CN116206441A - Optimization method, device, equipment and medium of automatic driving planning model - Google Patents
Optimization method, device, equipment and medium of automatic driving planning model Download PDFInfo
- Publication number
- CN116206441A CN116206441A CN202211723076.8A CN202211723076A CN116206441A CN 116206441 A CN116206441 A CN 116206441A CN 202211723076 A CN202211723076 A CN 202211723076A CN 116206441 A CN116206441 A CN 116206441A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- traffic
- traffic data
- planning model
- 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 65
- 238000005457 optimization Methods 0.000 title claims abstract description 30
- 230000006870 function Effects 0.000 claims description 15
- 230000008447 perception Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 230000006872 improvement Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000001914 filtration Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- BLRPTPMANUNPDV-UHFFFAOYSA-N Silane Chemical compound [SiH4] BLRPTPMANUNPDV-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the specification discloses an optimization method, device, equipment and medium of an automatic driving planning model. The method comprises the following steps: the traffic data reported by the road side equipment is obtained through the platform, then the target traffic data matched with the preset traffic scene recognition rule is determined from the traffic data, so that the target vehicle related to the target traffic data is determined, and the manual driving data of the target vehicle in a specified time period is obtained, so that the automatic driving planning model is optimized by utilizing the manual driving data and the traffic data. Because the traffic data is not required to be acquired by the vehicle through the carrying sensor, and the road side equipment can acquire a large number of traffic data under different preset traffic scenes in a short time, the acquisition time of the traffic data is effectively shortened, and the optimization efficiency of the automatic driving planning model is further improved.
Description
Technical Field
The present disclosure relates to the field of computer data processing technologies, and in particular, to a method, an apparatus, a device, and a medium for optimizing an autopilot planning model.
Background
With the development of intelligent driving technology, an intelligent driving vehicle can utilize a platform, such as an automatic driving planning model at a cloud control platform, to generate a driving strategy in the driving process, at present, the training iterative optimization of the automatic driving planning model is usually carried out by utilizing a single vehicle in the driving process, acquiring environmental data including traffic data of other vehicles in a sensing range of the sensor through the sensor, and then utilizing the environmental data acquired by the sensor to check the iteratively optimized automatic driving planning model, namely, utilizing a self-vehicle data recharging method to carry out the on-loop test and iterative optimization of the model for the automatic driving planning model in an off-line manner; because the automatic driving planning model of the same scene is tested, a plurality of vehicles are required to repeatedly conduct the reciprocating driving test in the same area so as to acquire environment data of a sufficient quantity of the same scene, the time is long, and the automatic driving planning model cannot be quickly updated and iterated.
Based on this, how to provide a method for optimizing an autopilot planning model so that an autopilot decision planning algorithm can be quickly iterated and optimized becomes a technical problem to be solved.
Disclosure of Invention
The embodiment of the specification provides an optimization method, device and equipment of an automatic driving planning model, so as to solve the problem of slow optimization iteration in the existing model optimization method.
In order to solve the above technical problems, the embodiments of the present specification are implemented as follows:
the embodiment of the specification provides an optimization method of an automatic driving planning model, which may include:
the platform acquires traffic data reported by road side equipment;
determining target traffic data matched with a preset traffic scene recognition rule from the traffic data;
determining a target vehicle related to the target traffic data;
acquiring manual driving data of the target vehicle in a specified time period; the appointed time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment;
optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
An optimization device for an autopilot planning model provided in an embodiment of the present disclosure may include:
The traffic data acquisition module is used for acquiring traffic data reported by the road side equipment by the platform;
the target traffic data determining module is used for determining target traffic data matched with a preset traffic scene recognition rule from the traffic data;
a target vehicle determining module, configured to determine a target vehicle related to the target traffic data;
the manual driving data acquisition module is used for acquiring manual driving data of the target vehicle in a specified time period; the appointed time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment;
the model optimization module is used for optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
An optimization device for an autopilot planning model provided in an embodiment of the present specification may include:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
Acquiring traffic data reported by road side equipment;
determining target traffic data matched with a preset traffic scene recognition rule from the traffic data;
determining a target vehicle related to the target traffic data;
acquiring manual driving data of the target vehicle in a specified time period; the appointed time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment;
optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
Embodiments of the present disclosure provide a computer readable medium having computer readable instructions stored thereon that are executable by a processor to implement a method of optimizing an autopilot planning model.
At least one embodiment of the present disclosure can achieve the following beneficial effects: the traffic data reported by the road side equipment is obtained through the platform, so that target traffic data matched with a preset traffic scene recognition rule is determined from the traffic data, and therefore a target vehicle related to the target traffic data is determined, manual driving data of the target vehicle is obtained when the target vehicle is in a specified time period under a preset traffic scene, and the manual driving data and the traffic data are utilized to optimize an automatic driving planning model. The data for training the automatic driving planning model can be acquired through the road side equipment by utilizing the platform without acquiring the data through the onboard sensor by utilizing the vehicle, and the road side equipment can acquire a large amount of traffic data under different preset traffic scenes in a short time, so that the acquisition time of the traffic data is shortened, and meanwhile, the target vehicle related to the target traffic data meeting the preset traffic scene recognition rule is determined from the traffic data, so that the manual driving data of the target vehicle in a specified time period can be acquired from the traffic data, the acquisition time of the manual driving data is shortened, and the optimization efficiency of the automatic driving planning model is improved.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a schematic flow chart of an optimization method of an autopilot planning model according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of an optimization device for an autopilot planning model according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an optimizing apparatus for an autopilot planning model according to an embodiment of the present disclosure.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of one or more embodiments of the present specification more clear, the technical solutions of one or more embodiments of the present specification will be clearly and completely described below in connection with specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without undue burden, are intended to be within the scope of one or more embodiments herein.
The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.
In the prior art, a bicycle is generally used for carrying a sensor in an automatic driving process, environmental data including other vehicle traffic data in a sensing range of the sensor is collected through the sensor, and then the environmental data collected by the sensor is used for verifying the iterative optimized automatic driving planning model, namely, the model is subjected to on-loop test and iterative optimization by offline aiming at the automatic driving planning model by using a bicycle data recharging method; because the automatic driving planning model of the same scene is tested, a plurality of vehicles are required to repeatedly conduct the reciprocating driving test in the same area so as to acquire environment data of a sufficient quantity of the same scene, the time is long, and the automatic driving planning model cannot be quickly updated and iterated.
In order to solve the drawbacks of the prior art, the present solution provides the following embodiments:
fig. 1 is a schematic flow chart of an optimization method of an autopilot planning model according to an embodiment of the present disclosure. From the program perspective, the execution subject of the flow may be a program or an application client that is installed on an application server.
As shown in fig. 1, the process may include the steps of:
step 102: and the platform acquires traffic data reported by the road side equipment.
In this embodiment of the present disclosure, the platform may be a cloud control platform, and of course, may also be other platforms that may be used to receive traffic data, which is not specifically limited herein.
In this embodiment of the present disclosure, the road side device may include a device for acquiring video data of vehicle operation, for example, a camera, and may further include other devices that may be used to acquire vehicle operation data, such as a radar device and a road side computing unit (Roadside ComputingUnit, abbreviated as RCU in english), where the road side device may acquire traffic data within a sensing range of the road side device, and may report the acquired traffic data to a cloud control platform.
In the embodiment of the present specification, the traffic data may include operation data of vehicles within a perception range of the road side perception device.
In the embodiment of the specification, the platform can acquire a large amount of traffic data in a short time through the road side equipment, so that the automatic driving planning model is optimized and verified by utilizing the large amount of traffic data.
Step 104: and determining target traffic data matched with a preset traffic scene recognition rule from the traffic data.
In this embodiment of the present disclosure, the preset traffic scene recognition rule is any one of traffic scene recognition rules, and in practical application, it may be determined whether the running data of the vehicle in the open circuit side sensing device meets the preset traffic scene recognition rule, so as to determine target traffic data meeting different preset traffic scene recognition rules from the traffic data, so as to obtain driving data of different traffic scenes subsequently, and further train and optimize an automatic driving planning model of different traffic scenes.
In practical applications, the traffic scene recognition rule may include: the left lane overtaking recognition rule, the right lane overtaking recognition rule, the outgoing ramp recognition rule, the left lane changing recognition rule, the right lane changing recognition rule, etc., as will be understood by those skilled in the art, the traffic scene recognition rule may also include other traffic scene recognition rules, which are not specifically limited herein.
Step 106: and determining the target vehicle related to the target traffic data.
In this embodiment of the present disclosure, the target traffic data may be operation data of the target vehicle, where the target vehicle is within a perception range of the roadside apparatus.
Step 108: acquiring manual driving data of the target vehicle in a specified time period; the specified time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment.
In the embodiment of the present specification, assuming that the target vehicle is not in a traffic scene or no traffic scene event occurs, the vehicle may generally travel at a preset speed, a preset acceleration, and the vehicle may include the target vehicle.
In this embodiment of the present disclosure, the specified time period may be a time period in which the target vehicle is in a preset traffic scene, and the preset time range may be specifically set according to a duration of the preset traffic scene, or may be set to a specific fixed value, which is not specifically limited herein; the manual driving data may be data for manually driving the target vehicle for a specified period of time, and the manual driving data may include: the target vehicle may include vehicle position data, vehicle speed data, vehicle acceleration data, etc. over a specified period of time, it being understood that the manual driving data may also be determined from traffic data.
In the embodiment of the present disclosure, the manual driving data of the target vehicle in the same preset traffic scene may be obtained, so that the manual driving data of the target vehicle in the same preset traffic scene is used for training the preset traffic scene for the automatic driving planning model, and in practical application, the manual driving data of the target vehicle in different preset traffic scenes may be used for training the automatic driving planning model in different traffic scenes.
Step 110: optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
In the embodiment of the specification, the manual driving data can be used as an output target of the automatic driving planning model, the traffic data reported by the road side equipment is used as training data of the automatic driving planning model, the traffic data is input into the automatic driving planning model to obtain the automatic driving data, and the automatic driving data is compared with the manual driving data, so that the automatic driving planning model is trained.
It should be understood that the method according to one or more embodiments of the present disclosure may include the steps in which some of the steps are interchanged as needed, or some of the steps may be omitted or deleted.
In the method in fig. 1, traffic data reported by road side equipment is obtained through a platform, so that target traffic data matched with a preset traffic scene recognition rule is determined from the traffic data, and thus a target vehicle related to the target traffic data is determined, manual driving data of the target vehicle is obtained by manually driving the target vehicle in a specified time period under a preset traffic scene, and the automatic driving planning model is optimized by utilizing the manual driving data and the traffic data. The data for training the automatic driving planning model can be acquired through the road side equipment by utilizing the platform without acquiring the data through the onboard sensor by utilizing the vehicle, and the road side equipment can acquire a large amount of traffic data under different preset traffic scenes in a short time, so that the acquisition time of the traffic data is shortened, and meanwhile, the target vehicle related to the target traffic data meeting the preset traffic scene recognition rule is determined from the traffic data, so that the manual driving data of the target vehicle in a specified time period can be acquired from the traffic data, the acquisition time of the manual driving data is shortened, and the optimization efficiency of the automatic driving planning model is further improved.
Based on the method of fig. 1, the examples of the present specification also provide some specific implementations of the method, as described below.
Optionally, the traffic data reported by the road side device may specifically include:
the running data of the vehicle in the sensing range of the road test equipment, which is acquired by the road side equipment, specifically may include: at least one of vehicle position data, vehicle speed data, vehicle acceleration data, and vehicle heading angle data.
In the embodiment of the present specification, an implementation manner of determining target traffic data matching with a preset traffic scene recognition rule from the traffic data is also provided.
Specifically, the determining, from the traffic data, the target traffic data that matches with the preset traffic scene recognition rule may specifically include:
judging whether the running data of the vehicle meets a preset traffic scene recognition rule or not to obtain a judging result; the vehicle is any vehicle in the sensing range of the road side equipment; the preset traffic scene recognition rule comprises the following steps: left lane overtaking recognition rule, right lane overtaking recognition rule, driving-out ramp recognition rule, left lane changing recognition rule and right lane changing recognition rule.
If the judgment result indicates that the traffic data of the vehicle meets the preset traffic scene recognition rule, then
And determining the traffic data of the vehicle as target traffic data matched with the preset traffic scene recognition rule.
In practical application, different preset traffic scene recognition rules are different, and the recognized data corresponding to the rules are different, so that whether the running data of the vehicle meets the preset traffic scene recognition rules can be judged according to the running data of any vehicle in the perception range of the road side equipment, and the target vehicle with the traffic scene event can be determined according to the target traffic data meeting the preset traffic scene recognition rules.
In the present embodiment, for example, the left lane change recognition rule may be expressed as: the course angle of the vehicle deflects leftwards compared with the previous moment, the course angle of the vehicle deflects less or deflects less than a preset threshold value compared with the previous moment at a certain moment, and the position of the vehicle changes from a first lane to a second lane; in practical application, the preset traffic scene recognition rule may be specifically set according to needs, which is not described herein.
In the embodiment of the present disclosure, the traffic data reported by the roadside device generally includes operation data of all vehicles within a perception range of the roadside device, and as can be understood by those skilled in the art, redundant data that has no influence on the operation of the target vehicle is also included, so that the quality of training data of the optimized autopilot planning model can be effectively improved by reducing the redundant data, thereby improving the accuracy of the autopilot planning model.
Based on this, before the traffic data reported by the road side device and the manual driving data are optimized for the automatic driving planning model, the method may further include:
and determining relevant traffic data of a traffic scene related to the target vehicle from the traffic data, wherein the relevant traffic data specifically comprises the following steps: the operation data of the target vehicle, the operation data of the appointed vehicle in the preset range of the target vehicle and the relative operation data of the appointed vehicle and the target vehicle.
The optimizing the automatic driving planning model by using the traffic data reported by the road side equipment and the manual driving data specifically may include:
and optimizing an automatic driving planning model applicable to the traffic scene by utilizing the related traffic data of the traffic scene related to the target vehicle and the manual driving data.
In this embodiment of the present disclosure, the preset range may be specifically set according to needs, for example, assuming that a traffic scene related to the target vehicle is a lane change of a left lane, the preset range may include a range within a first preset distance from the target vehicle in a current lane of the target vehicle and a range within a second preset distance from the target vehicle in a left lane; those skilled in the art will appreciate that different traffic scenarios may set different preset ranges, and are not specifically limited herein.
In the embodiment of the present specification, the specified vehicle is a vehicle that is within a preset range and that may affect the operation of the target vehicle.
In the embodiment of the present specification, the related traffic data of the traffic scene to which the target vehicle relates may include the operation data of the specified vehicle that affects the operation of the target vehicle, and the operation data of the target vehicle, and may further include the operation data of the target vehicle with respect to the specified vehicle calculated from the operation data of the target vehicle and the operation data of the specified vehicle.
In the embodiment of the specification, the redundant data is reduced by selecting the related traffic data of the traffic related to the target vehicle, so that the quality of training data of the optimized automatic driving planning model is effectively improved, and the accuracy of the optimized automatic driving planning model is further improved.
In the embodiment of the present disclosure, different drivers will also have different driving operations in the same traffic scene, for example, for the same traffic scene, some drivers have large force of stepping on the brake and the accelerator, and some drivers have small force of stepping on the brake and the accelerator, so that there is a large difference in manual driving data in the same traffic scene.
Based on this, before the traffic data reported by the road side device and the manual driving data are optimized for the automatic driving planning model, the method may further include:
clustering the manual driving data of the target vehicle in the specified time period to obtain clustered manual driving data of various types.
Determining a specified automatic driving planning model applicable to the clustered manual driving data of a specified type; the specified type of clustered manual driving data is any one of a plurality of types of clustered manual driving data.
Determining the appointed target vehicle related to the appointed type of clustered manual driving data; the specified type of post-cluster manual driving data is data generated by manually driving the specified target vehicle in the specified time period.
Determining a designated road side device according to the vehicle position data of the designated target vehicle in the designated time period; the specified target vehicle is located within a perception range of the specified roadside apparatus within the specified time period.
And the platform acquires the appointed traffic data reported by the appointed road side equipment.
The optimizing the automatic driving planning model by using the traffic data reported by the road side equipment and the manual driving data specifically may include:
And optimizing the specified automatic driving planning model by utilizing the clustered manual driving data of the specified type and the specified traffic data.
In the embodiment of the present specification, the specified time period may be a time period in which the target vehicle is in a traffic scene, and it is understood that the specified time periods related to different target vehicles may be different.
In practical applications, the manual driving data of the target vehicle in the specified time period may be clustered, so that the manual driving data may be divided into driving data of different driving types, for example, aggressive driving data and conservative driving data, and may be divided into driving data of other driving types, which is not limited specifically herein. The clustered manual driving data of the specified type can be aggressive manual driving data, can also be conservative manual driving data, and can also be manual driving data of other driving types. The specified automatic driving planning model can be a model which is trained in advance and is suitable for the manual driving data after the specified type of clustering, and further optimization is required.
In the embodiment of the specification, the clustered manual driving data with different specified types and the corresponding specified traffic data are optimized for the specified automatic driving planning model, so that a user can select the automatic driving planning model with different types, and the experience of automatic driving of the user is improved.
In practical applications, it is often necessary to determine whether the autopilot planning model is optimized to prevent the model from overfitting.
Based on this, the optimizing the traffic data reported by the road side device and the manual driving data for the automatic driving planning model may specifically include:
and processing the traffic data by utilizing the automatic driving planning model to obtain the automatic driving data of the target vehicle.
And determining the accuracy of the automatic driving planning model according to the manual driving data and the automatic driving data.
And if the precision of the automatic driving planning model is smaller than the preset precision, adjusting model parameters until the precision of the automatic driving planning model is larger than or equal to the preset precision.
In an embodiment of the present disclosure, the determining, according to the manual driving data and the automatic driving data, the accuracy of the automatic driving planning model may specifically include: processing traffic data reported by road side equipment by using the optimized automatic driving model to obtain automatic driving data; meanwhile, the preset quantity of manual driving data can be obtained, and filtering and cleaning can be carried out on the manual driving data of the preset data so as to clean out extreme value data and invalid data; the filtering processing method may include: and (3) one or more of mean value filtering, point cloud filtering and Kalman filtering, and then averaging the manual driving data after filtering and cleaning so as to compare the automatic driving data with the average value of the manual driving data after filtering and cleaning, wherein if the difference between the automatic driving data and the average value is smaller, the higher the accuracy of the automatic driving planning model is indicated.
In this embodiment of the present disclosure, the accuracy of the autopilot planning model may be represented by a difference between autopilot data and the average value, and if the accuracy of the autopilot planning model is less than a preset accuracy, parameters of the autopilot planning model need to be continuously adjusted.
In practical application, it is generally possible to determine whether the difference between the autopilot data output by the autopilot planning model after the current optimization and adjustment and the average value is smaller than the difference between the autopilot data output by the autopilot planning model after the last optimization and adjustment and the average value; if the number of the parameters is smaller than the number, judging that the parameter optimization adjustment direction of the number of the automatic driving planning models is correct, and guiding the optimization of the automatic driving planning models.
In practical application, the vehicle with the data uploading function can report the vehicle running data of the vehicle in real time, so that more and more accurate vehicle running data can be obtained through the vehicle with the data uploading function, and the accuracy and efficiency of optimizing the automatic driving planning model are improved.
Based on this, the method may further include:
the platform acquires vehicle running data reported by a vehicle with a data uploading function; the vehicle travel data includes vehicle driving parameters and vehicle position data.
The determining, from the traffic data, target traffic data that matches with a preset traffic scene recognition rule may specifically include:
and determining target traffic data matched with a preset traffic scene recognition rule from the traffic data and the vehicle driving data.
In the embodiment of the present specification, the vehicle having the data uploading function may report vehicle running data of the vehicle to the vehicle bus, and the platform may obtain the vehicle running data by communicating with the vehicle bus, where the vehicle running data may include: the vehicle position data and the vehicle position positioning time may be a time when the vehicle is positioned to a vehicle position corresponding to the vehicle position data.
In practical application, the traffic data reported by the road side equipment may include the running data of the vehicle in the perception range of the road side perception equipment, which is acquired by the road side equipment, and the time when the road side equipment acquires the running data of the vehicle; the traffic data may include vehicle location data in particular.
In the embodiment of the present disclosure, it is assumed that the time when the road side device obtains the vehicle running data and the time when the vehicle is located at the same time, and the vehicle position data carried in the vehicle running data reported by the vehicle is the same as the vehicle position indicated by the vehicle position data carried in the traffic data reported by the road side device, which indicates that the vehicle running data and the vehicle corresponding to the traffic data are the same vehicle, so that the vehicle running data and the traffic data can be combined to determine whether the vehicle running data and the traffic data meet the preset traffic scene recognition rule, thereby determining the target traffic data matched with the preset traffic scene recognition rule from the traffic data and the vehicle running data.
Based on the same thought, the embodiment of the specification also provides a device corresponding to the method. Fig. 2 is a schematic structural diagram of an optimizing apparatus corresponding to the autopilot planning model of fig. 1 according to an embodiment of the present disclosure. As shown in fig. 2, the apparatus may include:
the traffic data acquisition module 202 is configured to acquire traffic data reported by the roadside device by using a platform;
a target traffic data determining module 204, configured to determine target traffic data matched with a preset traffic scene recognition rule from the traffic data;
a target vehicle determination module 206 for determining a target vehicle to which the target traffic data relates;
a manual driving data obtaining module 208, configured to obtain manual driving data of the target vehicle in a specified time period; the appointed time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment;
the model optimization module 210 is configured to optimize an automatic driving planning model by using traffic data reported by the roadside device and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
The present examples also provide some embodiments of the method based on the apparatus of fig. 2, as described below.
Optionally, the target traffic data determining module 204 may specifically be configured to:
judging whether the running data of the vehicle meets a preset traffic scene recognition rule or not to obtain a judging result; the vehicle is any vehicle in the sensing range of the road side equipment; the preset traffic scene recognition rule comprises the following steps: left lane overtaking recognition rule, right lane overtaking recognition rule, driving-out ramp recognition rule, left lane changing recognition rule and right lane changing recognition rule.
If the judgment result indicates that the traffic data of the vehicle meets the preset traffic scene recognition rule, then
And determining the traffic data of the vehicle as target traffic data matched with the preset traffic scene recognition rule.
Optionally, the apparatus in fig. 2 may further include:
the related traffic data determining module is configured to determine related traffic data of a traffic scene related to the target vehicle from the traffic data, where the related traffic data specifically may include: the operation data of the target vehicle, the operation data of the appointed vehicle in the preset range of the target vehicle and the relative operation data of the appointed vehicle and the target vehicle.
The model optimization module 210 may specifically be configured to:
and optimizing an automatic driving planning model applicable to the traffic scene by utilizing the related traffic data of the traffic scene related to the target vehicle and the manual driving data.
Optionally, the apparatus in fig. 2 may further include:
and the clustering module is used for clustering the manual driving data of the target vehicle in the specified time period to obtain multiple types of clustered manual driving data.
The specified model determining module is used for determining a specified automatic driving planning model applicable to the clustered manual driving data of the specified type; the specified type of clustered manual driving data is any one of a plurality of types of clustered manual driving data.
The specified target vehicle determining module is used for determining the specified target vehicles related to the clustered manual driving data of the specified type; the clustered manual driving data of the specified type is data generated by manually driving the specified target vehicle in the specified time period;
a designated road side equipment determining module, configured to determine a designated road side equipment according to vehicle position data of the designated target vehicle in the designated time period; the specified target vehicle is positioned in the perception range of the specified road side equipment in the specified time period;
The specified traffic data acquisition module is used for acquiring the specified traffic data reported by the specified road side equipment by the platform;
the model optimization module 210 may specifically be configured to:
and optimizing the specified automatic driving planning model by utilizing the clustered manual driving data of the specified type and the specified traffic data.
Optionally, the model optimization module 210 may specifically be configured to:
and processing the traffic data by utilizing the automatic driving planning model to obtain the automatic driving data of the target vehicle.
And determining the accuracy of the automatic driving planning model according to the manual driving data and the automatic driving data.
And if the precision of the automatic driving planning model is smaller than the preset precision, adjusting parameters of the automatic driving planning model until the precision of the automatic driving planning model is larger than or equal to the preset precision.
Optionally, the apparatus in fig. 2 may further include:
the vehicle running data acquisition module is used for acquiring vehicle running data reported by a vehicle with a data uploading function by the platform; the vehicle travel data includes vehicle driving parameters and vehicle position data.
The target traffic data determination module 204 may be specifically configured to:
and determining target traffic data matched with a preset traffic scene recognition rule from the traffic data and the vehicle driving data. .
Based on the same thought, the embodiment of the specification also provides equipment corresponding to the method.
Fig. 3 is a schematic structural diagram of an optimizing apparatus corresponding to the autopilot planning model of fig. 1 according to an embodiment of the present disclosure. As shown in fig. 3, the apparatus 300 may include:
at least one processor 310; the method comprises the steps of,
a memory 330 communicatively coupled to the at least one processor; wherein,,
the memory 330 stores instructions 320 executable by the at least one processor 310, the instructions being executable by the at least one processor 310 to enable the at least one processor 310 to:
and the platform acquires traffic data reported by the road side equipment.
And determining target traffic data matched with a preset traffic scene recognition rule from the traffic data.
And determining the target vehicle related to the target traffic data.
Acquiring manual driving data of the target vehicle in a specified time period; the specified time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment.
Optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
Based on the same thought, the embodiment of the specification also provides a computer readable medium corresponding to the method. Computer readable instructions stored on a computer readable medium are executable by a processor to implement the above-described method of optimizing an autopilot planning model:
and the platform acquires traffic data reported by the road side equipment.
And determining target traffic data matched with a preset traffic scene recognition rule from the traffic data.
And determining the target vehicle related to the target traffic data.
Acquiring manual driving data of the target vehicle in a specified time period; the specified time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment.
Optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the optimization device of the autopilot planning model shown in fig. 3, the description is relatively simple, since it is substantially similar to the method embodiment, as relevant see the partial description of the method embodiment.
In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (ProgrammableLogicDevice, PLD), such as a Field programmable gate array (Field ProgrammableGateArray, FPGA), is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (HardwareDescriptionLanguage, HDL), and HDL is not only one but a plurality of kinds, such as ABEL (AdvancedBooleanExpressionLanguage), AHDL (Altera HardwareDescriptionLanguage), confluence, CUPL (CornellUniversity ProgrammingLanguage), HDCal, JHDL (javahard description language), lava, lola, myHDL, PALASM, RHDL (rubyhardhard description language), and so on, and VHDL (Very-High-SpeedIntegratedCircuitHardware DescriptionLanguage) and Verilog are most commonly used at present. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application SpecificIntegratedCircuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC625D, atmelAT91SAM, microchipPIC F26K20 and silicane labsc8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash memory (flashRAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transshipment) such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. A method of optimizing an autopilot planning model, the method comprising:
the platform acquires traffic data reported by road side equipment;
determining target traffic data matched with a preset traffic scene recognition rule from the traffic data;
determining a target vehicle related to the target traffic data;
acquiring manual driving data of the target vehicle in a specified time period; the appointed time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment;
optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
2. The method of claim 1, wherein the traffic data reported by the roadside device specifically comprises:
the method comprises the steps that running data of a vehicle in a sensing range of road test equipment are acquired by road side equipment, wherein the running data specifically comprise: at least one of vehicle position data, vehicle speed data, vehicle acceleration data, and vehicle heading angle data.
3. The method according to claim 2, wherein the determining, from the traffic data, the target traffic data matching with a preset traffic scene recognition rule specifically includes:
judging whether the running data of the vehicle meets a preset traffic scene recognition rule or not to obtain a judging result; the vehicle is any vehicle in the sensing range of the road side equipment; the preset traffic scene recognition rule comprises the following steps: any one of a left lane overtaking recognition rule, a right lane overtaking recognition rule, an outgoing ramp recognition rule, a left lane changing recognition rule and a right lane changing recognition rule;
if the judgment result indicates that the traffic data of the vehicle meets the preset traffic scene recognition rule, then
And determining the traffic data of the vehicle as target traffic data matched with the preset traffic scene recognition rule.
4. The method of claim 1, wherein before optimizing the automated driving planning model using traffic data reported by the roadside device and the manual driving data, further comprising:
and determining relevant traffic data of a traffic scene related to the target vehicle from the traffic data, wherein the relevant traffic data specifically comprises the following steps: the operation data of the target vehicle, the operation data of the appointed vehicle in the preset range of the target vehicle and the relative operation data of the appointed vehicle and the target vehicle;
the optimizing the traffic data reported by the road side equipment and the manual driving data aiming at the automatic driving planning model specifically comprises the following steps:
and optimizing an automatic driving planning model applicable to the traffic scene by utilizing the related traffic data of the traffic scene related to the target vehicle and the manual driving data.
5. The method of claim 1, wherein before optimizing the automated driving planning model using traffic data reported by the roadside device and the manual driving data, further comprising:
Clustering the manual driving data of the target vehicle in the specified time period to obtain clustered manual driving data of various types;
determining a specified automatic driving planning model applicable to the clustered manual driving data of a specified type; the specified type of clustered manual driving data is any one of a plurality of types of clustered manual driving data;
determining the appointed target vehicle related to the appointed type of clustered manual driving data; the clustered manual driving data of the specified type is data generated by manually driving the specified target vehicle in the specified time period;
determining a designated road side device according to the vehicle position data of the designated target vehicle in the designated time period; the specified target vehicle is positioned in the perception range of the specified road side equipment in the specified time period;
the platform acquires the appointed traffic data reported by the appointed road side equipment;
the optimizing the traffic data reported by the road side equipment and the manual driving data aiming at the automatic driving planning model specifically comprises the following steps:
and optimizing the specified automatic driving planning model by utilizing the clustered manual driving data of the specified type and the specified traffic data.
6. The method according to claim 1, wherein the traffic data reported by the roadside device and the manual driving data are optimized for an automatic driving planning model, specifically comprising:
processing the traffic data by utilizing the automatic driving planning model to obtain automatic driving data of the target vehicle;
determining the accuracy of the automatic driving planning model according to the manual driving data and the automatic driving data;
and if the precision of the automatic driving planning model is smaller than the preset precision, adjusting parameters of the automatic driving planning model until the precision of the automatic driving planning model is larger than or equal to the preset precision.
7. The method according to claim 1 or 2, characterized in that the method further comprises:
the platform acquires vehicle running data reported by a vehicle with a data uploading function; the vehicle driving data comprises vehicle driving parameters and vehicle position data;
determining target traffic data matched with a preset traffic scene recognition rule from the traffic data, wherein the target traffic data specifically comprises:
and determining target traffic data matched with a preset traffic scene recognition rule from the traffic data and the vehicle driving data.
8. An apparatus for optimizing an autopilot planning model, the apparatus comprising:
the traffic data acquisition module is used for acquiring traffic data reported by the road side equipment by the platform;
the target traffic data determining module is used for determining target traffic data matched with a preset traffic scene recognition rule from the traffic data;
a target vehicle determining module, configured to determine a target vehicle related to the target traffic data;
the manual driving data acquisition module is used for acquiring manual driving data of the target vehicle in a specified time period; the appointed time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment;
the model optimization module is used for optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
9. An apparatus for optimizing an autopilot planning model, the apparatus comprising:
at least one processor; the method comprises the steps of,
A memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring traffic data reported by road side equipment;
determining target traffic data matched with a preset traffic scene recognition rule from the traffic data;
determining a target vehicle related to the target traffic data;
acquiring manual driving data of the target vehicle in a specified time period; the appointed time period at least comprises a first moment when the road side equipment acquires the traffic data and a preset time range after the first moment;
optimizing an automatic driving planning model by utilizing traffic data reported by the road side equipment and the manual driving data; the automatic driving planning model is a model for planning a driving state of an automatic driving vehicle.
10. A computer readable medium having stored thereon computer readable instructions executable by a processor to implement the method of optimizing an autopilot planning model of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211723076.8A CN116206441A (en) | 2022-12-30 | 2022-12-30 | Optimization method, device, equipment and medium of automatic driving planning model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211723076.8A CN116206441A (en) | 2022-12-30 | 2022-12-30 | Optimization method, device, equipment and medium of automatic driving planning model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116206441A true CN116206441A (en) | 2023-06-02 |
Family
ID=86518240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211723076.8A Pending CN116206441A (en) | 2022-12-30 | 2022-12-30 | Optimization method, device, equipment and medium of automatic driving planning model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116206441A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200302233A1 (en) * | 2017-12-11 | 2020-09-24 | Honda Motor Co., Ltd. | Training data generation apparatus |
| CN113687600A (en) * | 2021-10-21 | 2021-11-23 | 中智行科技有限公司 | Simulation test method, simulation test device, electronic equipment and storage medium |
| WO2022016901A1 (en) * | 2020-07-20 | 2022-01-27 | 华为技术有限公司 | Method for planning driving route of vehicle, and intelligent vehicle |
| CN114355793A (en) * | 2021-12-24 | 2022-04-15 | 阿波罗智能技术(北京)有限公司 | Training method and device of automatic driving planning model for vehicle simulation evaluation |
| CN114676844A (en) * | 2020-12-24 | 2022-06-28 | 北京百度网讯科技有限公司 | Method, apparatus, device, computer-readable storage medium for automatic driving |
| CN115195785A (en) * | 2022-07-26 | 2022-10-18 | 东软睿驰汽车技术（沈阳）有限公司 | Optimization method, device, equipment and storage medium for automatic driving model |
-
2022
- 2022-12-30 CN CN202211723076.8A patent/CN116206441A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200302233A1 (en) * | 2017-12-11 | 2020-09-24 | Honda Motor Co., Ltd. | Training data generation apparatus |
| WO2022016901A1 (en) * | 2020-07-20 | 2022-01-27 | 华为技术有限公司 | Method for planning driving route of vehicle, and intelligent vehicle |
| CN114676844A (en) * | 2020-12-24 | 2022-06-28 | 北京百度网讯科技有限公司 | Method, apparatus, device, computer-readable storage medium for automatic driving |
| CN113687600A (en) * | 2021-10-21 | 2021-11-23 | 中智行科技有限公司 | Simulation test method, simulation test device, electronic equipment and storage medium |
| CN114355793A (en) * | 2021-12-24 | 2022-04-15 | 阿波罗智能技术(北京)有限公司 | Training method and device of automatic driving planning model for vehicle simulation evaluation |
| CN115195785A (en) * | 2022-07-26 | 2022-10-18 | 东软睿驰汽车技术（沈阳）有限公司 | Optimization method, device, equipment and storage medium for automatic driving model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112766468B (en) | Trajectory prediction method and device, storage medium and electronic equipment | |
| CN112629550B (en) | Method and device for predicting obstacle track and model training | |
| CN111127551B (en) | Target detection method and device | |
| CN111238450B (en) | Visual positioning method and device | |
| CN111208838A (en) | Control method and device of unmanned equipment | |
| CN111062372B (en) | Method and device for predicting obstacle track | |
| CN112013853B (en) | Method and device for verifying track points of unmanned equipment | |
| CN110942181A (en) | Method and device for predicting obstacle track | |
| CN112734810B (en) | Obstacle tracking method and device | |
| CN111238523A (en) | Method and device for predicting motion trail | |
| CN111797711A (en) | Model training method and device | |
| CN112883871B (en) | Model training and unmanned vehicle motion strategy determining method and device | |
| CN110956214A (en) | Training method and device for automatic driving visual positioning model | |
| CN111426299B (en) | Method and device for ranging based on depth of field of target object | |
| CN115856979B (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN114153207B (en) | Control method and control device of unmanned equipment | |
| CN116206441A (en) | Optimization method, device, equipment and medium of automatic driving planning model | |
| CN112734851B (en) | Pose determination method and device | |
| CN116300842A (en) | Unmanned equipment control method and device, storage medium and electronic equipment | |
| CN112925210A (en) | Method and device for model training and unmanned equipment control | |
| CN115923843A (en) | Optimization method, device and equipment of automatic driving decision planning model | |
| CN117009919A (en) | Multi-sensor perception data fusion method, device and equipment | |
| CN114117746B (en) | Simulation data generation method and device, storage medium and electronic equipment | |
| CN117382593B (en) | Vehicle emergency braking method and system based on laser point cloud filtering | |
| CN118107576A (en) | Vehicle speed planning method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |