CN118276481A - Intelligent driving debugging method, device, system, electronic equipment and storage medium - Google Patents
Intelligent driving debugging method, device, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118276481A CN118276481A CN202410244074.3A CN202410244074A CN118276481A CN 118276481 A CN118276481 A CN 118276481A CN 202410244074 A CN202410244074 A CN 202410244074A CN 118276481 A CN118276481 A CN 118276481A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- intelligent driving
- scene
- tested
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000002159 abnormal effect Effects 0.000 claims abstract description 49
- 238000005520 cutting process Methods 0.000 claims abstract description 37
- 239000012634 fragment Substances 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 20
- 238000009877 rendering Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 16
- 230000001133 acceleration Effects 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 8
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 13
- 230000005856 abnormality Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The invention discloses an intelligent driving debugging method, device, system, electronic equipment and storage medium. The method is applied to a computer end of a debugging system, and comprises the steps of responding to a data cutting request, and determining a data cutting range according to an abnormal mark in an intelligent driving scene of a vehicle to be tested; cutting out driving scene fragments from the intelligent driving scene according to the data cutting range; and responding to the data restoration request, restoring the multi-dimensional scene modeling data corresponding to the driving scene segment, so that the debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment. The technical scheme of the embodiment improves the debugging efficiency and the accuracy of the debugging result.
Description
Technical Field
The present invention relates to the field of intelligent driving technologies, and in particular, to an intelligent driving debugging method, device, system, electronic device, and storage medium.
Background
The intelligent driving control algorithm of the vehicle relates to the fusion of a plurality of expertise, has high difficulty and complex realization, and the algorithm program is mostly operated at a vehicle-mounted domain control end in a background process mode, and is interacted and transmitted in a data and signal mode, and finally, the displayed result is a sensing result sent to a regulation and control professional, and the regulation and control professional finally controls the vehicle. In the prior art, the whole driving scene is usually observed manually in the debugging of the intelligent driving control algorithm of the vehicle, and then the algorithm is analyzed, so that the problems of low debugging efficiency and inaccurate debugging result generally exist in the complex intelligent driving control algorithm of the vehicle.
Disclosure of Invention
The invention provides an intelligent driving debugging method, device, system, electronic equipment and storage medium, which are used for improving the debugging efficiency and improving the accuracy of a debugging result.
According to one aspect of the present invention, there is provided an intelligent driving debugging method applied to a computer terminal of a debugging system, the method comprising:
Responding to the data clipping request, and determining a data clipping range according to an abnormal mark in an intelligent driving scene of the vehicle to be detected;
cutting out driving scene fragments from the intelligent driving scene according to the data cutting range;
And responding to a data restoration request, and restoring the multi-dimensional scene modeling data corresponding to the driving scene segment so that a debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment.
According to another aspect of the present invention, there is provided an intelligent driving debugging device integrated at a computer end of a debugging system, the device comprising:
the data cutting range determining module is used for responding to the data cutting request and determining the data cutting range according to the abnormal mark in the intelligent driving scene of the vehicle to be detected;
The target range data clipping module is used for clipping driving scene fragments from the intelligent driving scene according to the data clipping range;
The data restoration module is used for responding to the data restoration request and restoring the multi-dimensional scene modeling data corresponding to the driving scene segment so that the debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment.
According to another aspect of the present invention, there is provided a debugging system, the system comprising: a vehicle-mounted domain control end and a computer end of a vehicle to be tested; the vehicle-mounted domain control end comprises a data acquisition module;
the data acquisition module is used for acquiring scene modeling data of multiple dimensions of the vehicle to be tested in the intelligent driving test process and sending the scene modeling data of the multiple dimensions to the computer terminal;
the computer end is used for executing the intelligent driving debugging method according to any embodiment of the invention according to the scene modeling data with multiple dimensions sent by the vehicle-mounted domain control end.
According to another aspect of the present invention, there is provided an electronic apparatus including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the intelligent driving debugging method of any embodiment of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the intelligent driving debugging method according to any embodiment of the present invention when executed.
The technical scheme of the embodiment of the invention is applied to a computer end of a debugging system, and the data cutting range is determined according to the abnormal mark in the intelligent driving scene of the vehicle to be tested by responding to the data cutting request; cutting out driving scene fragments from the intelligent driving scene according to the data cutting range; and responding to the data restoration request, restoring the multi-dimensional scene modeling data corresponding to the driving scene segment, so that the debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment. By adopting the technical means of anomaly marking and data clipping analysis, the problems that the debugging efficiency is low and the debugging result is inaccurate are generally caused for a complex intelligent driving control algorithm of a vehicle by manually observing the whole driving scene and analyzing the algorithm in the prior art, the debugging efficiency is improved, and the accuracy of the debugging result is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1a is a flowchart of an intelligent driving debugging method according to a first embodiment of the present invention;
FIG. 1b is a schematic diagram of a functional framework of a debug system according to the present embodiment;
FIG. 1c is a schematic diagram of a real-time mode workflow of a debug system according to the present embodiment;
FIG. 1d is a schematic diagram of a playback mode workflow of the debug system according to the present embodiment;
fig. 2 is a schematic structural diagram of an intelligent driving debugging device according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a debug system according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device implementing the intelligent driving debugging method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1a is a flowchart of an intelligent driving debugging method according to an embodiment of the present invention, where the method may be applied to a computer (PC) of a debugging system, and the method may be performed by an intelligent driving debugging device, and the intelligent driving debugging device may be implemented in hardware and/or software, and the intelligent driving debugging device may be configured in a computer. As shown in fig. 1a, the method comprises:
S110, responding to the data clipping request, and determining a data clipping range according to the abnormal mark in the intelligent driving scene of the vehicle to be detected.
The data clipping request may be a driving scene clipping request initiated by a user for an anomaly flag during playback of an intelligent driving scene of the vehicle to be tested. The vehicle to be tested may be a vehicle that requires intelligent driving algorithm testing. The intelligent driving scene of the vehicle to be tested can be a virtual driving scene displayed on a computer end of the debugging system. The abnormal mark may be a mark in the intelligent driving scene of the vehicle to be tested, which is inconsistent with the actual intelligent driving scene. The data clipping range may be a range that clips for an abnormality flag of the intelligent driving environment of the vehicle to be tested.
In the intelligent driving test process of the vehicle, the actual intelligent driving scene of the vehicle to be tested can be modeled and stored at a computer end, so that subsequent debugging personnel can analyze the abnormality to realize intelligent driving debugging. In this embodiment, the computer end may further mark an abnormality existing in the constructed intelligent driving scene of the vehicle to be tested, so that when the debugger plays back the intelligent driving scene of the vehicle to be tested, the debugger may perform separate cutting analysis on the segment corresponding to the abnormality mark.
The abnormality in the intelligent driving scene may refer to the situation that the constructed intelligent driving scene is inconsistent with the actual intelligent driving scene, such as error of perceived obstacle position, error of perceived lane line position, error of visual perceived speed limit board value, error of visual perceived light spot position, etc., as well as abnormal control such as speed and direction of the vehicle to be detected, and also such as loss or failure of perceived result signals sent to the computer end by the vehicle to be detected. Therefore, the computer end of the embodiment can respond to the data cutting request of the debugging personnel, and the data cutting range is determined according to the abnormal mark in the intelligent driving scene of the vehicle to be tested.
Alternatively, the intelligent driving scenario of the vehicle under test may be constructed by: acquiring scene modeling data of multiple dimensions of the vehicle to be tested in the intelligent driving test process of the vehicle to be tested; and performing time alignment and rendering processing on the scene modeling data of the multiple dimensions of the vehicle to be tested so as to construct an intelligent driving scene of the vehicle to be tested.
The scene modeling data of the plurality of dimensions of the vehicle to be tested can comprise real-time image information of the driving surrounding environment, intelligent driving real-time sensing data, intelligent driving real-time control data and the like, wherein the real-time image information is acquired in the intelligent driving test process of the vehicle to be tested. Real-time image information of the driving surrounding environment can be acquired by an image acquisition device arranged on the vehicle to be detected; the intelligent driving real-time perception data can be acquired through radar equipment and the like arranged on the vehicle to be detected, such as obstacle information and the like; the intelligent driving real-time control data may be, for example, steering wheel control data, acceleration control data, deceleration control data, mcu (Microcontroller Unit, micro control unit) signals, etc. of the vehicle to be tested.
In the field of intelligent driving algorithms, scene modeling data (such as vehicle speed, acceleration, steering angle, images, radar signals and the like) of multiple dimensions such as real-time image information of driving surrounding environment, real-time perception data of intelligent driving, real-time control data of intelligent driving and the like often come from different source domains, such as a backbone network of vehicle can (Controller Area Network, vehicle-mounted control local area network) signals; for example, entering into a vehicle-mounted soc (System on Chip) end through a name/IP (Scalableservice-Oriented Middleware over IP, extensible service-oriented middleware based on IP) protocol; and for example, devices such as an external USB camera are directly connected to a computer end of the debugging system. The data of different source domains adopts respective clock sources. For example, the vehicle-mounted soc terminal performs time service through ICC (Internet Computer Consensus ) protocol; the vehicle can signal itself adopts relative time; the external equipment of the computer end has no timestamp, and the time of the computer end can be used as a reference. Therefore, when the intelligent driving scene is built at the computer end, time alignment and rendering processing can be carried out on the scene modeling data with multiple dimensions so as to build the intelligent driving scene of the vehicle to be tested.
Optionally, performing time alignment and rendering processing on the scene modeling data of multiple dimensions of the vehicle to be tested to construct an intelligent driving scene of the vehicle to be tested may include: according to the receiving time of the scene modeling data of the multiple dimensions of the vehicle to be detected at the computer end or the satellite synchronous clock of the global positioning system, performing time alignment processing on the scene modeling data of the multiple dimensions of the vehicle to be detected to obtain a time alignment processing result; rendering the time alignment processing result to construct an intelligent driving scene of the vehicle to be detected.
Specifically, the alignment process can be performed by uniformly using the PC-terminated reception time. Because all the scene modeling data of multiple dimensions are finally imported to the PC end for recording, the data are approximately considered to be synchronously received in practice. Therefore, the PC end clock is used as a source to mark the receiving time, and the data of all signals related to a certain time can be rapidly positioned.
The alignment process may be performed using a satellite synchronizing clock of GPS (Global Positioning System ). For example, for a vehicle-mounted soc terminal, time service is performed through an ICC protocol, and GPS satellite time is adopted; and for can signals, the GPS signals can be subscribed to for time output. The GPS satellite time and the PC end system time have fixed time deviation, and clock alignment of scene modeling data with multiple dimensions can be realized through background processing. Therefore, the signal from the vehicle-mounted soc end, the can signal and the external signal of the PC end equipment can keep high-precision time synchronization as long as the GPS signal is unobstructed even if the signals are in different clock spaces.
In one case, the anomaly flag may be marked by: acquiring each target driving parameter of a vehicle to be tested in a specified time range from an intelligent driving scene; each target driving parameter can comprise the absolute speed, the relative speed, the acceleration and the position of the vehicle to be tested; drawing curves of all target running parameters at each moment in a designated time range to obtain parameter curves corresponding to each moment in the designated time range; comparing and analyzing the parameter curves according to time sequence to determine the error of each target running parameter at adjacent moment; and determining abnormal time from the specified time range according to the error, and marking.
The speed real-time value, the acceleration real-time value and the position real-time value of the vehicle to be measured in the 5 th minute to the 6 th minute can be obtained from the intelligent driving scene, the speed real-time value, the acceleration real-time value and the position real-time value of each target driving parameter are drawn into a curve at each moment in the minute, and therefore each curve is subjected to comparative analysis, the error condition of the speed real-time value, the acceleration real-time value and the position real-time value is judged, and if the error of the position real-time value at the adjacent moment exceeds a preset position difference threshold value, the abnormal moment with position abnormality can be determined.
In another case, the anomaly flag may be marked by: in response to the first marking instruction, adding an abnormal mark in the intelligent driving scene; the first marking instruction is issued through a user interface of a computer after a user observes the abnormal position of the driving environment in the intelligent driving scene.
For example, the intelligent driving scene displayed by the computer end is observed manually, the position with obvious abnormality is selected in a frame or the time when the obvious scene is discontinuous is marked, and the computer end can mark the abnormality according to the instruction of the user.
In yet another case, the anomaly flag may be marked by: in response to the second marking instruction, marking abnormal moments in the intelligent driving scene; the second marking instruction is issued by a user through a user interface of the computer end according to the path state and fault signals of the scene modeling data of the multiple dimensions of the vehicle to be tested.
The computer end of the embodiment can count the receiving frame rate of the modeling data of each dimension scene in real time and display the receiving frame rate on the interface, so that a user can rapidly judge the channel state and the frame rate state of each data. The computer end can also display fault signals sent by the vehicle to be tested, so that a user can quickly locate and diagnose the abnormality of the vehicle. The computer end can also display the performance data of the vehicle-mounted domain control end of the vehicle to be tested, so that the running state of the vehicle-mounted domain control system is reflected in real time, and the user is abnormal in positioning. Therefore, the method can manually observe the path state, fault signals, performance state data and the like of the scene modeling data which are displayed in real time by the computer end and are transmitted by the vehicle end to be tested, and then issue a marking instruction, so that the computer end performs abnormal marking according to the instruction of a user.
Optionally, determining the data clipping range according to the abnormal mark in the intelligent driving scene of the vehicle to be tested may include: determining abnormal time in the intelligent driving scene according to the abnormal mark; and determining a data clipping range according to the preset time periods before and after the abnormal time.
In this embodiment, the time corresponding to the abnormal mark in the intelligent driving scene may be determined, and the preset period before and after the time may be determined as the data clipping range. The preset time periods before and after the abnormal time can be preset by a computer end, and can also be determined according to instructions of debugging personnel.
S120, cutting out driving scene fragments from the intelligent driving scene according to the data cutting range.
In this embodiment, driving scene segments may be cut out from the intelligent driving scene according to the data cutting range and displayed to the debugging personnel.
S130, responding to a data restoration request, and restoring the multi-dimensional scene modeling data corresponding to the driving scene segment, so that the debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment.
In this embodiment, the driving scene segment may be restored to the original multidimensional scene modeling data according to the requirement that the debugger views the original driving data corresponding to the driving scene segment, so that the debugger performs intelligent driving debugging on the vehicle to be tested according to the multidimensional scene modeling data corresponding to the driving scene segment.
Optionally, in order to meet different service requirements of the debugger on the driving scene segment, the driving scene segment can be converted into a visualized json format or csv format, so that the debugger can view specific original data content according to the timestamp. In addition, the driving scene segment can be converted into an original binary stream for recharging by debugging personnel.
The technical scheme of the embodiment of the invention is applied to a computer end of a debugging system, and the data cutting range is determined according to the abnormal mark in the intelligent driving scene of the vehicle to be tested by responding to the data cutting request; cutting out driving scene fragments from the intelligent driving scene according to the data cutting range; and responding to the data restoration request, restoring the multi-dimensional scene modeling data corresponding to the driving scene segment, so that the debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment. By adopting the technical means of anomaly marking and data clipping analysis, the problems that the debugging efficiency is low and the debugging result is inaccurate are generally caused for a complex intelligent driving control algorithm of a vehicle by manually observing the whole driving scene and analyzing the algorithm in the prior art, the debugging efficiency is improved, and the accuracy of the debugging result is improved.
In order to enable those skilled in the art to better understand the debug system of the present embodiment, fig. 1b is a schematic diagram of a functional framework of the debug system according to the present embodiment. The debugging system can comprise a real-time mode and a playback mode, wherein the real-time mode can comprise a data acquisition module, a data recording module and a state data real-time display module, the playback mode can comprise a data playback module and an offline data format conversion module, and the real-time mode and the playback mode can also jointly comprise a data forwarding module, a data rendering module, an automatic deployment module and a plug-in management module.
And a data acquisition module:
The data acquisition module is deployed at the vehicle-mounted domain control end of the vehicle to be tested in the debugging system and can be responsible for subscribing and issuing a plurality of dimension scene construction data (images, vision, fusion, radar, vehicle body and mcu signals) of the vehicle-mounted domain control end. The intelligent driving algorithm debugging metadata come from the vehicle-mounted domain control end, and in the process of data transmission, the data can be copied through the message middleware and injected into the board end time. The visual debugging tool can subscribe professional signals (namely scene construction data in multiple dimensions) of the vehicle-mounted domain control end, acquire and send the professional signals to the PC end, and complete the data acquisition process.
And a data forwarding module:
The data forwarding module can realize the receiving and forwarding of the PC end data. After receiving the professional signal from the vehicle-mounted domain control terminal, the PC terminal realizes data distribution through the data forwarding module and provides the data for other professional plug-ins, and the professional plug-ins can include but are not limited to: plug-ins such as data storage, real-time rendering, curve display, and table display.
And a data rendering module:
The data rendering module can achieve drawing and display and hidden control of target objects such as barriers, lane lines, speed limit signs and the like. The intelligent driving scene needs to carry out position marking on obstacles, such as a two-dimensional box and a three-dimensional stereo box; the track display of the lane lines is needed, including a driving front view and a road top view; the color distinction of different professional renderings is needed; development control is required for different target rendering displays. These functions may all be implemented in the data rendering module.
And a data recording module:
The data recording module can realize the storage of data received by the PC end. The PC end can write the acquired professional data into a file to generate a data packet, so that the post management and maintenance are convenient. The recording mode can comprise periodic recording, and the data packet supports an automatic switching function of different period durations. The recording process can support abnormal marks and support a data cutting function; the abnormal mark can be displayed in the data cutting process, so that data near the abnormal moment can be cut out, and the debugging personnel can conveniently analyze the data in a targeted manner.
And a data playback module:
The data playback module can realize alignment and playback control of the professional signal data. And (3) aligning the time stamp of each professional signal with the image by adopting a self-grinding alignment strategy to form a frame of complete data, and completing continuous playing of the data. The PC end can be provided with a playback toolbar to support functions such as playing, pausing, single frame advancing, single frame retreating, cyclic playing, progress bar dragging display and playing and the like.
An offline data format conversion module:
The offline data format conversion module can convert the data packet into json, csv and binary formats. Different requirements of debugging personnel are met, the data package can be converted into a visualized json format or csv format, and the debugging personnel can view specific original data content according to the time stamp. In addition, the data packet can be converted into an original binary stream for recharging by a debugging person. .
The state data real-time display module is used for:
the state data real-time display module can display the channel state, fault signals and performance state data in the professional signal sending process in real time. The computer end can count the receiving frame rate of the modeling data of each dimension scene in real time and display the receiving frame rate on the interface, so that a user can rapidly judge the channel state and the frame rate state of each data. The computer end can also display fault signals sent by the vehicle-mounted domain control end of the vehicle to be detected, so that a user can rapidly locate and diagnose the abnormality of the vehicle. The computer end can also display the performance data of the vehicle-mounted domain control end of the vehicle to be tested, so that the running state of the vehicle-mounted domain control system is reflected in real time, and the user is abnormal in positioning.
And (3) an automatic deployment module:
the automatic deployment module can deploy vehicle-mounted domain control terminal software at the PC terminal in a man-machine interaction mode. The automatic deployment module of the PC terminal can automatically package the functions of all processes of uploading, deployment, setting dependence, version checking, interactive start-stop and the like of the vehicle-mounted domain control terminal software. The test engineer does not need to know the internal dependency relationship of the software, and through the interactive interface provided by the embodiment, when the PC end is connected to the vehicle-mounted board end through the network cable, all processes are started by selecting to upload the software package, decompressing, displaying the version number deployed first, checking and one-key through visual interface prompt of the PC end. Through automatic deployment interface and operation, the test engineer greatly simplifies the software installation flow, improves the efficiency and reduces the test error rate. The automatic deployment module reduces the difficulty of deploying the vehicle-mounted domain control terminal software through a friendly man-machine interaction interface, and can ensure correct and effective deployment.
Plug-in management module:
The plug-in management module can dynamically manage the use of the PC end function plug-in. The debugging system has rich functions and supports dynamic expansion, so that a plug-in management module is required to be responsible for maintenance, and plug-in functions are deployed aiming at different scenes. In the software design level, the embodiment adopts a scalable, expandable and easily-maintained software architecture, and supports the function continuously added in the form of a plug-in the process of iterative upgrading of the software. The plug-in units and the plug-in units can not form abnormal conditions which are caused by strong dependency on a software starting layer and can not be started, the data communication between the plug-in units is realized through a unified communication standard on an information interaction layer, and the function is newly increased under the condition that the software is not added by loading the appointed plug-in units on a function realization layer. In addition, aiming at different application scenes, for example, when USB camera data are not required to be acquired, the appointed plug-in can be closed in a configuration mode; for the same version of software, corresponding plug-ins and functions are quickly loaded and unloaded in a configuration mode. In some special occasions, including but not limited to poor configuration of the PC end, insufficient resources and excessive software start, the load of the software is effectively reduced, and the concerned function is realized.
In order to enable those skilled in the art to better understand the intelligent driving debugging method of the present embodiment, fig. 1c is a schematic diagram of a real-time mode workflow of the debugging system provided in the present embodiment, and fig. 1d is a schematic diagram of a playback mode workflow of the debugging system.
Real-time mode:
Responding to the deployment instruction, automatically deploying the visual service of the vehicle-mounted domain control terminal, starting the service, and waiting for data access;
displaying professional signal real-time alignment and rendering effects;
checking the state of a professional signal channel, fault signals and performance state data of a vehicle-mounted domain control terminal;
starting signal recording according to the recording period;
marking abnormality, namely selecting an abnormal option mark when abnormality occurs in the recording process, so that off-line cutting is facilitated;
and finishing the recording operation, sorting off-line data, and uploading the data platform.
Playback mode:
Responding to the data cutting request, cutting the data packet, and taking off-line data near the abnormal mark;
Selecting a data playback function, selecting the clipped data, and playing back the clipped data. Still the result after alignment at playback;
focusing on the specified professional signal result by using the implicit function;
Positioning to abnormal data frames, such as single-frame playing, pausing, dragging a progress bar and the like by using a playback control tool;
converting the data packet into json file or csv file by using a format conversion function;
and positioning to a certain line of the professional signal json file or csv file according to the time stamp on the abnormal frame picture, and carrying out data analysis.
Example two
Fig. 2 is a schematic structural diagram of an intelligent driving debugging device according to a second embodiment of the present invention. The device is integrated at the computer end of the debugging system, as shown in fig. 2, and the device comprises: the data clipping range determination module 210, the target range data clipping module 220, and the data restoration module 230. Wherein:
The data clipping range determining module 210 is configured to determine a data clipping range according to an abnormal mark in an intelligent driving scene of the vehicle to be tested in response to the data clipping request;
the target range data clipping module 220 is configured to clip a driving scene segment from the intelligent driving scene according to the data clipping range;
The data restoring module 230 is configured to restore the scenario modeling data of multiple dimensions corresponding to the driving scenario segment in response to a data restoring request, so that a debugger performs intelligent driving debugging on the vehicle to be tested according to the scenario modeling data of multiple dimensions corresponding to the driving scenario segment.
The technical scheme of the embodiment of the invention is applied to a computer end of a debugging system, and the data cutting range is determined according to the abnormal mark in the intelligent driving scene of the vehicle to be tested by responding to the data cutting request; cutting out driving scene fragments from the intelligent driving scene according to the data cutting range; and responding to the data restoration request, restoring the multi-dimensional scene modeling data corresponding to the driving scene segment, so that the debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment. By adopting the technical means of anomaly marking and data clipping analysis, the problems that the debugging efficiency is low and the debugging result is inaccurate are generally caused for a complex intelligent driving control algorithm of a vehicle by manually observing the whole driving scene and analyzing the algorithm in the prior art, the debugging efficiency is improved, and the accuracy of the debugging result is improved.
Optionally, the intelligent driving debugging device further includes an intelligent driving scene construction module, including:
The scene modeling data acquisition unit is used for acquiring scene modeling data of multiple dimensions of the vehicle to be tested in the intelligent driving test process of the vehicle to be tested;
and the intelligent driving scene construction unit is used for performing time alignment and rendering processing on the scene modeling data of the plurality of dimensions of the vehicle to be tested so as to construct an intelligent driving scene of the vehicle to be tested.
Optionally, the intelligent driving scene construction unit may be specifically configured to:
according to the receiving time of the scene modeling data of the multiple dimensions of the vehicle to be detected at the computer end or the satellite synchronous clock of the global positioning system, performing time alignment processing on the scene modeling data of the multiple dimensions of the vehicle to be detected to obtain a time alignment processing result;
And rendering the time alignment processing result to construct an intelligent driving scene of the vehicle to be detected.
Optionally, the data clipping range determining module 210 may specifically be configured to:
determining abnormal time in the intelligent driving scene according to the abnormal mark;
and determining the data clipping range according to the preset time periods before and after the abnormal time.
Optionally, the anomaly flag is marked by:
Acquiring each target driving parameter of the vehicle to be tested in a specified time range from the intelligent driving scene; the target driving parameters comprise the absolute speed, the relative speed, the acceleration and the position of the vehicle to be tested;
drawing curves of the target running parameters at each moment in the appointed time range to obtain parameter curves corresponding to each moment in the appointed time range;
comparing and analyzing each parameter curve according to time sequence, and determining the error of each target running parameter at adjacent time;
and determining abnormal time from the specified time range according to the error, and marking.
Optionally, the anomaly flag is marked by:
in response to a first marking instruction, adding an abnormal marking in the intelligent driving scene; and the first marking instruction is issued through a user interface of the computer after the user observes the abnormal position of the driving environment in the intelligent driving scene.
Optionally, the anomaly flag is marked by:
In response to a second marking instruction, marking abnormal moments in the intelligent driving scene; and the second marking instruction is issued by a user through a user interface of the computer end according to the path state and fault signals of the scene modeling data of the multiple dimensions of the vehicle to be tested.
The intelligent driving debugging device provided by the embodiment of the invention can execute the intelligent driving debugging method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example III
Fig. 3 is a schematic structural diagram of a debug system according to a third embodiment of the present invention. As shown in fig. 3, the system includes a vehicle-mounted domain control end 310 and a computer end 320 of a vehicle to be tested; the vehicle-mounted domain control end 310 comprises a data acquisition module 3101;
the data acquisition module is used for acquiring scene modeling data of multiple dimensions of the vehicle to be tested in the intelligent driving test process and sending the scene modeling data of the multiple dimensions to the computer terminal;
The computer end is used for executing the intelligent driving debugging method according to any embodiment of the invention according to the scene modeling data of the plurality of dimensions sent by the vehicle-mounted domain control end.
The debugging system provided by the embodiment of the invention can improve the debugging efficiency and the accuracy of the debugging result.
Example IV
Fig. 4 shows a schematic diagram of an electronic device 400 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers or various forms of mobile devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 400 includes at least one processor 401, and a memory communicatively connected to the at least one processor 401, such as a Read Only Memory (ROM) 402, a Random Access Memory (RAM) 403, etc., in which the memory stores a computer program executable by the at least one processor, and the processor 401 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 402 or the computer program loaded from the storage unit 408 into the Random Access Memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 may also be stored. The processor 401, the ROM 402, and the RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
Various components in electronic device 400 are connected to I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, etc.; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Processor 401 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 401 performs the various methods and processes described above, such as the intelligent drive debugging method.
In some embodiments, the intelligent drive debugging method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 400 via the ROM 402 and/or the communication unit 409. When the computer program is loaded into RAM 403 and executed by processor 401, one or more steps of the intelligent drive debugging method described above may be performed. Alternatively, in other embodiments, the processor 401 may be configured to perform the intelligent driving debugging method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (11)
1. An intelligent driving debugging method applied to a computer end of a debugging system is characterized by comprising the following steps:
Responding to the data clipping request, and determining a data clipping range according to an abnormal mark in an intelligent driving scene of the vehicle to be detected;
cutting out driving scene fragments from the intelligent driving scene according to the data cutting range;
And responding to a data restoration request, and restoring the multi-dimensional scene modeling data corresponding to the driving scene segment so that a debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment.
2. The method of claim 1, wherein the intelligent driving scenario is constructed by:
Acquiring scene modeling data of multiple dimensions of the vehicle to be tested in the intelligent driving test process of the vehicle to be tested;
And performing time alignment and rendering processing on the scene modeling data of the multiple dimensions of the vehicle to be tested so as to construct an intelligent driving scene of the vehicle to be tested.
3. The method of claim 2, wherein time-aligning and rendering the multi-dimensional scene modeling data of the vehicle under test to construct an intelligent driving scene of the vehicle under test comprises:
according to the receiving time of the scene modeling data of the multiple dimensions of the vehicle to be detected at the computer end or the satellite synchronous clock of the global positioning system, performing time alignment processing on the scene modeling data of the multiple dimensions of the vehicle to be detected to obtain a time alignment processing result;
And rendering the time alignment processing result to construct an intelligent driving scene of the vehicle to be detected.
4. The method of claim 1, wherein determining the data clipping range based on anomaly markers in the intelligent driving scenario of the vehicle under test comprises:
determining abnormal time in the intelligent driving scene according to the abnormal mark;
and determining the data clipping range according to the preset time periods before and after the abnormal time.
5. The method of claim 1, wherein the anomaly signature is marked by:
Acquiring each target driving parameter of the vehicle to be tested in a specified time range from the intelligent driving scene; the target driving parameters comprise the absolute speed, the relative speed, the acceleration and the position of the vehicle to be tested;
drawing curves of the target running parameters at each moment in the appointed time range to obtain parameter curves corresponding to each moment in the appointed time range;
comparing and analyzing each parameter curve according to time sequence, and determining the error of each target running parameter at adjacent time;
and determining abnormal time from the specified time range according to the error, and marking.
6. The method of claim 1, wherein the anomaly signature is marked by:
in response to a first marking instruction, adding an abnormal marking in the intelligent driving scene; and the first marking instruction is issued through a user interface of the computer after the user observes the abnormal position of the driving environment in the intelligent driving scene.
7. The method of claim 1, wherein the anomaly signature is marked by:
In response to a second marking instruction, marking abnormal moments in the intelligent driving scene; and the second marking instruction is issued by a user through a user interface of the computer end according to the transmission path state and fault signals of the scene modeling data of the multiple dimensions of the vehicle to be tested.
8. An intelligent driving debugging device integrated at a computer end of a debugging system, which is characterized by comprising:
the data cutting range determining module is used for responding to the data cutting request and determining the data cutting range according to the abnormal mark in the intelligent driving scene of the vehicle to be detected;
The target range data clipping module is used for clipping driving scene fragments from the intelligent driving scene according to the data clipping range;
The data restoration module is used for responding to the data restoration request and restoring the multi-dimensional scene modeling data corresponding to the driving scene segment so that the debugger can intelligently drive and debug the vehicle to be tested according to the multi-dimensional scene modeling data corresponding to the driving scene segment.
9. A debug system, comprising: a vehicle-mounted domain control end and a computer end of a vehicle to be tested; the vehicle-mounted domain control end comprises a data acquisition module;
the data acquisition module is used for acquiring scene modeling data of multiple dimensions of the vehicle to be tested in the intelligent driving test process and sending the scene modeling data of the multiple dimensions to the computer terminal;
The computer end is used for executing the intelligent driving debugging method according to the scene modeling data of the plurality of dimensions, which is sent by the vehicle-mounted domain control end.
10. An electronic device, the electronic device comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the intelligent driving debugging method of any of claims 1-7.
11. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the intelligent driving debugging method of any of claims 1-7 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410244074.3A CN118276481A (en) | 2024-03-04 | 2024-03-04 | Intelligent driving debugging method, device, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410244074.3A CN118276481A (en) | 2024-03-04 | 2024-03-04 | Intelligent driving debugging method, device, system, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118276481A true CN118276481A (en) | 2024-07-02 |
Family
ID=91639196
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410244074.3A Pending CN118276481A (en) | 2024-03-04 | 2024-03-04 | Intelligent driving debugging method, device, system, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118276481A (en) |
-
2024
- 2024-03-04 CN CN202410244074.3A patent/CN118276481A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP4030299A2 (en) | Method, device, and system for simulation test | |
CN111858318B (en) | Response time testing method, device, equipment and computer storage medium | |
CN112994980B (en) | Time delay test method, device, electronic equipment and storage medium | |
US20210374438A1 (en) | Validating object detection hardware and algorithms | |
CN109558297A (en) | EMS memory management process and device | |
WO2019047663A1 (en) | Video format-based end-to-end automatic driving data storage method and device | |
EP4020312B1 (en) | Traffic light recognition method, apparatus, storage medium and program product | |
KR20230088332A (en) | Data annotation methods, devices, systems, devices and storage media | |
EP2894850B1 (en) | Video playback system and method | |
CN112254977B (en) | Data processing method and device based on automatic emergency braking system | |
CN113380229A (en) | Voice response speed determination method, related device and computer program product | |
CN118276481A (en) | Intelligent driving debugging method, device, system, electronic equipment and storage medium | |
CN116486277A (en) | Remote sensing load image interpretation method and remote sensing load quick-looking system | |
CN115308754A (en) | Laser radar point cloud simulation time delay test method and system | |
CN115891868A (en) | Fault detection method, device, electronic apparatus, and medium for autonomous vehicle | |
CN115348441A (en) | Time delay measuring method, system, device, equipment and storage medium | |
CN116642511A (en) | AR navigation image rendering method and device, electronic equipment and storage medium | |
CN115384526A (en) | Debugging system and debugging method | |
CN111597940A (en) | Method and device for evaluating rendering model, electronic equipment and readable storage medium | |
CN111538407A (en) | Information interaction method and device and electronic equipment | |
CN113411368B (en) | Data synchronization method and device, storage medium and electronic equipment | |
CN116827938B (en) | Data recharging method, system and storage medium | |
CN114520855A (en) | Image frame rendering method and device based on multi-module data and storage medium | |
CN115862321A (en) | Scene data acquisition method, device, equipment and storage medium | |
CN117421203A (en) | Simulation test method based on real vehicle data recharging and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination |