in the image information, filtering the image information to reduce noise, and converting the image information into an image space through Fourier inverse transformation;
step three: and constructing a corresponding three-dimensional scene model according to the optimized image information, carrying out coordinate system processing on the three-dimensional scene model, then collecting the position information of the test vehicle positioned by the satellite, and matching the position coordinates of the vehicle with the corresponding position coordinates in the three-dimensional scene model to complete positioning.
The method is characterized in that the step (2) of simulating the running specifically comprises the following steps:
step I: the method comprises the following steps that a researcher sets a starting point and an end point of the test vehicle through a computer, and then a terminal control module receives a starting point position and an end point position input by a worker and controls the test vehicle to run to the starting point position;
step II: and the positioning satellite acquires the position of the test vehicle in real time, synchronizes the position of the test vehicle with the position coordinates of the vehicle in the three-dimensional scene model, marks the position of a terminal in the three-dimensional scene model and plans a running route, and after the route planning is finished, the terminal control module controls the test vehicle to run according to the specified route.
The method is characterized in that the cascade analysis in the step (3) comprises the following specific steps:
step (1): the analysis module receives image information acquired by the camera and carries out frame-by-frame processing, extracts features in each frame of image through a primary detection network, then sends the features into a bidirectional feature pyramid for feature fusion, carries out classification regression on the fusion result, and outputs a detection frame and a category;
step (2): the first-level detection network collects the detection frame information in each image, generates corresponding detection frame coordinates, performs expanded cutting on the related images, collects each group of images generated after the expanded cutting, and stores the images;
and (3): the secondary target detection network filters simple negative samples belonging to the background in each group of pictures through RPN, selects areas possibly containing obstacles for classification and regression, generates nine anchor frames on each point of the pictures with high and low semantic information, classifies and regresses the anchor frames, and detects the positions of the obstacles in each group of pictures through enlarged cutting;
and (4): calculating the interval time of the actual video frames, recording the calculated time, establishing a motion model through a Kalman filtering theory, and simultaneously acquiring the motion state of the obstacle in real time through the established motion model;
and (5): allocating one ID to all the obstacles, acquiring appearance characteristic vectors of all the tracked targets after allocation is finished, defining the motion state of the tracked targets in a video frame by a motion model according to the linear motion hypothesis of the tracked targets, then collecting the motion state of the obstacles in the current video frame, and constructing a prediction equation to estimate the motion state of each tracked target in the next video frame;
and (6): and setting a plurality of groups of standby running schemes for the test vehicle according to the estimated motion state, if the barrier has a moving condition, selecting the corresponding standby running scheme to replace the original scheme, and simultaneously feeding back the position coordinates of the test vehicle to researchers in real time.
The method is characterized in that the abnormality analysis in the step (4) comprises the following specific steps:
s1: the anomaly detection module constructs an analysis neural network, leads each group of data generated in the running process of the test vehicle into the analysis neural network, processes each group of data into a uniform format, and extracts characteristic parameters by a time domain and frequency domain method;
s2: screening out characteristic parameters capable of expressing the running information of the tested vehicle, screening out the characteristic parameters with poor representation capability, then carrying out normalization processing on each group of data, dividing the processed each group of data into a training set and a testing set, and carrying out standardization processing on the training set to generate a training sample;
s3: and (3) conveying the training samples to an analytical neural network, setting specific parameters of the model, training the analytical neural network by adopting a long-term iteration method, inputting the test set into the trained analytical neural network, drawing a test vehicle state curve, and labeling and feeding back abnormal points.
The intelligent driving and ADAS simulation test system based on satellite positioning comprises an information acquisition module, a positioning module, a virtual synchronization module, a terminal control module, a state acquisition module, an analysis module, an abnormality detection module, a hub motor, a user side, a cloud server and a performance optimization module;
the information acquisition module is used for acquiring test site information;
the positioning module is used for collecting the position information of the test vehicle and the starting point and the end point information uploaded by a researcher;
the virtual synchronization module is used for receiving test site information, constructing a three-dimensional site model, coordinating the three-dimensional site model and synchronizing the position of a test vehicle into the three-dimensional site model;
the state acquisition module is used for acquiring the state information of the test vehicle in real time;
the analysis module is used for carrying out motion estimation on obstacles in front of and behind the vehicle and generating a plurality of groups of standby driving schemes;
the abnormality detection module is used for receiving the state information of the tested vehicle and carrying out abnormality analysis on the state information;
the hub motor is used for testing the movement and turning of the vehicle;
the user side is used for researchers to issue related control instructions and check related vehicle driving data;
the cloud server is used for receiving and storing each group of test data;
the performance optimization module is used for optimizing the connection performance between the cloud server and the user side.
The method is characterized in that the performance optimization module specifically comprises the following steps:
p1: the cloud server is in communication connection with each group of user sides, and the performance optimization module generates a start linked list for each connected user side and sorts the start linked lists in sequence from small to large according to the access times;
p2: before the user side starts, the performance optimization module clears the access bits of all the updated page table entries, records the information accessed by each group of user sides in the starting process, and updates the data of each group of pages in the corresponding starting linked list;
p3: selecting the least active user side from the head of the LRU linked list in sequence, selecting the victim pages from the corresponding start linked list in sequence until enough victim pages are recovered, stopping collecting, combining the selected victim pages into a block and marking;
p4: analyzing the marked block, obtaining a physical page belonging to the block, copying the physical page into a buffer area, calling a compression algorithm to compress the physical page in the buffer area into a compression block, and storing the compression block into a performance optimization module.
Compared with the prior art, the invention has the beneficial effects that:
1. the intelligent driving and ADAS simulation test method based on satellite positioning is compared with the traditional test method, the image information acquired by a camera is received by an analysis module and is processed frame by frame, the positions of obstacles in each group of pictures are detected by a cascade network, the interval time of actual video frames is calculated and the calculated time is recorded, a motion model is established by Kalman filtering theory, the motion state of the obstacles is acquired in real time by the established motion model, then the motion state of the obstacles in the video frames is defined by the motion model according to the linear motion assumption of a tracked target, then the motion state of the obstacles in the current video frames is collected, a prediction equation is established to estimate the motion state of each tracked target in the next video frame, a plurality of groups of standby running schemes are set for a test vehicle according to the estimated motion state, if the obstacles move, the corresponding standby running schemes are selected to replace the original schemes, meanwhile, the position coordinates of the test vehicle are fed back to researchers in real time, the detection accuracy of the obstacles can be improved, meanwhile, the motion state of the obstacles can be predicted and a plurality of groups of standby running schemes can be generated, and the safety of the vehicles in the running process can be improved;
2. the intelligent driving and ADAS simulation test system based on satellite positioning is provided with a performance optimization module, when a cloud server is in communication connection with each group of user terminals, the performance optimization module generates a starting linked list for each connected user terminal, sequences the user terminals in sequence from small to large according to the number of access times, before the user terminals are started, clears access bits of all updated page table entries, records information accessed by each group of user terminals in the starting process, updates data of each group of pages in the corresponding starting linked list, sequentially selects the most inactive user terminal from the head of an LRU linked list, sequentially selects victim pages from the corresponding starting linked list until enough victim pages are recovered, stops collecting, combines the selected victim pages into a block and marks the block, analyzes the marked block to obtain the physical pages of the block, copies the physical pages into a buffer area, then calls a compression algorithm to compress the physical pages in the buffer area into a compression block, and stores the compression block into the performance optimization module, can compress the stored data with large granularity, ensures that the cloud server is connected with excessive data, and improves the experience of the cloud server.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Fig. 1 is a block diagram of a flow chart of an intelligent driving and ADAS simulation test method based on satellite positioning according to the present invention;
fig. 2 is a system block diagram of an intelligent driving and ADAS simulation test system based on satellite positioning according to the present invention.
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.
Example 1
Referring to fig. 1, the embodiment discloses an intelligent driving and ADAS simulation test method based on satellite positioning, which includes the following specific steps:
and acquiring scene information and performing positioning simulation on the test vehicle.
Specifically, the information acquisition module collects image information of a test site, image segmentation is carried out on the collected image information according to a display scale, each group of image information is converted into a frequency space through Fourier forward transformation, high-frequency components in the frequency space are analyzed and extracted, then filtering processing is carried out on the image information to reduce noise, the image information is converted into an image space through Fourier inverse transformation, a corresponding three-dimensional scene model is built according to the optimized image information and is processed through a coordinate system, then test vehicle position information of satellite positioning is collected, and then vehicle position coordinates are matched with corresponding position coordinates in the three-dimensional scene model to complete positioning.
And collecting vehicle state information and controlling the vehicle to perform simulated driving.
Specifically, a researcher sets a running starting point and a running end point of the test vehicle through a computer, then a terminal control module receives a starting point position and a running end point position input by a worker and controls the test vehicle to run to the starting point position, then a positioning satellite collects the position of the test vehicle in real time and synchronizes the position with a vehicle position coordinate in a three-dimensional scene model, then the terminal position is marked in the three-dimensional scene model and a running route is planned, and after the route planning is finished, the terminal control module controls the test vehicle to run according to the specified route.
And carrying out cascade analysis and adjustment on the vehicle running path.
Specifically, an analysis module receives image information collected by a camera and carries out frame-by-frame processing, the characteristics in each frame of image are extracted through a primary detection network, then the images are sent into a bidirectional characteristic pyramid for characteristic fusion, the fusion result is classified and regressed, detection frames and categories are output, then the primary detection network collects the detection frame information in each image and generates corresponding detection frame coordinates, related images are subjected to expanded cutting, each group of images generated after the expanded cutting are collected and stored, then a secondary target detection network filters out simple negative samples belonging to the background in each group of images through RPN, regions possibly containing obstacles are selected for classification and regression, nine anchor frames are generated at each point of the images with high or low semantic information and are classified and regressed, detecting the position of an obstacle in each group of pictures through enlarged clipping, calculating the interval time of actual video frames and recording the calculated time, establishing a motion model through a Kalman filtering theory, simultaneously acquiring the motion state of the obstacle in real time through the established motion model, allocating an ID (identity) to all obstacles, acquiring the appearance characteristic vectors of all tracked targets after the allocation is finished, defining the motion state of the tracked targets in the video frames according to the linear motion assumption of the tracked targets by the motion model, then collecting the motion state of the obstacle in the current video frame, establishing a prediction equation to estimate the motion state of each tracked target in the next video frame, setting a plurality of groups of standby driving schemes for a test vehicle according to the estimated motion state, and selecting the corresponding standby driving scheme to replace the original scheme if the obstacle has a moving condition, and simultaneously, feeding back the position coordinates of the test vehicle to researchers in real time.
And receiving the running state of the vehicle in real time and carrying out abnormity analysis.
Specifically, the anomaly detection module constructs an analytical neural network, leads each group of data generated in the running process of a test vehicle into the analytical neural network, processes each group of data into a uniform format, extracts characteristic parameters by a time domain and frequency domain method, screens out characteristic parameters capable of expressing the running information of the test vehicle, screens out characteristic parameters with poor characterization capability, normalizes each group of data, divides each group of processed data into a training set and a test set, standardizes the training set to generate a training sample, conveys the training sample to the analytical neural network, sets specific parameters of a model, trains the analytical neural network by a long-term iteration method, inputs the test set into the trained analytical neural network, draws a state curve of the test vehicle, and marks and feeds back abnormal points.
Example 2
Referring to fig. 2, the embodiment discloses an intelligent driving and ADAS simulation test system based on satellite positioning, which includes an information acquisition module, a positioning module, a virtual synchronization module, a terminal control module, a state acquisition module, an analysis module, an anomaly detection module, a hub motor, a user side, a cloud server, and a performance optimization module.
The information acquisition module is used for acquiring test site information; the positioning module is used for collecting the position information of the test vehicle and the starting point and the end point information uploaded by a researcher; the virtual synchronization module is used for receiving the test site information, constructing a three-dimensional site model, coordinating the three-dimensional site model and synchronizing the position of the test vehicle into the three-dimensional site model; the state acquisition module is used for acquiring the state information of the test vehicle in real time.
The analysis module is used for carrying out motion estimation on obstacles in front of and behind the vehicle and generating a plurality of groups of standby driving schemes; the abnormality detection module is used for receiving the state information of the tested vehicle and carrying out abnormality analysis on the state information; the hub motor is used for testing the movement and turning of the vehicle; the client is used for the researchers to issue related control instructions and check related vehicle driving data; the cloud server is used for receiving and storing each group of test data; the performance optimization module is used for optimizing the connection performance of the cloud server and the user side.
Specifically, the cloud server is in communication connection with each group of user sides, the performance optimization module generates a starting linked list for each connected user side, the starting linked lists are sequentially sorted from small to large according to the access times, before the user sides are started, the performance optimization module clears access bits of all updated page table entries, records information accessed by each group of user sides in the starting process, updates data of each group of pages in the corresponding starting linked list, sequentially selects the least active user side from the head of the LRU linked list, sequentially selects victim pages from the corresponding starting linked list until enough victim pages are recovered, stops collecting, combines the selected victim pages into one block and marks the block, analyzes the marked block, obtains physical pages belonging to the block, copies the physical pages into the buffer area, calls a compression algorithm to compress the physical pages in the buffer area into the compression block, and stores the compression block into the performance optimization module.
Claims (7)
1. The intelligent driving and ADAS simulation test method based on satellite positioning is characterized by comprising the following specific steps:
(1) Collecting scene information and carrying out positioning simulation on a test vehicle;
(2) Collecting vehicle state information and controlling the vehicle to carry out simulated driving;
(3) Carrying out cascade analysis and adjustment on the vehicle running path;
(4) And receiving the running state of the vehicle in real time and carrying out abnormity analysis.
2. The intelligent driving and ADAS simulation testing method based on satellite positioning as claimed in claim 1, wherein the positioning simulation of step (1) specifically comprises the following steps:
the method comprises the following steps: the information acquisition module collects image information of a test site and performs image segmentation on the acquired image information according to a display scale;
step two: converting each group of image information into a frequency space through Fourier forward transformation, analyzing and extracting high-frequency components in the image information, filtering the image information to reduce noise, and converting the image information into an image space through Fourier inverse transformation;
step three: and constructing a corresponding three-dimensional scene model according to the optimized image information, carrying out coordinate system processing on the three-dimensional scene model, then collecting the position information of the test vehicle positioned by the satellite, and matching the position coordinates of the vehicle with the corresponding position coordinates in the three-dimensional scene model to complete positioning.
3. The intelligent driving and ADAS simulation test method based on satellite positioning as claimed in claim 2, wherein the simulation driving of step (2) comprises the following specific steps:
step I: the method comprises the following steps that a researcher sets a starting point and an end point of the test vehicle through a computer, and then a terminal control module receives a starting point position and an end point position input by a worker and controls the test vehicle to run to the starting point position;
step II: and the positioning satellite acquires the position of the test vehicle in real time, synchronizes the position of the test vehicle with the position coordinates of the vehicle in the three-dimensional scene model, marks the position of a terminal in the three-dimensional scene model and plans a running route, and after the route planning is finished, the terminal control module controls the test vehicle to run according to the specified route.
4. The intelligent driving and ADAS simulation test method based on satellite positioning according to claim 1, wherein the step (3) of the cascade analysis specifically comprises the following steps:
step (1): the analysis module receives image information acquired by the camera and carries out frame-by-frame processing, extracts features in each frame of image through a primary detection network, then sends the features into a bidirectional feature pyramid for feature fusion, carries out classification regression on the fusion result, and outputs a detection frame and a category;
step (2): the first-level detection network collects the detection frame information in each image, generates corresponding detection frame coordinates, performs expanded cutting on the related images, collects each group of images generated after the expanded cutting, and stores the images;
and (3): the secondary target detection network filters simple negative samples belonging to the background in each group of pictures through RPN, selects areas possibly containing obstacles for classification and regression, generates nine anchor frames on each point of the pictures with high and low semantic information, classifies and regresses the anchor frames, and detects the positions of the obstacles in each group of pictures through enlarged cutting;
and (4): calculating the interval time of the actual video frames, recording the calculated time, establishing a motion model through a Kalman filtering theory, and simultaneously acquiring the motion state of the obstacle in real time through the established motion model;
and (5): allocating one ID to all the obstacles, acquiring appearance characteristic vectors of all the tracked targets after allocation is finished, defining the motion state of the tracked targets in a video frame by a motion model according to the linear motion hypothesis of the tracked targets, then collecting the motion state of the obstacles in the current video frame, and constructing a prediction equation to estimate the motion state of each tracked target in the next video frame;
and (6): and setting a plurality of groups of standby running schemes for the test vehicle according to the estimated motion state, if the barrier has a moving condition, selecting the corresponding standby running scheme to replace the original scheme, and simultaneously feeding back the position coordinates of the test vehicle to researchers in real time.
5. The intelligent driving and ADAS simulation testing method based on satellite positioning as claimed in claim 1, wherein the abnormality analysis of step (4) specifically comprises the following steps:
s1: the anomaly detection module constructs an analysis neural network, leads each group of data generated in the running process of the test vehicle into the analysis neural network, processes each group of data into a uniform format, and extracts characteristic parameters by a time domain and frequency domain method;
s2: screening out characteristic parameters capable of expressing the running information of the tested vehicle, screening out the characteristic parameters with poor representation capability, then carrying out normalization processing on each group of data, dividing the processed each group of data into a training set and a testing set, and carrying out standardization processing on the training set to generate a training sample;
s3: and (3) conveying the training samples to an analytical neural network, setting specific parameters of the model, training the analytical neural network by adopting a long-term iteration method, inputting the test set into the trained analytical neural network, drawing a test vehicle state curve, and labeling and feeding back abnormal points.
6. The intelligent driving and ADAS simulation test system based on satellite positioning is characterized by comprising an information acquisition module, a positioning module, a virtual synchronization module, a terminal control module, a state acquisition module, an analysis module, an abnormality detection module, a hub motor, a user side, a cloud server and a performance optimization module;
the information acquisition module is used for acquiring test site information;
the positioning module is used for collecting the position information of the test vehicle and the starting point and the end point information uploaded by a researcher;
the virtual synchronization module is used for receiving test site information, constructing a three-dimensional site model, coordinating the three-dimensional site model and synchronizing the position of a test vehicle into the three-dimensional site model;
the state acquisition module is used for acquiring the state information of the test vehicle in real time;
the analysis module is used for carrying out motion estimation on obstacles in front of and behind the vehicle and generating a plurality of groups of standby driving schemes;
the abnormality detection module is used for receiving the state information of the tested vehicle and carrying out abnormality analysis on the state information;
the hub motor is used for testing the movement and turning of the vehicle;
the user side is used for researchers to issue related control instructions and check related vehicle driving data;
the cloud server is used for receiving and storing each group of test data;
the performance optimization module is used for optimizing the connection performance between the cloud server and the user side.
7. The intelligent driving and ADAS simulation testing system based on satellite positioning of claim 6, wherein the performance optimization module specifically performs the following steps:
p1: the cloud server is in communication connection with each group of user sides, and the performance optimization module generates a start linked list for each connected user side and sorts the start linked lists in sequence from small to large according to the access times;
p2: before the user side starts, the performance optimization module clears the access bits of all the updated page table entries, records the information accessed by each group of user sides in the starting process, and updates the data of each group of pages in the corresponding starting linked list;
p3: selecting the least active user side from the head of the LRU linked list in sequence, selecting the victim pages from the corresponding start linked list in sequence until enough victim pages are recovered, stopping collecting, combining the selected victim pages into a block and marking;
p4: analyzing the marked block, obtaining a physical page belonging to the block, copying the physical page into a buffer area, calling a compression algorithm to compress the physical page in the buffer area into a compression block, and storing the compression block into a performance optimization module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211658785.2A CN115857473A (en) | 2022-12-22 | 2022-12-22 | Intelligent driving and ADAS simulation test method and system based on satellite positioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211658785.2A CN115857473A (en) | 2022-12-22 | 2022-12-22 | Intelligent driving and ADAS simulation test method and system based on satellite positioning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115857473A true CN115857473A (en) | 2023-03-28 |
Family
ID=85653989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211658785.2A Withdrawn CN115857473A (en) | 2022-12-22 | 2022-12-22 | Intelligent driving and ADAS simulation test method and system based on satellite positioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115857473A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116909260A (en) * | 2023-09-12 | 2023-10-20 | 常州星宇车灯股份有限公司 | Intelligent driving domain controller test verification method for simulating HIL (high-performance liquid chromatography) rack |
-
2022
- 2022-12-22 CN CN202211658785.2A patent/CN115857473A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116909260A (en) * | 2023-09-12 | 2023-10-20 | 常州星宇车灯股份有限公司 | Intelligent driving domain controller test verification method for simulating HIL (high-performance liquid chromatography) rack |
CN116909260B (en) * | 2023-09-12 | 2023-12-01 | 常州星宇车灯股份有限公司 | Intelligent driving domain controller test verification method for simulating HIL (high-performance liquid chromatography) rack |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110147700B (en) | Video classification method, device, storage medium and equipment | |
CN113870260B (en) | Welding defect real-time detection method and system based on high-frequency time sequence data | |
CN108764167B (en) | Space-time correlated target re-identification method and system | |
CN109284729A (en) | Method, apparatus and medium based on video acquisition human face recognition model training data | |
CN111985325B (en) | Aerial small target rapid identification method in extra-high voltage environment evaluation | |
CN103020590B (en) | A kind of vehicle identification system based on three-dimensional model and images match and method thereof | |
CN113284144B (en) | Tunnel detection method and device based on unmanned aerial vehicle | |
CN115857473A (en) | Intelligent driving and ADAS simulation test method and system based on satellite positioning | |
CN109948429A (en) | Image analysis method, device, electronic equipment and computer-readable medium | |
CN116052276A (en) | Human body posture estimation behavior analysis method | |
CN112183412A (en) | Personnel identity identification method and device, electronic equipment and storage medium | |
CN115620393A (en) | Fine-grained pedestrian behavior recognition method and system oriented to automatic driving | |
CN115880529A (en) | Method and system for classifying fine granularity of birds based on attention and decoupling knowledge distillation | |
CN110796090A (en) | Human-computer cooperation human behavior intention judging method based on cyclic neural network | |
CN113569912A (en) | Vehicle identification method and device, electronic equipment and storage medium | |
CN112613425A (en) | Target identification method and system for small sample underwater image | |
CN110728316A (en) | Classroom behavior detection method, system, device and storage medium | |
CN110738208A (en) | efficient scale-normalized target detection training method | |
CN113450321B (en) | Single-stage target detection method based on edge detection | |
CN114882580A (en) | Measuring method for motion action consistency based on deep learning | |
CN115588150A (en) | Pet dog video target detection method and system based on improved YOLOv5-L | |
Afrin et al. | AI based facial expression recognition for autism children | |
CN111178134B (en) | Tumble detection method based on deep learning and network compression | |
CN114005054A (en) | AI intelligence system of grading | |
CN113180701A (en) | Electroencephalogram signal depth learning method for image label labeling |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230328 |