CN106254461A - A kind of intelligent vehicle perception test platform and method of data synchronization thereof - Google Patents
A kind of intelligent vehicle perception test platform and method of data synchronization thereof Download PDFInfo
- Publication number
- CN106254461A CN106254461A CN201610638158.0A CN201610638158A CN106254461A CN 106254461 A CN106254461 A CN 106254461A CN 201610638158 A CN201610638158 A CN 201610638158A CN 106254461 A CN106254461 A CN 106254461A
- Authority
- CN
- China
- Prior art keywords
- data
- test
- queue
- intelligent vehicle
- client
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/08—Protocols specially adapted for terminal emulation, e.g. Telnet
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Small-Scale Networks (AREA)
Abstract
The present invention relates to a kind of intelligent vehicle perception test platform, including: disk, for storing the most acquired complete test data and test result；Server end, is used for providing virtual-sensor, and the data of simulation actual sensor send, and the perception of intelligent vehicle to be measured are made evaluation simultaneously；Network, for the data transmission of server end with client；Client, provides message subscribing, data receiver, digital independent and test result loopback service for intelligent vehicle to be measured.The invention also discloses the method for data synchronization of a kind of intelligent vehicle perception test platform.The test platform that the present invention provides, can get rid of hardware interference, utilizes and gathers complete data and virtual-sensor and carry out the perception of intelligent vehicle to be measured controlled repeatably testing and assessing；The method of data synchronization that the present invention provides can ensure that the data of the simulating realistic sensor of data test platform real-time synchronization send, thus improves the accuracy of test and appraisal.
Description
Technical field
The present invention relates to intelligent vehicle perception evaluation technology field, especially a kind of intelligent vehicle perception test
Platform and method of data synchronization thereof.
Background technology
In the last few years, intelligent vehicle was studied widely as a focus of artificial intelligence.Intelligent vehicle is to merge
The complication system of numerous key technologies such as environment sensing, decision rule, motor control, platform execution.And as other technology
Basis, in environment sensing ability, domestic and international academic organisations and industrial undertaking have also been made substantial amounts of research, but in test evaluation
In the environment sensing ability of intelligent vehicle, the method that still neither one is generally accepted by industry.At present, each producer and scientific research
Universities and colleges use real steering vectors mostly, but real steering vectors has its limitation, such as the uncontrollable of test environment and nonrepeatability, survey
The interference that cost is of a relatively high in examination, cannot get rid of the hardware such as sensor carries out the problems such as evaluation and test to perception algorithm.
Summary of the invention
The primary and foremost purpose of the present invention is to provide the most acquired actual sensor data of a kind of utilization to enter intelligent vehicle
Row data test, can in real time, synchronously simulate a kind of intelligent vehicle perception test that actual sensor carries out data transmission
Platform.
For achieving the above object, present invention employs techniques below scheme: a kind of intelligent vehicle perception test platform,
This test platform includes:
Disk, for storing the most acquired complete test data and test result；
Server end, is used for providing virtual-sensor, the data of simulation actual sensor to send, simultaneously to intelligent vehicle to be measured
Perception make evaluation；
Network, for the data transmission of server end with client；
Client, provides message subscribing, data receiver, digital independent and test result loopback clothes for intelligent vehicle to be measured
Business.
Described server end includes:
Multiple virtual-sensors, each virtual-sensor emulates a type of actual sensor, for testing data
Send；
Server end controls thread, for sending control signal to client, receives the control from client simultaneously and believes
Number, and notify that virtual-sensor makes corresponding operation；
Test result receiving thread, for receiving the test result from client, with the perception to intelligent vehicle
Make test and appraisal.
Described client includes:
Test data for receiving the test data sent from server end, and are put into by multiple data receiver threads
Corresponding message sink queue；
Message sink queue, for storing the test data that data receiver thread receives；
Client controls thread, for sending control signal to server end, receives the control from server end simultaneously
Signal, and notify that other thread of client makes corresponding operating；
Test result loopback thread, for giving server end so that server end is treated the test result of client
The perception surveying intelligent vehicle makes evaluation.
Described virtual-sensor includes:
Digital independent thread, for read test data from disk, puts into message transmit queue and notifies that data send
Thread；
Message transmit queue, for storing the test data that digital independent thread reads from disk, in order to data send
Thread sends；
Data transmission line journey, for taking out test data from message transmit queue, and is sent to subscribe to this data type
Client.
The invention also discloses the method for data synchronization of a kind of intelligent vehicle perception test platform, under the method includes
The step of row order:
(1) data-message in disk to be sent is numbered by server end；
(2) the caching threshold values of each message sink queue of client is calculated, all message sink queues that and if only if
After cache size all arrives the caching threshold values of setting, intelligent vehicle to be measured could utilize message interface to fetch data；
(3) data arriving message sink queue are carried out frame losing process；
(4) intelligent vehicle to be measured is after reading and having processed data, and test result consigns to message interface, message interface
Notice test result loopback thread, is sent to server end test result；
(5) server end receives, by test result receiving thread, the test result that client is sent, and resolves test knot
It is also made evaluation by fruit, finally the result of test and appraisal is stored in disk.
In step (2), the computational methods of described caching threshold values are as follows:
The computing formula of multiframe data buffer storage threshold values is as follows:
Wherein, CacheSize is caching threshold values, and Total is the totalframes of data, and Vn is the speed that server sends data
Rate, Vr is the speed that to-be-detected machine fetches data；
Must assure that any one moment t sending data, the data frame number of transmission should be more than or equal to reading data
Frame number, i.e.
CacheSize+t*Vn≥t*Vr (2)
Formula (2) to meet to be set up in the t=Total/Vr moment, and i.e. in the t=Total/Vr moment, formula (2) meets a left side
Right equal, so the minima of CacheSize is:
If transmission rate Vn>Vr, then CacheSize<0, illustrate that at this moment, CacheSize takes 0 without caching.
In step (3), when the data of the numbered n of current data arrive client, point three kinds of situations:
If (3a) message queue is empty or the tail of the queue data number of stop press queue is n-1, then current data is put into
Message tail of the queue；
If (3a) message queue is the most empty and tail of the queue data number is less than n-1, then the data between explanation n-i+1 to n-1 can
Can lose, now need first to insert in the position of n-i+1 to n-1 i-1 null frame, then n-th frame data are inserted into tail of the queue, i 1；
If (3c) message queue is different and tail of the queue data number is more than n-1, now it is divided into two kinds of situations:
3c1) current number n is more than or equal to team's head element, illustrates that these frame data have been done null frame process, by these frame data
Replace corresponding null frame data；
If 3c2) current number is less than team's head element, illustrate that these frame data are taken away with null frame by client, then this frame
The no longer effective property of data, abandons this frame data.
As shown from the above technical solution, the test platform that the present invention provides, hardware interference can be got rid of, utilize collection complete
Data and virtual-sensor carry out the perception of intelligent vehicle to be measured controlled repeatably testing and assessing；The number that the present invention provides
Can ensure that according to synchronous method the data of the simulating realistic sensor of data test platform real-time synchronization send, thus improve test and appraisal
Accuracy；The test platform that the present invention provides has good autgmentability, surveys to carry out the perception under certain new scene
Comment, only the data of this scene once need to be gathered, and input database can be tested and assessed.
Accompanying drawing explanation
Fig. 1 is the structure composed schematic diagram of test platform in the present invention；
Fig. 2: frame loss condition 1 data process schematic diagram
Fig. 3: frame loss condition 2 data process schematic diagram
Fig. 4: frame loss condition 3.1 data process schematic diagram
Fig. 5: frame loss condition 3.2 data process schematic diagram
Fig. 6: exemplary client message queue view
Detailed description of the invention
As it is shown in figure 1, a kind of intelligent vehicle perception test platform, this test platform includes:
Disk, for storing the most acquired complete test data and test result；
Server end 1, is used for providing virtual-sensor, the data of simulation actual sensor to send, simultaneously to intelligence to be measured
The perception of vehicle makes evaluation；
Network, for the data transmission of server end 1 with client 2；
Client 2, provides message subscribing, data receiver, digital independent and test result loopback clothes for intelligent vehicle to be measured
Business.
Described server end 1 includes:
Multiple virtual-sensors, each virtual-sensor emulates a type of actual sensor, for testing data
Send；
Server end controls thread, for sending control signal to client 2, receives the control from client 2 simultaneously
Signal, and notify that virtual-sensor makes corresponding operation；
Test result receiving thread, for receiving the test result from client 2, with the perception to intelligent vehicle
Make test and appraisal.
Described client 2 includes:
Test data for receiving the test data sent from server end 1, and are put into by multiple data receiver threads
Corresponding message sink queue；
Message sink queue, for storing the test data that data receiver thread receives；
Client controls thread, for sending control signal to server end 1, receives the control from server end 1 simultaneously
Signal processed, and notify that other thread of client 2 makes corresponding operating；
Test result loopback thread, for giving server end 1 the test result of client 2 so that server end 1
The perception of intelligent vehicle to be measured is made evaluation.
Described virtual-sensor includes:
Digital independent thread, for read test data from disk, puts into message transmit queue and notifies that data send
Thread；
Message transmit queue, for storing the test data that digital independent thread reads from disk, in order to data send
Thread sends；
Data transmission line journey, for taking out test data from message transmit queue, and is sent to subscribe to this data type
Client 2.
This method includes the step of following order:
(1) data-message in disk to be sent is numbered by server end 1；
(2) the caching threshold values of each message sink queue of client 2 is calculated, all message sink queues that and if only if
After cache size all arrives the caching threshold values of setting, intelligent vehicle to be measured could utilize message interface to fetch data；
(3) data arriving message sink queue are carried out frame losing process；
(4) intelligent vehicle to be measured is after reading and having processed data, and test result consigns to message interface, message interface
Notice test result loopback thread, is sent to server end 1 test result；
(5) server end 1 receives, by test result receiving thread, the test result that client 2 is sent, and resolves test
It is also made evaluation by result, finally the result of test and appraisal is stored in disk.
In step (2), the computational methods of described caching threshold values are as follows:
The computing formula of multiframe data buffer storage threshold values is as follows:
Wherein, CacheSize is caching threshold values, and Total is the totalframes of data, and Vn is the speed that server sends data
Rate, Vr is the speed that to-be-detected machine fetches data；
Must assure that any one moment t sending data, the data frame number of transmission should be more than or equal to reading data
Frame number, i.e.
CacheSize+t*Vn≥t*Vr (2)
Formula (2) to meet to be set up in the t=Total/Vr moment, and i.e. in the t=Total/Vr moment, formula (2) meets a left side
Right equal, so the minima of CacheSize is:
If transmission rate Vn>Vr, then CacheSize<0, illustrate that at this moment, CacheSize takes 0 without caching.
In step (3), when the data of the numbered n of current data arrive client 2, point three kinds of situations:
If (3a) message queue is empty or the tail of the queue data number of stop press queue is n-1, then current data is put into
Message tail of the queue；
If (3a) message queue is the most empty and tail of the queue data number is less than n-1, then the data between explanation n-i+1 to n-1 can
Can lose, now need first to insert in the position of n-i+1 to n-1 i-1 null frame, then n-th frame data are inserted into tail of the queue, i 1；
If (3c) message queue is different and tail of the queue data number is more than n-1, now it is divided into two kinds of situations:
3c1) current number n is more than or equal to team's head element, illustrates that these frame data have been done null frame process, by these frame data
Replace corresponding null frame data；
If 3c2) current number is less than team's head element, illustrate that these frame data are taken away with null frame by client 2, then this frame
The no longer effective property of data, abandons this frame data.
Embodiment one
As a example by certain test exercise question, it is assumed that needing the data sent is picture and each 10 frames of laser radar data, each message
The caching threshold values that receiving queue calculates according to caching threshold calculation method is all 2.In addition, it is assumed that intelligent vehicle to be measured has San Taichu
Reason machine, image data datatron, radar data datatron and decision machine, receive respectively image data, radar data, picture and
Radar data.
The first step, server end 1, when test starts, reads Item-Code information such as examination question classification, sensing from disk
Device calibration information etc., and Item-Code is broadcast to intelligent vehicle to be measured；
Second step, each datatron of intelligent vehicle to be measured is according to the data logarithm needed for Item-Code information and present treatment machine
Subscribing to according to type, picture processing machine is subscribed to image information and opens data receiver thread and the message sink team of a picture
Arranging, radar processor is subscribed to radar message and opens data receiver thread and the message sink queue of a radar, and decision machine is ordered
Read two kinds of data and open image data and two receiving threads of radar data and corresponding image data and radar data disappears
Breath queue, processes image data and radar data, respectively as it is shown in figure 1, three machines are utilized respectively client control line afterwards
Journey controls thread to server end and sends signal, shows that the machine parsing Item-Code information is complete and opens corresponding data and connects
Take-up journey, server end 1 can send data.Three client computer start to fetch data afterwards, but now each message queue number
According to being all 0, less than caching threshold values, so three client computer will wait.
3rd step, server end 1 is receiving after three machines resolve the signals that Item-Code information is complete, for picture and
Radar data builds a virtual-sensor respectively, i.e. opens up a data read line journey, message transmit queue, sends control line
Journey.Digital independent thread is responsible for reading the most acquired data from disk and putting into message transmit queue tail of the queue, and notifies number
According to sending thread.Message transmit queue is mainly used to store the data being read into internal memory.If message transmit queue is the most empty, then
Data transmission line journey takes its team's head data, and is sent to have subscribed the datatron of this type of message, and otherwise data transmission line journey is hung
Rise, and wait waking up up of digital independent thread.After pending data is sent, transmit queue is empty, picture and the number of radar simultaneously
Exit according to sending thread.
4th step, when data arrive client 2, it should carry out frame losing process, as a example by decision machine, simulate front 5 frame numbers
According to situation about arriving, as shown in Figure 6:
The image data of T1: numbered 1 and the radar data of numbered 1 reach, now n=1, because two queues are all
Sky, puts into message queue, and when the data of Fig. 2 arrive shown in state, now client 2 is fetched data still failed, because not reaching
To caching threshold values；
The image data of T2: numbered 2 and the radar data of numbered 2 reach, now n=2, because tail of the queue data number
It is 1, equal to n-1, puts into message queue, when the data of Fig. 2 arrive shown in state, because two queues have all reached caching valve
Value, so client controls thread and controls thread one signal of transmission to server end and wait, server end controls thread and exists
After receiving the signal of picture processing machine, radar processor and decision machine, then send a signal to three machines, show institute
Some machines have all reached caching threshold values, can start to read data, and now client 2 is fetched data successfully, and test starts.Now
Two message queues are all left the data of numbered 2；
The image data of T3: numbered 3 and the radar data of numbered 5 reach, when the data of image data such as Fig. 2 arrive
Shown in state, it is directly placed into tail of the queue, for radar data, n=5, tail of the queue numbered 2, if not processing, then decision machine
To get image data and the radar data of numbered 5 of numbered 3 when third time is fetched data, then data there will be difference
Step.Now according to after Fig. 3 is disposed shown in state, the empty radar data of numbered 3 and 4 should be inserted；NULL generation in Fig. 3
Table null frame；
T4: client computer takes picture and the radar data of numbered 2 away, remains the data of numbered 3 in now picture queue,
Empty data and the data of numbered 5 having volume to be 3 and 4 in radar queue；
The image data of T5: numbered 4 and the radar data of numbered 4 reach, when the data of image data such as Fig. 2 arrive
Shown in state, being directly placed into tail of the queue, for radar data, current n=4, less than tail of the queue numbering 5 and more than team's head numbering 3, such as figure
Shown in 4, so the data of 4 are replaced null frame；
T6: client 2 takes picture and the radar data of numbered 3, and now radar data is as the frame losing of actual sensor
Behavior, directly returns null frame；
The image data of T7: numbered 5 and the radar data of numbered 3 reach, when the data of image data such as Fig. 2 arrive
Shown in state, it is directly placed into tail of the queue, for radar data, current n=3, number less than tail of the queue, simultaneously again smaller than team's head numbering,
As it is shown in figure 5, illustrate that the radar data of numbered 3 is taken away as null frame, the most no longer effective property of these frame data, so directly
Connect and abandon.The just data of numbered 4 and 5 is all left in now two queues；Dotted line in Fig. 5 represents the most removed data；
5th step, test result, after reading and having processed data, is consigned to message interface, message by intelligent vehicle to be measured
Interface notification test result loopback thread, is sent to server end 1 test result；
6th step, server end 1 receives, by test result receiving thread, the test result that client 2 is sent, and resolves
It is also made evaluation by test result, finally the result of test and appraisal is stored in disk.
Visible, the present invention can real-time as actual sensor, synchronize data are transmitted, be vehicle to be measured simultaneously
The message interface provided can allow intelligent vehicle to be measured can test in the case of code only makes a small amount of amendment.
Claims (7)
1. an intelligent vehicle perception test platform, it is characterised in that: this test platform includes:
Disk, for storing the most acquired complete test data and test result；
Server end, is used for providing virtual-sensor, the data of simulation actual sensor to send, simultaneously to intelligent vehicle to be measured
Perception makes evaluation；
Network, for the data transmission of server end with client；
Client, provides message subscribing, data receiver, digital independent and test result loopback service for intelligent vehicle to be measured.
Intelligent vehicle perception test platform the most according to claim 1, it is characterised in that: described server end bag
Include:
Multiple virtual-sensors, each virtual-sensor emulates a type of actual sensor, for testing the transmission of data；
Server end controls thread, for sending control signal to client, receives the control signal from client simultaneously, and
Notice virtual-sensor makes corresponding operation；
Test result receiving thread, for receiving the test result from client, makes with the perception to intelligent vehicle
Test and appraisal.
Intelligent vehicle perception test platform the most according to claim 1, it is characterised in that: described client includes:
Test data for receiving the test data sent from server end, and are put into accordingly by multiple data receiver threads
Message sink queue；
Message sink queue, for storing the test data that data receiver thread receives；
Client controls thread, for sending control signal to server end, receives the control signal from server end simultaneously,
And notify that other thread of client makes corresponding operating；
Test result loopback thread, for giving server end the test result of client so that server end is to intelligence to be measured
The perception of energy vehicle makes evaluation.
Intelligent vehicle perception test platform the most according to claim 2, it is characterised in that: described virtual-sensor bag
Include:
Digital independent thread, for read test data from disk, puts into message transmit queue and notifies data transmission line journey；
Message transmit queue, for storing the test data that digital independent thread reads from disk, in order to data transmission line journey
Send；
Data transmission line journey, for taking out test data from message transmit queue, and is sent to subscribe to the visitor of this data type
Family end.
The method of data synchronization of intelligent vehicle perception test platform the most according to any one of claim 1 to 4, should
Method includes the step of following order:
(1) data-message in disk to be sent is numbered by server end；
(2) the caching threshold values of each message sink queue of client, the caching of all message sink queues that and if only if are calculated
After size all arrives the caching threshold values of setting, intelligent vehicle to be measured could utilize message interface to fetch data；
(3) data arriving message sink queue are carried out frame losing process；
(4) intelligent vehicle to be measured is after reading and having processed data, and test result consigns to message interface, and message interface notifies
Test result loopback thread, is sent to server end test result；
(5) server end receives, by test result receiving thread, the test result that client is sent, and resolves test result also
It is made evaluation, finally the result of test and appraisal is stored in disk.
The method of data synchronization of described intelligent vehicle perception test platform the most according to claim 5, its feature
Being: in step (2), described caching threshold calculation method is as follows:
The computing formula of multiframe data buffer storage threshold values is as follows:
Wherein, CacheSize is caching threshold values, and Total is the totalframes of data, and Vn is the speed that server sends data, Vr
It is the speed fetched data of to-be-detected machine；
Must assure that any one moment t sending data, the data frame number of transmission should be more than or equal to the frame number reading data,
I.e.
CacheSize+t*Vn≥t*Vr (2)
Formula (2) to meet to be set up in the t=Total/Vr moment, and i.e. in the t=Total/Vr moment, formula (2) meets left and right phase
Deng, so the minima of CacheSize is:
If transmission rate Vn>Vr, then CacheSize<0, illustrate that at this moment, CacheSize takes 0 without caching.
The method of data synchronization of described intelligent vehicle perception test platform the most according to claim 5, its feature
It is: in step (3), when the data of the numbered n of current data arrive client, point three kinds of situations:
If (3a) message queue is empty or the tail of the queue data number of stop press queue is n-1, then current data is put into message
Tail of the queue；
If (3a) message queue is the most empty and tail of the queue data number is less than n-1, then the data between explanation n-i+1 to n-1 may be lost
Lose, now need first to insert in the position of n-i+1 to n-1 i-1 null frame, then n-th frame data are inserted into tail of the queue, i 1；
If (3c) message queue is different and tail of the queue data number is more than n-1, now it is divided into two kinds of situations:
3c1) current number n is more than or equal to team's head element, illustrates that these frame data have been done null frame process, is replaced by these frame data
Corresponding null frame data；
If 3c2) current number is less than team's head element, illustrate that these frame data are taken away with null frame by client, then these frame data
No longer effective property, abandons this frame data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610638158.0A CN106254461B (en) | 2016-08-06 | 2016-08-06 | A kind of method of data synchronization of intelligent vehicle sensing capability test platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610638158.0A CN106254461B (en) | 2016-08-06 | 2016-08-06 | A kind of method of data synchronization of intelligent vehicle sensing capability test platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106254461A true CN106254461A (en) | 2016-12-21 |
| CN106254461B CN106254461B (en) | 2019-04-05 |
Family
ID=58077712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610638158.0A Active CN106254461B (en) | 2016-08-06 | 2016-08-06 | A kind of method of data synchronization of intelligent vehicle sensing capability test platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106254461B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108306926A (en) * | 2017-11-30 | 2018-07-20 | 深圳市科列技术股份有限公司 | A kind of method for pushing and device of car networking device gateway business datum |
| CN109240271A (en) * | 2018-10-18 | 2019-01-18 | 东南（福建）汽车工业有限公司 | A kind of the cloud platform test macro and method of full-vehicle control equipment |
| CN109936420A (en) * | 2017-12-15 | 2019-06-25 | 上海蔚来汽车有限公司 | Method and apparatus for the synchronous data acquired by multiple sensors |
| CN110473562A (en) * | 2018-05-10 | 2019-11-19 | 杭州海康威视数字技术股份有限公司 | Audio data processing method, device and system |
| CN111309599A (en) * | 2020-01-21 | 2020-06-19 | 同济大学 | Vehicle-road cooperative system testing method and framework |
| CN111522727A (en) * | 2019-02-01 | 2020-08-11 | 阿里巴巴集团控股有限公司 | Simulation object test method, device and system |
| US11634153B2 (en) | 2019-12-30 | 2023-04-25 | Waymo Llc | Identification of proxy calibration targets for a fleet of vehicles |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013072925A2 (en) * | 2011-09-19 | 2013-05-23 | Tata Consultancy Services Limited | A computing platform for development and deployment of sensor data based applications and services |
| CN104112363A (en) * | 2014-07-04 | 2014-10-22 | 西安交通大学 | Multi-sensing-data space-time synchronization method and road multi-sensing-data vehicle-mounted acquisition system |
| CN105807630A (en) * | 2015-01-21 | 2016-07-27 | 福特全球技术公司 | Virtual sensor testbed |
-
2016
- 2016-08-06 CN CN201610638158.0A patent/CN106254461B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013072925A2 (en) * | 2011-09-19 | 2013-05-23 | Tata Consultancy Services Limited | A computing platform for development and deployment of sensor data based applications and services |
| CN104112363A (en) * | 2014-07-04 | 2014-10-22 | 西安交通大学 | Multi-sensing-data space-time synchronization method and road multi-sensing-data vehicle-mounted acquisition system |
| CN105807630A (en) * | 2015-01-21 | 2016-07-27 | 福特全球技术公司 | Virtual sensor testbed |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108306926A (en) * | 2017-11-30 | 2018-07-20 | 深圳市科列技术股份有限公司 | A kind of method for pushing and device of car networking device gateway business datum |
| CN109936420A (en) * | 2017-12-15 | 2019-06-25 | 上海蔚来汽车有限公司 | Method and apparatus for the synchronous data acquired by multiple sensors |
| CN109936420B (en) * | 2017-12-15 | 2022-05-03 | 上海蔚来汽车有限公司 | Method and apparatus for synchronizing data collected by multiple sensors |
| CN110473562A (en) * | 2018-05-10 | 2019-11-19 | 杭州海康威视数字技术股份有限公司 | Audio data processing method, device and system |
| CN109240271A (en) * | 2018-10-18 | 2019-01-18 | 东南（福建）汽车工业有限公司 | A kind of the cloud platform test macro and method of full-vehicle control equipment |
| CN111522727A (en) * | 2019-02-01 | 2020-08-11 | 阿里巴巴集团控股有限公司 | Simulation object test method, device and system |
| CN111522727B (en) * | 2019-02-01 | 2023-04-14 | 阿里巴巴集团控股有限公司 | Simulation object test method, device and system |
| US11634153B2 (en) | 2019-12-30 | 2023-04-25 | Waymo Llc | Identification of proxy calibration targets for a fleet of vehicles |
| US11945467B2 (en) | 2019-12-30 | 2024-04-02 | Waymo Llc | Identification of proxy calibration targets for a fleet of vehicles |
| CN111309599A (en) * | 2020-01-21 | 2020-06-19 | 同济大学 | Vehicle-road cooperative system testing method and framework |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106254461B (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106254461A (en) | A kind of intelligent vehicle perception test platform and method of data synchronization thereof | |
| CN106267774B (en) | Moving state identification method and apparatus | |
| CN112673381B (en) | Method and related device for identifying confrontation sample | |
| CN109902832A (en) | Training method, predicting abnormality method and the relevant apparatus of machine learning model | |
| CN108235116A (en) | Feature propagation method and device, electronic equipment, program and medium | |
| CN109884721A (en) | Safety check prohibited items detection method, device and electronic equipment based on artificial intelligence | |
| CN108681908A (en) | Anti- cheat method, device, computing device and storage medium | |
| CN115577746A (en) | Network intrusion detection method based on meta-learning | |
| WO2020107022A4 (en) | Signal processing workflow engine incorporating graphical user interface for space situational awareness | |
| CN113807350A (en) | Target detection method, device, equipment and storage medium | |
| CN111382635B (en) | Commodity category identification method and device and electronic equipment | |
| CN110033424A (en) | Method, apparatus, electronic equipment and the computer readable storage medium of image procossing | |
| CN113726545B (en) | Network traffic generation method and device for generating countermeasure network based on knowledge enhancement | |
| CN108875519A (en) | Method for checking object, device and system and storage medium | |
| CN106323272B (en) | A kind of method and electronic equipment obtaining track initiation track | |
| CN115222061A (en) | Federal learning method based on continuous learning and related equipment | |
| CN105654134A (en) | Supervised self feedback-based context awareness system, working method and application thereof | |
| CN108875500A (en) | Pedestrian recognition methods, device, system and storage medium again | |
| Liao et al. | Toward fully autonomous seismic networks: Backprojecting deep learning‐based phase time functions for earthquake monitoring on continuous recordings | |
| CN115588150A (en) | Pet dog video target detection method and system based on improved YOLOv5-L | |
| CN108921012A (en) | A method of utilizing artificial intelligence chip processing image/video frame | |
| CN106126195A (en) | A kind of information processing method and electronic equipment | |
| CN113343093A (en) | Intelligent online service information recommendation method based on artificial intelligence and cloud computing system | |
| CN104598917A (en) | Support vector machine classifier IP (internet protocol) core | |
| CN116703161B (en) | Prediction method and device for man-machine co-fusion risk, terminal equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |