CN108773373B - Method and device for operating an autonomous vehicle - Google Patents
Method and device for operating an autonomous vehicle Download PDFInfo
- Publication number
- CN108773373B CN108773373B CN201810588432.7A CN201810588432A CN108773373B CN 108773373 B CN108773373 B CN 108773373B CN 201810588432 A CN201810588432 A CN 201810588432A CN 108773373 B CN108773373 B CN 108773373B
- Authority
- CN
- China
- Prior art keywords
- driving
- vehicle
- information
- scene
- risk
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000002159 abnormal effect Effects 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000001960 triggered effect Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 238000012986 modification Methods 0.000 claims description 6
- 230000004048 modification Effects 0.000 claims description 6
- 230000002787 reinforcement Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 abstract description 19
- 238000012502 risk assessment Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000002829 reductive effect Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0062—Adapting control system settings
- B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Economics (AREA)
- Automation & Control Theory (AREA)
- Entrepreneurship & Innovation (AREA)
- Transportation (AREA)
- Strategic Management (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
Methods and apparatus for operating an autonomous vehicle are disclosed. One embodiment of the method comprises: collecting a driving scheme and driving scene information adopted by a driver when the driver performs abnormal intervention on the semi-automatic driving vehicle; determining a risk level according to a driving scheme; decomposing object information, vehicle running state information and driving environment information of a driving environment where the vehicle is located from the driving scene information; learning the object information and the corresponding risk level, and identifying a risk object associated with the risk level; for the risk object, learning object information, vehicle driving state information, driving environment information and a driving scheme, and determining an association relation between a combination of the object information, the vehicle driving state information and the driving environment information of the risk object and the driving scheme to serve as a driving strategy; candidate driving scenarios are determined using a driving strategy. This embodiment enables the optimization of candidate driving scenarios according to the behavior of the driver.
Description
The present application is a divisional application of the chinese patent application having an application number CN201610825323.3, an application date of 2016, 9, and 14, entitled "method and apparatus for operating an autonomous vehicle".
Technical Field
The present application relates to the field of vehicle technology, in particular to unmanned vehicle technology, and more particularly to methods and apparatus for operating an autonomous vehicle.
Background
Automatic driving mainly relates to three main technologies of recognition, decision and control. For autonomous driving, safety is the first condition. In the prior art, risk objects identified by vehicle-mounted sensors are usually marked manually, and the risk of each object is further evaluated or a driving scheme is established through repeated tests.
However, the risk factors are marked completely by manpower, and the cost is extremely high. In addition, in an open driving environment, the existing risk factors are difficult to be exhausted and manually marked by designers and manufacturers, so that the system can automatically identify the risk factors. In addition, even if all current risk objects are marked in advance when a vehicle is designed or manufactured, new objects which are likely to cause driving risks can continuously appear in the driving process of the vehicle after the vehicle is put into use, and the existing mode cannot mark the continuously appearing new risk objects in time and cannot establish a risk assessment strategy or a driving strategy aiming at the new risk objects in time. Therefore, there is a need to devise fast, large-scale, low-cost identification methods for risk objects.
Disclosure of Invention
The present application provides methods and apparatus for operating an autonomous vehicle that address the technical problems identified in the background section above.
In a first aspect, the present application provides a method for operating an autonomous vehicle, the method comprising: collecting a driving scheme adopted when a driver performs abnormal intervention on a semi-automatic driving vehicle and driving scene information of a driving scene where the semi-automatic driving vehicle is located; determining the risk level of the driving risk of the semi-automatic driving vehicle under the driving scene according to the driving scheme adopted by the driver; decomposing object information of scene objects in the driving scene, vehicle driving state information and driving environment information of a driving environment where the vehicle is located from the driving scene information; learning the object information and the corresponding risk level, and identifying a risk object associated with the risk level in the scene object; learning object information, vehicle driving state information, driving environment information and corresponding driving schemes for the identified risk objects, and determining an association relation between a combination of the object information, the vehicle driving state information and the driving environment information of the risk objects and the driving schemes to serve as a driving strategy of the autonomous vehicle; determining a candidate driving scenario for the autonomous vehicle using the driving strategy.
In some embodiments, the method further comprises: a step of optimizing the driving strategy, comprising: controlling the test vehicle to run in the scene simulated by the driving simulator by using the driving strategy; detecting whether the driving rule preset in the driving simulator is met or not when the test vehicle runs; and correcting the driving strategy according to the detection result.
In some embodiments, a reinforcement learning algorithm is employed to modify the driving strategy.
In some embodiments, the method further comprises: adding the driving strategy to a driving strategy database of a semi-autonomous vehicle; determining whether the semi-autonomous vehicle is abnormally intervened by the driver when the driving strategy is triggered; and if the semi-automatic driving vehicle is not abnormally intervened, improving the reliability of the driving strategy.
In some embodiments, the method further comprises: and if the semi-automatic driving vehicle is abnormally intervened, continuously acquiring a driving scheme and corresponding driving scene information adopted by a driver when the semi-automatic driving vehicle intervenes so as to adjust the driving strategy according to the newly acquired driving scheme and the driving scene information.
In a second aspect, the present application provides an apparatus for operating an autonomous vehicle, the apparatus comprising: the device comprises: the system comprises a collecting unit, a judging unit and a judging unit, wherein the collecting unit is used for collecting a driving scheme adopted when a driver performs abnormal intervention on a semi-automatic driving vehicle and driving scene information of a driving scene where the semi-automatic driving vehicle is located;
the grade determining unit is used for determining the risk grade of the driving risk of the semi-automatic driving vehicle under the driving scene according to the driving scheme adopted by the driver; the decomposition unit is used for decomposing the object information, the vehicle running state information and the driving environment information of the driving environment of the vehicle of each scene object in the driving scene from the driving scene information; the risk object learning unit is used for learning the object information and the corresponding risk level and identifying a risk object related to the risk level in the scene object; a driving scheme learning unit which learns the object information, the vehicle driving state information, the driving environment information and the corresponding driving scheme for the identified risk object, and determines an association relation between the object information, the vehicle driving state information, the combination of the driving environment information and the driving scheme of the risk object as a driving strategy of the autonomous vehicle; a driving scheme determination unit for determining a candidate driving scheme for the autonomous vehicle using the driving strategy.
In some embodiments, the apparatus further comprises a driving strategy optimization unit for: controlling the test vehicle to run in the scene simulated by the driving simulator by using the driving strategy; detecting whether the driving rule preset in the driving simulator is met or not when the test vehicle runs; and correcting the driving strategy according to the detection result.
In some embodiments, the apparatus further comprises a policy modification unit configured to: adding the driving strategy to a driving strategy database of a semi-autonomous vehicle; determining whether the semi-autonomous vehicle is abnormally intervened by the driver when the driving strategy is triggered; and if the semi-automatic driving vehicle is not abnormally intervened, improving the reliability of the driving strategy.
In some embodiments, the policy modification unit is further configured to: and if the semi-automatic driving vehicle is abnormally intervened, continuously acquiring a driving scheme and corresponding driving scene information adopted by a driver when the semi-automatic driving vehicle intervenes so as to adjust the driving strategy according to the newly acquired driving scheme and the driving scene information.
According to the method and the device for operating the automatic driving vehicle, the risk level is determined through the abnormal intervention behavior of the driver on the semi-automatic driving vehicle, the scene object and the risk level are learned, and therefore the risk object related to the risk level is identified from the scene object. Through the mode, the abnormal intervention behaviors of the user can be continuously learned, so that the risk object can be automatically identified from the scene object which appears continuously, the automatic marking of the risk object is realized, the workload of manual marking is greatly reduced, and the risk factors which appear newly after the vehicle is put into use can be marked in time. In addition, the association relationship between the object information of the risk object and the risk level can be determined to generate a risk assessment strategy for the automatic driving vehicle, so that the risk identification can be optimized by learning the abnormal intervention behavior of the driver. In addition, for the identified risk object, the driving scheme when the driver performs abnormal intervention on the semi-automatic driving vehicle is used as a sample for learning, and the object information, the vehicle driving state and the driving environment of the risk object are established and associated relation with the driving scheme to generate a driving strategy, wherein the driving strategy can be used for determining a candidate driving scheme of the automatic driving vehicle, so that the candidate driving scheme of the automatic driving vehicle can be optimized according to the behavior of the driver.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a method for operating an autonomous vehicle according to the present application;
FIG. 3 is a flow chart of yet another embodiment of a method for operating an autonomous vehicle according to the present application;
FIG. 4 is a schematic structural diagram of one embodiment of an apparatus for operating an autonomous vehicle according to the present application;
FIG. 5 is a schematic structural diagram of yet another embodiment of an apparatus for operating an autonomous vehicle according to the present application;
fig. 6 is a schematic structural diagram of a computer system suitable for implementing the terminal device or the server according to the embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the methods and apparatus for operating an autonomous vehicle of the present application may be applied.
As shown in fig. 1, system architecture 100 may include semi-autonomous vehicles 101, 102, 103, networks 104, 106, server 105, and autonomous vehicle 107. Network 104 is used to provide the medium of the transmission link between semi-autonomous vehicles 101, 102, 103 and server 105, and network 104 is used to provide the medium of the transmission link between autonomous vehicle 107 and server 105. The networks 104, 106 may include various connection types, such as wired, wireless transmission links, or fiber optic cables, among others. Semi-autonomous vehicles 101, 102, 103 and autonomous vehicle 107 have onboard electronics installed therein for information collection, processing and communication.
The semi-autonomous vehicles 101, 102, 103 may collect the required data during the course of the trip and upload the collected data to the server 105 for further processing.
The server 105 may be a server that provides various services, such as a server that provides processing for data uploaded by the semi-autonomous vehicles 101, 102, 103. The server 105 may be trained using data uploaded by the semi-autonomous vehicles 101, 102, 103 to generate a risk assessment strategy or driving strategy. The server 105 may send the respective strategies to the autonomous vehicle 107 to operate the autonomous vehicle 107 to complete the assessment of risk or the determination of the driving schedule using the respective strategies. In addition, the server 105 may also send the policies back to each semi-autonomous vehicle so that each semi-autonomous vehicle tests the corresponding policy to facilitate further optimization of the policy.
It should be understood that the number of semi-autonomous vehicles, networks, and servers in fig. 1 is merely illustrative. There may be any number of semi-autonomous vehicles, networks, and servers, as desired for implementation.
Referring to FIG. 2, a flow diagram 200 of one embodiment of a method for operating an unmanned vehicle is shown, in accordance with the present application. It should be noted that the method for operating an unmanned vehicle provided in the embodiment of the present application is mainly performed by the server 105 in fig. 1, and some steps may also be performed by the autonomous vehicle 107 or the semi-autonomous vehicles 101, 102, 103; accordingly, the means for operating the unmanned vehicle is generally provided in the server 105, and some units may also be provided in the autonomous vehicle 107 or the semi-autonomous vehicles 101, 102, 103. The method comprises the following steps:
In the present embodiment, the electronic device (e.g., server 105 shown in fig. 1) on which the method for operating an autonomous vehicle operates may collect data from a semi-autonomous vehicle with which the driver travels through a wired connection or a wireless connection. The semi-automatic driving vehicle is a vehicle which is provided with an induction system of the automatic driving vehicle and can be manually intervened by a driver in the driving process.
The collected data comprises a driving scheme adopted when the driver performs abnormal intervention on the semi-automatic driving vehicle and driving scene information of a driving scene where the semi-automatic driving vehicle is located. In practice, these data may be collected by:
first, each semi-autonomous vehicle detects whether or not an abnormal intervention is made by the driver during driving. Secondly, when detecting that the driver performs abnormal intervention, the semi-automatic driving vehicle collects a driving scheme adopted by the driver during the abnormal intervention and collects driving scene information of a driving scene where the semi-automatic driving vehicle is located. The driving scene information may be data that is detected by various sensors or other means on the semi-autonomous driving vehicle and that can be used to describe the driving scene. For example, a video used for recording the surrounding environment of the vehicle can be collected through the vehicle-mounted camera, point cloud data around the vehicle can be collected through the laser radar, and high-precision map data of a road section where the vehicle is located and current weather data and the like can be acquired from the cloud end through the network. These data may be used for further fusion and analysis to derive information for various classes of objects in the driving scene, such as vehicle driving status information, driving environment information, scene object information, and the like. Finally, each semi-automatic driving vehicle uploads the collected data (including the driving scheme and the corresponding driving scene information) to the electronic device, and the electronic device can collect the data.
In some optional implementations of the present embodiment, the driving profile includes control behavior data that controls a vehicle speed and/or a vehicle direction of travel. The control behavior of the vehicle running speed mainly refers to the control behavior of components affecting the vehicle speed, such as the vehicle brake and the accelerator, and may be referred to as a longitudinal control behavior. The behavior of controlling the vehicle traveling direction mainly refers to the behavior of controlling a component, such as a steering wheel, that affects the vehicle traveling direction, and may also be referred to as lateral control behavior.
In this embodiment, the electronic device may map the driving scheme in the data obtained in step 201 to a risk level according to a preset mapping rule between the driving scheme and the risk level, so as to determine the risk level of the driving risk of the semi-automatic driving vehicle in the driving scene. Generally, risk ratings can be characterized by numerical values. For example, a hard break corresponds to a risk rating of 10, and a right turn corresponds to a risk rating of 9. In practice, the control amount of the control action may also be further rated, for example, a particular braking or right turn maneuver may be rated according to the magnitude of the braking or right turn. Alternatively, the determination of the risk level may also be directed to a combination of lateral and longitudinal control actions.
In step 203, object information of each scene object in the driving scene is decomposed from the driving scene information.
In the present embodiment, based on the driving scene information acquired in step 201, the electronic device may decompose object information of each scene object therefrom. In practice, the driving scene information can be analyzed through a certain algorithm, and scene objects which may influence the risk of the vehicle in the driving scene are decomposed. Scene objects may be vehicles, pedestrians, cyclists, other moving or stationary objects, etc. The object information may be information characterizing the scene objects. The characteristics can include static characteristics such as structure and color, and dynamic characteristics such as moving direction and moving speed. In general, these features can be used for identification of a particular scene object.
And step 204, learning the object information and the corresponding risk level, identifying a risk object associated with the risk level in the scene object, and determining an association relation between the object information of the risk object and the risk level to serve as a risk assessment strategy of the automatic driving vehicle.
In this embodiment, the electronic device may learn to attribute the risk level to each scene object according to the risk level obtained in step 202 and the object information obtained in step 203. Wherein scene objects associated with risk levels in the attribution process may be identified as risk objects. For the risk objects, the association relationship between the object information and the risk level of the risk objects can also be determined in the attribution process. The incidence relation can be used as a risk assessment strategy of the automatic driving vehicle, and the automatic driving vehicle can calculate the risk level.
In some optional implementations of the present embodiment, step 204 may employ a deep neural network algorithm to learn the object information and the corresponding risk level. The deep neural network algorithm can enable a machine to automatically learn the mode characteristics and integrate the characteristic learning into the process of establishing the model, so that the incompleteness caused by artificial design characteristics is reduced.
Optionally, the risk object includes a known risk object that has been marked in advance. For example, known risk objects that are common when driving a vehicle can be identified manually. In practice, the pattern features of these known risk objects need to be labeled. By the method, the deep neural network algorithm does not need to relearn the pattern characteristics of the frequently-occurring risk objects, the calculation difficulty of the deep neural network algorithm in characteristic learning is reduced, and the calculation efficiency is improved.
In this embodiment, the electronic device may configure the risk assessment strategy into the respective autonomous vehicle, and as such, the autonomous vehicle may identify a risk level of the driving risk using the risk assessment strategy. When the autonomous vehicle uses the risk assessment strategy, the risk object can be identified from the currently collected driving scene information, and the current risk level can be calculated according to the object information of the risk object.
In some optional implementations of this embodiment, the method further includes: resolving the vehicle running state information and the driving environment information of the driving environment of the vehicle from the driving scene information; and step 204 further comprises: and learning the object information, the vehicle driving state information, the driving environment information and the corresponding risk level, identifying a risk object associated with the risk level in the scene object, and determining the association relationship between the object information of the risk object, the vehicle driving state information and the driving environment information and the risk level. In this implementation, the risk level is attributed to a combination of the scene object, the vehicle driving state, and the driving environment, so that the risk assessment strategy also takes into account the conditions under which the scene object appears, making the factors considered by the risk assessment strategy more comprehensive.
According to the method provided by the embodiment of the application, the risk level is determined through the abnormal intervention behavior of the driver on the semi-automatic driving vehicle, and the scene objects and the risk level are learned, so that the risk objects related to the risk level are identified from the scene objects. Through the mode, the abnormal intervention behaviors of the user can be continuously learned, so that the risk object can be automatically identified from the scene object which appears continuously, the automatic marking of the risk object is realized, the workload of manual marking is greatly reduced, and the risk factors which appear newly after the vehicle is put into use can be marked in time. In addition, the association relationship between the object information of the risk object and the risk level can be determined to generate a risk assessment strategy for the automatic driving vehicle, so that the risk identification can be optimized by learning the abnormal intervention behavior of the driver.
With further reference to fig. 3, a flow 300 of yet another embodiment of a method for operating an autonomous vehicle is shown. The process 300 of the method includes the following steps:
In this embodiment, the specific processing of step 301 may refer to step 201 in the corresponding embodiment of fig. 2, which is not described herein again.
In this embodiment, the specific processing of step 302 may refer to step 202 in the corresponding embodiment of fig. 2, which is not described herein again.
In this embodiment, based on the driving scene information collected in step 301, the electronic device may resolve the object information of the scene object in the driving scene, the driving state information of the vehicle, and the driving environment information of the driving environment in which the vehicle is located according to a certain algorithm. The scene objects are scene objects that may be encountered during the driving process of the vehicle, such as pedestrians, other motor vehicles on the road, non-motor vehicles, goods scattered by other vehicles, and the like. The vehicle running state information is mainly state information of the vehicle itself, such as a vehicle running direction, a vehicle running speed, and the like. The driving environment information is used for indicating the macro environment of the vehicle, such as the road of the vehicle, the current weather and the like. Since the driving scene information is information acquired by a plurality of sensors, and various information are fused together, the electronic device needs to decompose the driving scene information, so that the object information of each scene object, the vehicle driving state information, and the driving environment information of the driving environment in which the vehicle is located are decomposed.
In step 304, the object information and the corresponding risk level are learned, and a risk object associated with the risk level in the scene object is identified.
In this embodiment, the electronic device may learn to attribute the risk level to each scene object according to the risk level obtained in step 202 and the object information obtained in step 203. Wherein scene objects associated with risk levels in the attribution process may be identified as risk objects.
And 305, learning object information, vehicle running state information, driving environment information and corresponding driving schemes for the identified risk objects, and determining the association relationship among the object information, the vehicle running state information and the driving environment information of the risk objects and the driving schemes to serve as the driving strategy of the automatic driving vehicle.
In this embodiment, for the risk object identified in step 304, the electronic device may train data related to the risk object as a sample based on the object information, the vehicle driving state information, the driving environment information obtained in step 303, and the driving scheme obtained in step 301, to determine an association relationship between a combination of the object information, the vehicle driving state information, and the driving environment information of the risk object and the driving scheme, thereby being a driving strategy of the autonomous vehicle.
At step 306, a candidate driving scenario for the autonomous vehicle is determined using the driving strategy.
In this embodiment, based on the driving strategy obtained in step 304, the electronic device may configure it into an autonomous vehicle so that candidate driving scenarios for the driving strategy may be determined using the driving strategy. It should be noted that the candidate driving scenario may be a driving scenario eventually adopted by the autonomous vehicle, or may be a driving scenario for further processing by the autonomous vehicle. In practice, the autonomous vehicle may select an end-use driving scenario from a plurality of candidate driving scenarios based on other aiding decision information, which may include, but is not limited to, one or more of driver preference information, weather information, trip information, energy consumption information.
In some optional implementations of the present embodiment, the method further includes a step of optimizing the driving strategy, where the step specifically includes: controlling the test vehicle to run in the scene simulated by the driving simulator by using the driving strategy; detecting whether a test vehicle meets a driving rule preset in a driving simulator when running; and correcting the driving strategy according to the detection result.
In the implementation mode, the driving strategy is tested through a simulator simulation scene and is corrected according to the test effect, so that the driving of the vehicle can accord with the driving rule through the corrected driving strategy, and the driving strategy is optimized in the aspect of driving safety.
In some optional implementation manners of the embodiment, in the step of optimizing the driving strategy, a reinforcement learning algorithm is adopted to modify the driving strategy according to the detection result. In this implementation, a reinforcement learning algorithm is employed when the driving strategy is modified according to the detection result, so that the weight of the driving scheme that conforms to the driving rule in the driving strategy is increased, and the weight of the driving scheme that does not conform to the driving rule is decreased. Through the test of a large number of scenes, the driving scheme corresponding to various driving scenes in the corrected driving strategy can be made to accord with the driving rule as much as possible.
In some optional implementations of this embodiment, the method further includes: adding a driving strategy to a driving strategy database of a semi-autonomous vehicle; determining whether the semi-autonomous vehicle is abnormally intervened by the driver when the driving strategy is triggered; and if the semi-automatic driving vehicle is not abnormally interfered, improving the reliability of the driving strategy. In this implementation, the derived driving strategy may be configured into a driving strategy database of the semi-autonomous vehicle for the semi-autonomous vehicle to be able to perform on-road testing. When the driving strategy is triggered and is not abnormally interfered by the driver, the reliability of the driving strategy is improved, so that the effectiveness of the driving strategy is effectively verified through actual road testing, and the reliability of the driving strategy is improved when the driving strategy is effective, so that the driving strategy can meet the actual driving requirement of the driver as much as possible.
In some optional implementations of the previous implementation, the method further includes: and if the semi-automatic driving vehicle is abnormally intervened, continuously acquiring a driving scheme and corresponding driving scene information adopted by a driver when the semi-automatic driving vehicle intervenes so as to adjust the driving strategy according to the newly acquired driving scheme and the driving scene information. When the driving strategy is triggered and abnormally intervened by the driver, the triggered driving strategy fails to meet the current driving requirement of the driver, so that the driving scheme and the corresponding driving scene information adopted by the driver when the driver intervenes the semi-automatic driving vehicle need to be continuously collected to adjust the driving strategy. Optionally, the existing driving scheme and driving scenario information and the newly acquired driving scheme and driving scenario information may be simultaneously used as sample data for generating a new driving strategy. In practice, when a new driving strategy is generated by using the model, higher weight can be set for the newly collected driving scheme and driving scene information so as to improve the timeliness of the driving strategy.
The process 300 of the method for operating an autonomous vehicle in this embodiment determines a risk level through abnormal intervention behavior of the driver with respect to the semi-autonomous vehicle and learns the scene objects and the risk level, thereby identifying the risk objects associated with the risk level from the scene objects. Through the mode, the abnormal intervention behaviors of the user can be continuously learned, so that the risk object can be automatically identified from the scene object which appears continuously, the automatic marking of the risk object is realized, the workload of manual marking is greatly reduced, and the risk factors which appear newly after the vehicle is put into use can be marked in time. In addition, for the identified risk object, the driving scheme when the driver performs abnormal intervention on the semi-automatic driving vehicle is used as a sample for learning, and the object information, the vehicle driving state and the driving environment of the risk object are established and associated relation with the driving scheme to generate a driving strategy, wherein the driving strategy can be used for determining a candidate driving scheme of the automatic driving vehicle, so that the candidate driving scheme of the automatic driving vehicle can be optimized according to the behavior of the driver.
With further reference to fig. 4, as an implementation of the methods illustrated in the above figures, the present application provides one embodiment of an apparatus for operating an autonomous vehicle, which corresponds to the method embodiment illustrated in fig. 2, and which has particular general application in the server 105 in fig. 1.
As shown in fig. 4, the apparatus 400 for operating an autonomous vehicle according to the present embodiment includes: a collection unit 401, a risk level determination unit 402, a decomposition unit 403, a learning unit 404, and an identification unit 405. The collecting unit 401 is configured to collect a driving scheme adopted when the driver performs abnormal intervention on the semi-autonomous vehicle and driving scene information of a driving scene where the semi-autonomous vehicle is located; the risk level determination unit 402 is configured to determine a risk level of a driving risk of the semi-automatic driving vehicle in a driving scene according to a driving scheme adopted by a driver; the decomposition unit 403 is configured to decompose object information of each scene object in the driving scene from the driving scene information; the learning unit 404 is configured to learn the object information and the corresponding risk level, identify a risk object associated with the risk level in the scene object, and determine an association relationship between the object information of the risk object and the risk level as a risk assessment policy of the autonomous vehicle; and the identification unit 405 is configured to identify a risk level of the driving risk of the autonomous vehicle using a risk assessment strategy.
In this embodiment, the specific processing of the collecting unit 401, the risk level determining unit 402, the decomposing unit 403, the learning unit 404, and the identifying unit 405 may refer to step 201, step 202, step 203, step 204, and step 205 in the corresponding embodiment of fig. 2, which is not described herein again.
In some optional implementations of the present embodiment, the decomposition unit 403 is further configured to decompose the driving state information of the vehicle and the driving environment information of the driving environment in which the vehicle is located from the driving scenario information; and, the learning unit 404 is further configured to: and learning the object information, the vehicle driving state information, the driving environment information and the corresponding risk level, identifying a risk object associated with the risk level in the scene object, and determining the association relationship between the object information of the risk object, the vehicle driving state information and the driving environment information and the risk level. The specific processing of this implementation may refer to a corresponding implementation in the corresponding embodiment of fig. 2, which is not described herein again.
In some optional implementations of the present embodiment, the driving profile includes control behavior data that controls a vehicle speed and/or a vehicle direction of travel. The specific processing of this implementation may refer to a corresponding implementation in the corresponding embodiment of fig. 2, which is not described herein again.
With further reference to fig. 5, as an implementation of the method shown in the above figures, the present application provides yet another embodiment of an apparatus for operating an autonomous vehicle, which corresponds to the method embodiment shown in fig. 3, and which may be particularly applicable in the server 105 in fig. 1.
As shown in fig. 5, the apparatus 500 for operating an autonomous vehicle according to the present embodiment includes: a collection unit 501, a decomposition unit 502, an association determination unit 503, and a driving schedule determination unit 504. The collecting unit 501 is configured to collect a driving scheme adopted when a driver performs abnormal intervention on a semi-autonomous vehicle and driving scene information of a driving scene where the semi-autonomous vehicle is located; the decomposition unit 502 is configured to decompose object information of each scene object in the driving scene, vehicle driving state information, and driving environment information of a driving environment in which the vehicle is located from the driving scene information; an association relation determination unit 503 for determining an association relation between a combination of the object information of the risk object, the vehicle running state information, the driving environment information, and the driving scenario as a driving strategy of the autonomous vehicle; and the driving scenario determination unit 504 is configured to determine a candidate driving scenario for the autonomous vehicle using the driving strategy.
In this embodiment, specific processes of the collecting unit 501, the level determining unit, the decomposing unit 503, the risk object learning unit 503, the driving scheme learning unit 505, and the driving scheme determining unit 506 may refer to step 301, step 302, step 303, step 304, step 305, and step 306 in the corresponding embodiment of fig. 3, respectively, and are not described herein again.
In some optional implementations of the present embodiment, the apparatus 500 further comprises a driving strategy optimization unit (not shown) for: controlling the test vehicle to run in the scene simulated by the driving simulator by using the driving strategy; detecting whether a test vehicle meets a driving rule preset in a driving simulator when running; and correcting the driving strategy according to the detection result. The specific processing of this implementation may refer to a corresponding implementation in the embodiment corresponding to fig. 3, which is not described herein again.
In some optional implementations of the present embodiment, the apparatus 500 further comprises a policy modification unit (not shown) configured to: adding a driving strategy to a driving strategy database of a semi-autonomous vehicle; determining whether the semi-autonomous vehicle is abnormally intervened by the driver when the driving strategy is triggered; and if the semi-automatic driving vehicle is not abnormally interfered, improving the reliability of the driving strategy.
In some optional implementations of the present embodiment, the policy modification unit is further configured to: and if the semi-automatic driving vehicle is abnormally intervened, continuously acquiring a driving scheme and corresponding driving scene information adopted by a driver when the semi-automatic driving vehicle intervenes so as to adjust the driving strategy according to the newly acquired driving scheme and the driving scene information. The specific processing of this implementation may refer to a corresponding implementation in the corresponding embodiment of fig. 2, which is not described herein again.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use in implementing a server or onboard vehicle electronic device is shown.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor comprises a collecting unit, a risk level determining unit, a decomposing unit, an association relation determining unit and an identifying unit. The names of these units do not constitute a limitation to the unit itself in some cases, and for example, the collecting unit may also be described as a "unit that collects driving scenario information of a driving scenario in which a driver performs an abnormal intervention on a semi-autonomous vehicle and the semi-autonomous vehicle is located".
As another aspect, the present application also provides a non-volatile computer storage medium, which may be the non-volatile computer storage medium included in the apparatus in the above-described embodiments; or it may be a non-volatile computer storage medium that exists separately and is not incorporated into the terminal. The non-transitory computer storage medium stores one or more programs that, when executed by a device, cause the device to: collecting a driving scheme adopted when a driver performs abnormal intervention on a semi-automatic driving vehicle and driving scene information of a driving scene where the semi-automatic driving vehicle is located; determining the risk level of the driving risk of the semi-automatic driving vehicle under the driving scene according to the driving scheme adopted by the driver; decomposing object information of each scene object in the driving scene from the driving scene information; learning the object information and the corresponding risk level, identifying a risk object in the scene object, which is associated with the risk level, and determining an association relation between the object information of the risk object and the risk level to serve as a risk assessment strategy of the automatic driving vehicle; identifying a risk level of a driving risk of the autonomous vehicle using the risk assessment policy. Alternatively, the non-volatile computer storage medium stores one or more programs that, when executed by a device, cause the device to: collecting a driving scheme adopted when a driver performs abnormal intervention on a semi-automatic driving vehicle and driving scene information of a driving scene where the semi-automatic driving vehicle is located; determining the risk level of the driving risk of the semi-automatic driving vehicle under the driving scene according to the driving scheme adopted by the driver; decomposing object information of scene objects in the driving scene, vehicle driving state information and driving environment information of a driving environment where the vehicle is located from the driving scene information; learning the object information and the corresponding risk level, and identifying a risk object associated with the risk level in the scene object; learning object information, vehicle driving state information, driving environment information and corresponding driving schemes for the identified risk objects, and determining an association relation between a combination of the object information, the vehicle driving state information and the driving environment information of the risk objects and the driving schemes to serve as a driving strategy of the autonomous vehicle; determining a candidate driving scenario for the autonomous vehicle using the driving strategy.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by a person skilled in the art that the scope of the invention as referred to in the present application is not limited to the embodiments with a specific combination of the above-mentioned features, but also covers other embodiments with any combination of the above-mentioned features or their equivalents without departing from the inventive concept. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (9)
1. A method for operating an autonomous vehicle, the method comprising:
collecting a driving scheme adopted when a driver performs abnormal intervention on a semi-automatic driving vehicle and driving scene information of a driving scene where the semi-automatic driving vehicle is located;
determining the risk level of the driving risk of the semi-automatic driving vehicle under the driving scene according to the driving scheme adopted by the driver;
decomposing object information of scene objects in the driving scene, vehicle driving state information and driving environment information of a driving environment where the vehicle is located from the driving scene information;
learning the object information and the corresponding risk level, and identifying a risk object associated with the risk level in the scene object;
learning object information, vehicle driving state information, driving environment information and corresponding driving schemes for the identified risk objects, and determining an association relation between a combination of the object information, the vehicle driving state information and the driving environment information of the risk objects and the driving schemes to serve as a driving strategy of the autonomous vehicle;
determining a candidate driving scenario for the autonomous vehicle using the driving strategy.
2. The method of claim 1, further comprising:
a step of optimizing the driving strategy, comprising:
controlling the test vehicle to run in the scene simulated by the driving simulator by using the driving strategy;
detecting whether the driving rule preset in the driving simulator is met or not when the test vehicle runs;
and correcting the driving strategy according to the detection result.
3. The method of claim 2, wherein the driving strategy is modified using a reinforcement learning algorithm.
4. The method according to one of claims 1 to 3, characterized in that the method further comprises:
adding the driving strategy to a driving strategy database of a semi-autonomous vehicle;
determining whether the semi-autonomous vehicle is abnormally intervened by the driver when the driving strategy is triggered;
and if the semi-automatic driving vehicle is not abnormally intervened, improving the reliability of the driving strategy.
5. The method of claim 4, further comprising:
and if the semi-automatic driving vehicle is abnormally intervened, continuously acquiring a driving scheme and corresponding driving scene information adopted by a driver when the semi-automatic driving vehicle intervenes so as to adjust the driving strategy according to the newly acquired driving scheme and the driving scene information.
6. An apparatus for operating an autonomous vehicle, the apparatus comprising:
the system comprises a collecting unit, a judging unit and a judging unit, wherein the collecting unit is used for collecting a driving scheme adopted when a driver performs abnormal intervention on a semi-automatic driving vehicle and driving scene information of a driving scene where the semi-automatic driving vehicle is located;
the grade determining unit is used for determining the risk grade of the driving risk of the semi-automatic driving vehicle under the driving scene according to the driving scheme adopted by the driver;
the decomposition unit is used for decomposing the object information, the vehicle running state information and the driving environment information of the driving environment of the vehicle of each scene object in the driving scene from the driving scene information;
the risk object learning unit is used for learning the object information and the corresponding risk level and identifying a risk object related to the risk level in the scene object;
a driving scheme learning unit which learns the object information, the vehicle driving state information, the driving environment information and the corresponding driving scheme for the identified risk object, and determines an association relation between the object information, the vehicle driving state information, the combination of the driving environment information and the driving scheme of the risk object as a driving strategy of the autonomous vehicle;
a driving scheme determination unit for determining a candidate driving scheme for the autonomous vehicle using the driving strategy.
7. The apparatus of claim 6, further comprising a driving strategy optimization unit to:
controlling the test vehicle to run in the scene simulated by the driving simulator by using the driving strategy;
detecting whether the driving rule preset in the driving simulator is met or not when the test vehicle runs;
and correcting the driving strategy according to the detection result.
8. The apparatus according to claim 6 or 7, wherein the apparatus further comprises a policy modification unit configured to:
adding the driving strategy to a driving strategy database of a semi-autonomous vehicle;
determining whether the semi-autonomous vehicle is abnormally intervened by the driver when the driving strategy is triggered;
and if the semi-automatic driving vehicle is not abnormally intervened, improving the reliability of the driving strategy.
9. The apparatus of claim 8, wherein the policy modification unit is further configured to:
and if the semi-automatic driving vehicle is abnormally intervened, continuously acquiring a driving scheme and corresponding driving scene information adopted by a driver when the semi-automatic driving vehicle intervenes so as to adjust the driving strategy according to the newly acquired driving scheme and the driving scene information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810588432.7A CN108773373B (en) | 2016-09-14 | 2016-09-14 | Method and device for operating an autonomous vehicle |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610825323.3A CN106347359B (en) | 2016-09-14 | 2016-09-14 | Method and apparatus for operating automatic driving vehicle |
| CN201810588432.7A CN108773373B (en) | 2016-09-14 | 2016-09-14 | Method and device for operating an autonomous vehicle |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610825323.3A Division CN106347359B (en) | 2016-09-14 | 2016-09-14 | Method and apparatus for operating automatic driving vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108773373A CN108773373A (en) | 2018-11-09 |
| CN108773373B true CN108773373B (en) | 2020-04-24 |
Family
ID=57857976
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810588432.7A Active CN108773373B (en) | 2016-09-14 | 2016-09-14 | Method and device for operating an autonomous vehicle |
| CN201610825323.3A Active CN106347359B (en) | 2016-09-14 | 2016-09-14 | Method and apparatus for operating automatic driving vehicle |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610825323.3A Active CN106347359B (en) | 2016-09-14 | 2016-09-14 | Method and apparatus for operating automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN108773373B (en) |
Families Citing this family (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102017201804A1 (en) * | 2017-02-06 | 2018-08-09 | Robert Bosch Gmbh | Method for collecting data, method for updating a scenario catalog, device, computer program and machine-readable storage medium |
| RU2733015C1 (en) * | 2017-02-10 | 2020-09-28 | Ниссан Норт Америка, Инк. | Real-time vehicle control |
| US10752239B2 (en) * | 2017-02-22 | 2020-08-25 | International Business Machines Corporation | Training a self-driving vehicle |
| CN107168303A (en) * | 2017-03-16 | 2017-09-15 | 中国科学院深圳先进技术研究院 | A kind of automatic Pilot method and device of automobile |
| US10705525B2 (en) * | 2017-04-07 | 2020-07-07 | Nvidia Corporation | Performing autonomous path navigation using deep neural networks |
| CN115855022A (en) | 2017-04-07 | 2023-03-28 | 辉达公司 | Performing autonomous path navigation using deep neural networks |
| CN107139917B (en) * | 2017-04-27 | 2019-05-31 | 江苏大学 | It is a kind of based on mixing theoretical pilotless automobile crosswise joint system and method |
| DE112017007561T5 (en) * | 2017-06-16 | 2020-02-20 | Ford Global Technologies, Llc | VEHICLE OCCUPANTS INTERFERENCE DETECTION |
| CN107194612B (en) * | 2017-06-20 | 2020-10-13 | 清华大学 | Train operation scheduling method and system based on deep reinforcement learning |
| KR102342143B1 (en) * | 2017-08-08 | 2021-12-23 | 주식회사 만도모빌리티솔루션즈 | Deep learning based self-driving car, deep learning based self-driving control device, and deep learning based self-driving control method |
| US10831190B2 (en) | 2017-08-22 | 2020-11-10 | Huawei Technologies Co., Ltd. | System, method, and processor-readable medium for autonomous vehicle reliability assessment |
| CN108009587B (en) * | 2017-12-01 | 2021-04-16 | 驭势科技（北京）有限公司 | Method and equipment for determining driving strategy based on reinforcement learning and rules |
| CN110276985B (en) | 2018-03-16 | 2020-12-15 | 华为技术有限公司 | Automatic driving safety evaluation method, device and system |
| CN108427417B (en) * | 2018-03-30 | 2020-11-24 | 北京图森智途科技有限公司 | Automatic driving control system and method, computer server and automatic driving vehicle |
| CN110414756B (en) * | 2018-04-28 | 2023-09-26 | 奥迪股份公司 | Vehicle driving system evaluation method, device and computer equipment |
| CN108803604A (en) * | 2018-06-06 | 2018-11-13 | 深圳市易成自动驾驶技术有限公司 | Vehicular automatic driving method, apparatus and computer readable storage medium |
| CN109242251B (en) * | 2018-08-03 | 2020-03-06 | 百度在线网络技术（北京）有限公司 | Driving behavior safety detection method, device, equipment and storage medium |
| CN109324608B (en) * | 2018-08-31 | 2022-11-08 | 阿波罗智能技术(北京)有限公司 | Unmanned vehicle control method, device, equipment and storage medium |
| CN109255442B (en) * | 2018-09-27 | 2022-08-23 | 北京百度网讯科技有限公司 | Training method, device and readable medium for control decision module based on artificial intelligence |
| US11260872B2 (en) * | 2018-10-12 | 2022-03-01 | Honda Motor Co., Ltd. | System and method for utilizing a temporal recurrent network for online action detection |
| CN109459734B (en) * | 2018-10-30 | 2020-09-11 | 百度在线网络技术（北京）有限公司 | Laser radar positioning effect evaluation method, device, equipment and storage medium |
| CN111216723B (en) * | 2018-11-26 | 2021-04-16 | 广州汽车集团股份有限公司 | Vehicle travel control method, device and storage medium |
| CN110356408A (en) * | 2019-07-31 | 2019-10-22 | 百度在线网络技术（北京）有限公司 | The determination method and device of automatic driving vehicle traveling scheme |
| CN110781069B (en) * | 2019-08-28 | 2022-05-20 | 腾讯科技（深圳）有限公司 | Positioning module testing method, device and equipment for automatic driving vehicle |
| CN111028531B (en) * | 2019-12-26 | 2022-02-08 | 苏州智加科技有限公司 | Prompting method, prompting device, automatic driving vehicle and storage medium |
| EP4120215A4 (en) * | 2020-04-02 | 2023-03-22 | Huawei Technologies Co., Ltd. | Method for identifying abnormal driving behavior |
| CN111653125B (en) * | 2020-05-28 | 2021-09-28 | 长安大学 | Method for determining pedestrian mode of zebra crossing of unmanned automobile |
| CN111599183B (en) * | 2020-07-22 | 2020-10-27 | 中汽院汽车技术有限公司 | Automatic driving scene classification and identification system and method |
| CN112115798B (en) * | 2020-08-21 | 2023-04-07 | 东风汽车集团有限公司 | Object labeling method and device in driving scene and storage medium |
| CN112141125A (en) * | 2020-10-28 | 2020-12-29 | 安徽江淮汽车集团股份有限公司 | Intelligent hierarchical interaction method, device and equipment for automatic driving and storage medium |
| CN112565468B (en) * | 2021-02-22 | 2021-08-31 | 华为技术有限公司 | Driving scene recognition method and system |
| CN113449589B (en) * | 2021-05-16 | 2022-11-15 | 桂林电子科技大学 | Method for calculating driving strategy of unmanned vehicle in urban traffic scene |
| CN113361086B (en) * | 2021-05-31 | 2024-05-28 | 重庆长安汽车股份有限公司 | Intelligent driving safety constraint method and system and vehicle |
| US20220413502A1 (en) * | 2021-06-25 | 2022-12-29 | Here Global B.V. | Method, apparatus, and system for biasing a machine learning model toward potential risks for controlling a vehicle or robot |
| CN113581199A (en) * | 2021-06-30 | 2021-11-02 | 银隆新能源股份有限公司 | Vehicle control method and device |
| CN114407860B (en) * | 2022-01-07 | 2023-04-28 | 所托(杭州)汽车智能设备有限公司 | False triggering judgment method, device, equipment and medium for automatic braking system |
| CN116880462B (en) * | 2023-03-17 | 2024-09-17 | 北京百度网讯科技有限公司 | Automatic driving model, training method, automatic driving method and vehicle |
| CN116881707A (en) * | 2023-03-17 | 2023-10-13 | 北京百度网讯科技有限公司 | Automatic driving model, training method, training device and vehicle |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009262702A (en) * | 2008-04-23 | 2009-11-12 | Fuji Heavy Ind Ltd | Safe driving support system |
| CN101652802A (en) * | 2007-04-02 | 2010-02-17 | 松下电器产业株式会社 | Safe driving assisting device |
| EP2779045A1 (en) * | 2013-03-14 | 2014-09-17 | Toyota Motor Engineering & Manufacturing North America, Inc. | Computer-based method and system for providing active and automatic personal assistance using an automobile or a portable electronic device |
| CN104859649A (en) * | 2014-02-25 | 2015-08-26 | 福特全球技术公司 | Autonomous driving sensing system and method |
| CN104903172A (en) * | 2012-10-05 | 2015-09-09 | 雷诺股份公司 | Method for assessing the risk of collision at an intersection |
| CN105270296A (en) * | 2014-06-09 | 2016-01-27 | 源捷公司 | Vehicle learning interface |
| DE102014218429A1 (en) * | 2014-09-15 | 2016-03-17 | Bayerische Motoren Werke Aktiengesellschaft | Method for carrying out an at least partially automated movement of a vehicle within a spatially limited area |
| CN105526942A (en) * | 2016-01-25 | 2016-04-27 | 重庆邮电大学 | Intelligent vehicle route planning method based on threat assessment |
| CN105551284A (en) * | 2016-01-29 | 2016-05-04 | 武汉光庭科技有限公司 | Open-type automatic driving system |
| CN105644567A (en) * | 2015-12-29 | 2016-06-08 | 大陆汽车投资（上海）有限公司 | Driving assistant system based on advanced driver assistant system (ADAS) |
| CN105892471A (en) * | 2016-07-01 | 2016-08-24 | 北京智行者科技有限公司 | Automatic automobile driving method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3102250B2 (en) * | 1994-02-14 | 2000-10-23 | 三菱自動車工業株式会社 | Ambient information display device for vehicles |
| US8509982B2 (en) * | 2010-10-05 | 2013-08-13 | Google Inc. | Zone driving |
| CN103996312B (en) * | 2014-05-23 | 2015-12-09 | 北京理工大学 | There is the pilotless automobile control system that social action is mutual |
| US9193314B1 (en) * | 2014-06-09 | 2015-11-24 | Atieva, Inc. | Event sensitive learning interface |
| CN104391504B (en) * | 2014-11-25 | 2017-05-31 | 浙江吉利汽车研究院有限公司 | The generation method and generating means of the automatic Pilot control strategy based on car networking |
| US9361599B1 (en) * | 2015-01-28 | 2016-06-07 | Allstate Insurance Company | Risk unit based policies |
| CN105930625B (en) * | 2016-06-13 | 2018-12-14 | 天津工业大学 | Q study combines the design method of the intelligent driving behaviour decision making system of neural network |
-
2016
- 2016-09-14 CN CN201810588432.7A patent/CN108773373B/en active Active
- 2016-09-14 CN CN201610825323.3A patent/CN106347359B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101652802A (en) * | 2007-04-02 | 2010-02-17 | 松下电器产业株式会社 | Safe driving assisting device |
| JP2009262702A (en) * | 2008-04-23 | 2009-11-12 | Fuji Heavy Ind Ltd | Safe driving support system |
| CN104903172A (en) * | 2012-10-05 | 2015-09-09 | 雷诺股份公司 | Method for assessing the risk of collision at an intersection |
| EP2779045A1 (en) * | 2013-03-14 | 2014-09-17 | Toyota Motor Engineering & Manufacturing North America, Inc. | Computer-based method and system for providing active and automatic personal assistance using an automobile or a portable electronic device |
| CN104859649A (en) * | 2014-02-25 | 2015-08-26 | 福特全球技术公司 | Autonomous driving sensing system and method |
| CN105270296A (en) * | 2014-06-09 | 2016-01-27 | 源捷公司 | Vehicle learning interface |
| DE102014218429A1 (en) * | 2014-09-15 | 2016-03-17 | Bayerische Motoren Werke Aktiengesellschaft | Method for carrying out an at least partially automated movement of a vehicle within a spatially limited area |
| CN105644567A (en) * | 2015-12-29 | 2016-06-08 | 大陆汽车投资（上海）有限公司 | Driving assistant system based on advanced driver assistant system (ADAS) |
| CN105526942A (en) * | 2016-01-25 | 2016-04-27 | 重庆邮电大学 | Intelligent vehicle route planning method based on threat assessment |
| CN105551284A (en) * | 2016-01-29 | 2016-05-04 | 武汉光庭科技有限公司 | Open-type automatic driving system |
| CN105892471A (en) * | 2016-07-01 | 2016-08-24 | 北京智行者科技有限公司 | Automatic automobile driving method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106347359A (en) | 2017-01-25 |
| CN108773373A (en) | 2018-11-09 |
| CN106347359B (en) | 2019-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108773373B (en) | Method and device for operating an autonomous vehicle | |
| CN107491073B (en) | Data training method and device for unmanned vehicle | |
| US10642268B2 (en) | Method and apparatus for generating automatic driving strategy | |
| CN107571864A (en) | The collecting method and device of automatic driving vehicle | |
| CN110660141B (en) | Road surface condition detection method and device, electronic equipment and readable storage medium | |
| CN112009397B (en) | Automatic driving drive test data analysis method and device | |
| US20220383736A1 (en) | Method for estimating coverage of the area of traffic scenarios | |
| JP2020042786A (en) | Processing method of car image, processing device of car image and computer-readable storage medium | |
| CN109684900B (en) | Method and apparatus for outputting color information | |
| CN111947669A (en) | Method for using feature-based positioning maps for vehicles | |
| CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
| CN113421298A (en) | Vehicle distance measuring method, vehicle control device, vehicle and readable storage medium | |
| CN116010854B (en) | Abnormality cause determination method, abnormality cause determination device, electronic device and storage medium | |
| CN111845769B (en) | Vehicle driving method and device, computer equipment and vehicle | |
| CN116989809A (en) | Navigation information updating method and device, electronic equipment and storage medium | |
| CN116198511A (en) | Vehicle regulation parameter configuration method and system | |
| US20240037296A1 (en) | Comparison of digital representations of driving situations of a vehicle | |
| CN115563020A (en) | Method and system for generating danger test scene, electronic device and storage medium | |
| CN113987751A (en) | Scheme screening method and device, electronic equipment and storage medium | |
| CN113947158A (en) | Data fusion method and device for intelligent vehicle | |
| CN114861793A (en) | Information processing method, device and storage medium | |
| CN113850929B (en) | Display method, device, equipment and medium for processing annotation data stream | |
| US20230377385A1 (en) | Method for validating safety precautions for vehicles moving in an at least partially automated manner | |
| CN111091192B (en) | Method, apparatus, central device and system for identifying distribution shifts | |
| WO2023228722A1 (en) | Image recognition system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |