CN115892053A - Vehicle-mounted intelligent management method and system for improving automatic driving performance - Google Patents
Vehicle-mounted intelligent management method and system for improving automatic driving performance Download PDFInfo
- Publication number
- CN115892053A CN115892053A CN202110901320.4A CN202110901320A CN115892053A CN 115892053 A CN115892053 A CN 115892053A CN 202110901320 A CN202110901320 A CN 202110901320A CN 115892053 A CN115892053 A CN 115892053A
- Authority
- CN
- China
- Prior art keywords
- driving
- vehicle
- level
- road
- automation
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 8
- 230000003213 activating effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 238000013461 design Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides a vehicle-mounted intelligent management method and system for improving automatic driving performance, wherein the system comprises the following steps: a driving automation level determination module configured to: acquiring a vehicle support level of a vehicle on a current driving road section for automatic driving; determining a driving automation level of the vehicle performed on the current driving section based on the infrastructure support level of the current driving section and the acquired vehicle support level, wherein the driving automation level indicates an automatic driving capability of the vehicle on the current driving section; and a decision-making module configured to make an automated driving decision based on the determined level of driving automation. The invention also provides an automobile with the vehicle-mounted intelligent management system.
Description
Technical Field
The present invention relates to the field of Automated Driving (AD), and more particularly, to an in-vehicle intelligent management method and system for improving automated driving performance.
Background
In recent years, the development of automotive automatic driving technology has been rapid, and 3 organizations such as german federal highway research institute (BASt), the National Highway Traffic Safety Administration (NHTSA), the Society of Automotive Engineers (SAE) and the like have defined automatic driving levels in turn. In 2016, month 9, the J3016 standard for SAE is gradually becoming the world's common grading standard for autonomous vehicles, as NHTSA first adopted the grading standard for SAE in federal autonomous vehicle policy. The standard divides the autonomous vehicle into 6 levels (L0 to L5) according to the functional description of different levels of automation of the vehicle, the performer of the driving operation, the detector of the driving environment, the takeover after the failure of the driving task, the capability range of the autonomous system, and the like. In L0-L5, L0-L2 requires the driver to be in a driving state and to observe various situations from time to time, and in L3-L5, the driver need only sit on the driver's seat, and L3 requires the driver to take over the vehicle when needed. On 10.4.2020, the department of science and technology of the industry and informatization issues a recommended national standard, "automotive driving automation classification", which is consistent with the SAE standard in terms of thinking, for example, class 3/L3 and above are implemented by a system for automatic driving switched from human takeover, but on class 0-2 (L0-L2), the SAE J3016 standard requires to be completely operated by a human driver; the chinese standard is defined as being operated by an automatic driving system in conjunction with a human driver.
On the other hand, the digitalization and intelligentization construction of the traffic infrastructure is also continuously developed, and various sensors (such as high-definition cameras, laser radars, millimeter wave radars and the like) are arranged on many roads and used for sensing the local traffic environment and state in real time. In addition, some roads are also provided with road side units (OBUs) which are used for communicating with on-board units (OBUs) and all system components, so that all-dimensional connection between the roads and vehicles, between the roads and people and between the roads and cloud platforms is realized, and the functions of edge calculation and the like are further achieved.
Current autonomous driving solutions are mainly in the form of bicycle intelligence, i.e. environmental sensing and thus autonomous driving decision making are based only on-board sensors. However, the driving scenario in the real world is very complex, the cost is high if only the bicycle intelligence is considered, and there is a limitation in the development of automatic driving, so it is desirable to provide an improved automatic driving solution that can effectively reduce the cost and improve the reliability.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
Aiming at the problems, the invention integrates the scheme for solving the automatic driving from two different angles of the vehicle and the road, improves the automatic driving performance, and solves the bottleneck of intelligent development of the automatic driving single vehicle by taking the vehicle-road cooperation as a starting point and utilizing the support of traffic infrastructure.
According to one aspect of the invention, a vehicle-mounted intelligent management method is provided, and the method comprises the following steps:
acquiring a vehicle support level of a vehicle on a current driving road section for automatic driving;
determining a driving automation level of the vehicle performed on the current driving section based on the infrastructure support level of the current driving section and the acquired vehicle support level, wherein the driving automation level indicates an automatic driving capability of the vehicle on the current driving section; and
an automated driving decision is made based on the determined level of driving automation.
According to an embodiment of the invention, the method further comprises:
obtaining one or more contextual parameters relating to autonomous driving; and
adjusting the determined level of driving automation based on the obtained one or more contextual parameters.
According to a further embodiment of the invention, the context parameters comprise one or more of road conditions, road network type, road type, weather conditions.
According to a further embodiment of the present invention, determining the level of driving automation performed by the vehicle on the current travel section further comprises:
determining a driving automation level that can be met by the vehicle and the infrastructure of the current driving road section under cooperative sensing and calculation; and
determining the driving automation level that can be met as a driving automation level that the vehicle performs on the current driving road segment.
According to a further embodiment of the present invention, determining the level of driving automation performed by the vehicle on the current travel section further comprises:
inquiring a pre-maintained vehicle and road cooperative driving automation level table based on the infrastructure support level of the current running road section and the acquired vehicle support level, wherein the vehicle and road cooperative driving automation level table indicates driving automation levels corresponding to combinations of different infrastructure support levels and different vehicle support levels; and
and determining the inquired result as the driving automation level of the vehicle on the current driving road section.
According to a further embodiment of the invention, the automated driving decision comprises switching driving mode, maintaining driving mode, activating or deactivating an automated driving system.
According to a further embodiment of the invention, the method further comprises:
the user is notified of the automated driving decision made.
According to another aspect of the present invention, there is provided an in-vehicle intelligent management system, the system including:
a driving automation level determination module configured to:
acquiring a vehicle support level of a vehicle on a current driving road section for automatic driving;
determining a driving automation level of the vehicle performed on the current driving section based on the infrastructure support level of the current driving section and the acquired vehicle support level, wherein the driving automation level indicates an automatic driving capability of the vehicle on the current driving section; and
a decision-making module configured to make an automated driving decision based on the determined level of driving automation.
According to an embodiment of the invention, the decision-making module is further configured to:
obtaining one or more contextual parameters relating to autonomous driving; and
adjusting the determined level of driving automation based on the obtained one or more contextual parameters.
According to a further embodiment of the invention, the context parameters comprise one or more of road conditions, road network type, road type, weather conditions.
According to a further embodiment of the present invention, determining the level of driving automation performed by the vehicle on the current driving route segment further comprises:
determining a driving automation level that can be met by the vehicle and the infrastructure of the current driving road section under cooperative sensing and calculation; and
determining the driving automation level that can be met as a driving automation level that the vehicle performs on the current driving road segment.
According to a further embodiment of the present invention, determining the level of driving automation performed by the vehicle on the current driving route segment further comprises:
inquiring a pre-maintained vehicle and road cooperative driving automation level table based on the infrastructure support level of the current running road section and the acquired vehicle support level, wherein the vehicle and road cooperative driving automation level table indicates driving automation levels corresponding to combinations of different infrastructure support levels and different vehicle support levels; and
and determining the inquired result as the driving automation level of the vehicle on the current driving road section.
According to a further embodiment of the invention, the automated driving decision comprises switching driving mode, maintaining driving mode, activating or deactivating an automated driving system.
According to still another aspect of the present invention, there is provided an automobile including:
a communication module configured to obtain digitized infrastructure information from a roadside infrastructure for autonomous driving;
the aforementioned in-vehicle intelligent management system configured to obtain the digitized infrastructure information via the communication module, determine the level of driving automation, and make automated driving decisions in conjunction with the obtained one or more contextual parameters; and
a vehicle control module configured to perform a respective vehicle control action based on the automated driving decision made.
According to one embodiment of the invention, the vehicle control module is further configured to inform the user of the automated driving decision made.
In view of the problems in the prior art, the present invention provides an onboard intelligent management system for improving automatic driving performance, which has at least the following advantages:
1. the automatic driving performance is improved/maintained by using road infrastructure support (for example, by using roadside facility equipment such as high-precision positioning, facility monitoring and intelligent perception monitoring) in a complex and variable traffic scene, and the intelligent cost of an automatic driving single vehicle is reduced;
2. edge computing capacity is set at the roadside, perception and decision are processed uniformly, the threshold of automatic driving can be greatly reduced through vehicle-road cooperation, and the bottleneck of intelligent development of an automatic driving single vehicle is solved; and
3. under the condition of considering the context parameters such as road conditions, weather conditions and the like, a better automatic driving decision is made, the automatic driving performance is improved, and the driving safety is improved.
These and other features and advantages will become apparent upon reading the following detailed description and upon reference to the accompanying drawings. It is to be understood that both the foregoing general description and the following detailed description are explanatory only and are not restrictive of aspects as claimed.
Drawings
So that the manner in which the above recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only some typical aspects of this invention and are therefore not to be considered limiting of its scope, for the description may admit to other equally effective aspects.
FIG. 1 shows an architectural diagram of an in-vehicle intelligent management system for improving autopilot performance, according to one embodiment of the present invention.
FIG. 2A shows a schematic diagram of improving autopilot performance with infrastructure support in a conventional situation according to one embodiment of the invention.
FIG. 2B shows a schematic diagram of maintaining autopilot performance with infrastructure support in an extreme situation according to one embodiment of the invention.
FIG. 3 shows a schematic flow diagram of an in-vehicle intelligent management method for improving autopilot performance according to one embodiment of the invention.
Fig. 4 shows a schematic structural diagram of a motor vehicle according to an embodiment of the invention.
Detailed Description
The present invention will be described in detail below with reference to the attached drawings, and the features of the present invention will be further apparent from the following detailed description.
FIG. 1 is an architectural diagram of an in-vehicle intelligent management system for improving autopilot performance, according to one embodiment of the present invention. As shown in fig. 1, the in-vehicle intelligent management system 100 may include at least a driving automation level determination module 101 and a decision making module 102.
The driving automation level determination module 101 may acquire a vehicle support level for the automated driving in the current travel section. The vehicle support level for the automatic driving may be classified into 6 classes (L0-L5) by the driving automation classification standard SAE J3016. Table 1 below specifically shows the driving automation ranking according to NHTSA and SAE standards.
Table 1: automated grading of driving according to NHTSA and SAE standards
In the SAE standard, the term "Dynamic Driving Task (DDT)" refers to all real-time operational and strategic functions required for a car to travel on a road. The term "design operational domain (ODD)" refers to the conditions and scope of applicability under which an autonomous driving system is designed to function, including, but not limited to, environmental, geographic, and temporal limitations, as well as traffic or roads that possess specific conditions. The ODD parameters include, for example, road type, road conditions, weather conditions, vehicle speed, traffic volume, etc. For example, the ODD indicates that the autopilot system can only operate at 35mph or less in a certain geo-fenced area. Specifically, as shown in table 1, level L0 represents full authority driving of the automobile by a human driver; the L1 level represents that an automatic system can assist a driver to complete certain driving tasks at times, one operation of a steering wheel and acceleration and deceleration is supported through a driving environment, and the rest is operated by a human driver; the L2 level represents that the automatic system can complete some driving tasks, but a driver needs to monitor the driving environment to complete the rest part, and meanwhile, the taking over is carried out at any time under the condition that problems occur, at the level, the error sensing and judgment of the automatic system are corrected at any time by the driver, and the level can be divided into different use scenes through the speed and the environment, such as loop low-speed traffic jam, rapid driving on a high-speed road, automatic parking of the driver in the vehicle and the like; level L3 represents that the automated system can perform some driving tasks and in some cases monitor the driving environment, but the driver must be ready to regain driving control when requested by the automated system, i.e. the hierarchy requires that all Dynamic Driving Tasks (DDTs) can be performed within a defined design operating domain (ODD), but requires that the driver be ready at all times to handle requests for driver intervention by the unmanned system when the system fails or goes beyond the range of the ODD, but requires in the standard that the system can continue to control the car for a few seconds before driver intervention after a driver intervention request is made; the L4 level represents that an automated system can complete driving tasks and monitor the driving environment in certain environments and specific conditions, and this level requires that the system not only can complete Dynamic Driving Tasks (DDT) within the ODD range, but also can cope with system failures without driver intervention; the L5 level represents that the automatic system can complete all driving tasks under all conditions, and the system is in failure, and an ODD is not required to be defined.
In some cases, the vehicle support level of the current driving section may reach the maximum level (e.g., level L2) that the autopilot/autopilot assist system is designed to reach when the vehicle is normally driving within a defined design operational domain (ODD). In other cases, when the vehicle encounters an extreme situation on the current travel segment, the current vehicle support level may drop, for example, to level L0, with the full authority of the human driver to take over driving control.
Subsequently, the driving automation level determination module 101 may determine a driving automation level performed by the vehicle on the current travel section based on the infrastructure support level of the current travel section and the acquired vehicle support level. In some aspects, with coordinated sensing and computation of the road-side infrastructure of the current road segment being traveled, the level of driving automation and stability of autonomous driving performed by the vehicle on the current road segment may be enhanced to some extent (e.g., above the current vehicle support level) or may be maintained in extreme traffic scenarios (e.g., on road segments where fog is occurring).
The road infrastructure support may be divided into 5 levels (a-E) according to the following intelligent internet road classification criteria, as shown in table 2 below.
Table 2: intelligent internet road grading
However, currently, the digital information provided by the roadside infrastructure is generally used for traffic flow status information reminding, navigation, and the like, for example, on the road segments with the grades a and B, the roadside infrastructure can monitor the microscopic traffic condition and sense the local traffic environment and status in real time, so as to realize more accurate navigation, but the digital information is not fused with the automatic driving of the vehicle.
In the present invention, different levels of road infrastructure support may assist the vehicle in autonomous driving to different degrees. For example, in the case where the road infrastructure support is classified into a-E levels according to the intelligent internet road classification standard as described above, the E level represents a conventional infrastructure without digitized information, does not support autonomous driving, and relies entirely on the recognition of road geometry and road identification by the autonomous vehicle itself; the level D supports static digital information including static road marks, and traffic lights, short-term road engineering, variable information boards and the like need to be identified by automatic driving vehicles; level C supports static and dynamic infrastructure information, including variable message boards, alerts, accidents, weather, etc., all of which may be acquired in a digitized form and provided to the autonomous vehicle; level B supports intelligent awareness, i.e., infrastructure can perceive microscopic traffic conditions and provide real-time to autonomous vehicles; level a supports smart driving, i.e., the infrastructure can direct autonomous vehicles (single cars or formation) to achieve global traffic flow optimization based on real-time information of vehicle movement. Thus, autonomous driving is not supported in case the road infrastructure is a traditional infrastructure (D-E) and thus cannot assist in improving the autonomous driving performance of the vehicle, whereas autonomous driving vehicles can be supported in case the road infrastructure is a digital infrastructure (a-C) and the level of driving automation of the vehicle is improved to a certain extent. The promotion of the driving automation level with the support of the road infrastructure is specifically shown in table 3 below.
| E | D | C | B | A | |
| L0 | - | - | L0 + | L0 + | L0 + |
| L1 | - | - | L1 + | L1 + | L1 + |
| L2 | - | - | L2 + | L2 + | L3 |
| L3 | - | - | L3 + | L3 + | L4 |
| L4 | - | - | L4 + | L4 + | L4 + |
Table 3: automatic grade table for vehicle and road cooperative driving
As shown in table 3, in one example, the vehicle support level for the automated driving is level L2 (partial automation) at the current road section, and the infrastructure support level for the automated driving is level a (smart driving) at the current road section, the driving automation level determination module 101 may determine that the driving automation level of the vehicle is raised to level L3 because the automated driving ability of the vehicle is improved by the vehicle-road coordination with the support of the road infrastructure. The boosting of the autopilot capability with roadside infrastructure support will be described in more detail below in fig. 2A-2B with examples of normal and extreme cases.
The decision-making module 102 may obtain one or more contextual parameters relating to autonomous driving, where the one or more contextual parameters include, but are not limited to, road conditions (such as traffic accidents, traffic jams, traffic lights, etc.), road types (freeways, urban roads, rural roads, etc.), weather conditions (such as light, temperature, wind, etc.), and the like. The one or more contextual parameters may be obtained by, for example, a sensor system of the vehicle, an On Board Unit (OBU), or the like. Sensor systems include, but are not limited to, cameras, millimeter wave radars, lidar, and the like. The decision-making module 102 may further combine the obtained one or more contextual parameters and the determined autopilot ability to make and inform a driver or user of an autopilot decision. In one example, where the current design operational realm (ODD) indicates that the vehicle's autonomous driving system can only operate in sunny weather, the decision-making module 102 may determine that the vehicle has left the design operational realm (ODD) if the decision-making module 102 obtains contextual parameters relating to extreme weather (rainstorm, snowstorm), make an autonomous driving decision to switch driving modes (e.g., take over driving control by the driver), and notify the driver to take over driving control. In another example, the vehicle's autonomous driving capability at the current road segment is level L3 (L2 + a), then despite the sudden appearance of a cloud in the front, the vehicle's autonomous driving system, with the support of the road infrastructure, can remain operational in this extreme weather situation and pass smoothly through the road segment without the driver taking over, in which case the decision-making module 102 can make autonomous driving decisions without switching driving modes, and can make no prompt to the driver.
Fig. 2A and 2B show the determination of the autopilot capability of a vehicle on a current road segment in an example of a normal situation and an extreme situation, respectively. FIG. 2A is a schematic illustration of improving autopilot performance with infrastructure support in a conventional situation according to one embodiment of the invention. As shown in fig. 2A, assuming that the vehicle travels to a section of road infrastructure level a, the driving automation level of the vehicle may be raised to L3 with the support of the roadside infrastructure in the case where the vehicle support level is L2. That is, since the road infrastructure of the current road segment provides functions of complete perception, prediction, decision, control, communication and the like in all scenes, the vehicle support level L2 vehicle can be assisted in monitoring the driving environment in the current road segment without the driver monitoring the driving environment, so that the vehicle can achieve the L3 level of automatic driving performance (since the L2 level also requires the driver to monitor the driving environment, and the L3 level does not require the driver to monitor the driving environment at any time). Furthermore, with a vehicle support level of L3, the driving automation level of the vehicle can be raised to L4 with the support of the road-side infrastructure, i.e. the autonomous driving system does not require driver intervention in case of a failure, a system failure can be countered e.g. by support of the road infrastructure (since the L3 level also requires driver intervention in case of an autonomous driving system failure, whereas the L4 level already does not require driver intervention). Further, in the case where the vehicle support level is L4, the driving automation level of the vehicle may be raised to L4 with the support of the roadside infrastructure + Here, L4 + It means that the automatic driving ability of the vehicle is improved to some extent on the basis of the L4 level (for example, the function of the portion L5 can be implemented), and the stability of automatic driving can be maintained (for example, not degraded) under extreme conditions.
Fig. 2B is a schematic diagram of maintaining autopilot performance with infrastructure support in an extreme situation according to one embodiment of the invention. As shown in fig. 2B, assuming that the vehicle travels to a road segment with a road infrastructure level a, the original automatic driving level can be maintained with the support of the roadside infrastructure even when the vehicle encounters an extreme situation (e.g., extreme weather (heavy rain, heavy snow, etc.), high speed merge, damaged sign lines, forward construction, etc.). For example, in the case where the current vehicle support level is L2/L3, the automated driving level should be reduced to L0 and the driving control authority taken over by the driver due to the departure from the ODD upon encountering an extreme situation, but detailed driving instructions are provided for the vehicle with the support of the roadside infrastructure of level a, so that the automated driving level is maintained at L2/L3. In the case where the current vehicle support level is L4, the autonomous driving level should be reduced to L1 due to encountering an extreme situation, but the autonomous driving level can be maintained at L4 without any operation by the driver with the support of the roadside infrastructure of level a.
FIG. 3 is a schematic flow diagram of an on-board intelligent management method for improving autopilot performance, according to one embodiment of the present invention. The method starts in step 301, where the driving automation level determination module 101 obtains a vehicle support level for automatic driving at a current driving road section, where the vehicle support level is L0-L5 from low to high, and is respectively non-automation, driving support, partial automation, conditional automation, high automation, and full automation.
In step 302, the driving automation level determination module 101 determines a driving automation level of the vehicle on the current driving section based on the infrastructure support level of the current driving section, which may be classified into a-E levels from high to low, smart driving, smart awareness, dynamic digital information, static digital information, and legacy infrastructure, and the acquired vehicle support level. The autopilot capability of a vehicle on a current travel segment may be enhanced/maintained due to the support of the digital road infrastructure. For example, in the case where the vehicle support level of the current road section is L2 and the road infrastructure is capable of full perception and global traffic flow optimization (level a), the driving automation level determination module 101 may query a previously maintained vehicle-and-road cooperative driving automation level table (e.g., table 3) indicating driving automation levels corresponding to different infrastructure support levels and combinations of different vehicle support levels, and determine the queried result (L3) as the driving automation level performed by the vehicle on the current travel road section.
In step 303, the decision-making module 102 obtains one or more contextual parameters related to autonomous driving, wherein the one or more contextual parameters include factors that affect autonomous driving, such as road network type, road conditions, weather conditions, and the like.
At step 304, the decision-making module 102 adjusts the determined level of driving automation based on the obtained one or more contextual parameters.
In step 305, the decision-making module 102 makes an automated driving decision based on the determined level of driving automation. Alternatively, the decision-making module 102 may notify the driver or user of the automated driving decision after the decision is made. In one example, the automated driving decision may be to switch driving modes, with the driver taking over driving control. In another example, the automated driving decision may be to switch driving modes, with the automated driving system taking over driving control. In yet another example, the automated driving decision may be to maintain driving mode without informing the driver to take over driving control. In one scenario, where a vehicle at a vehicle support level L2 is traveling on a road segment with a higher road intelligence level (e.g., level a), the roadside infrastructure can assist the vehicle in making intelligent awareness to maintain the vehicle's ability to autonomously drive even in extreme weather conditions, so that autonomous driving decisions can be made to maintain driving patterns without the driver taking over driving control.
Fig. 4 shows a schematic structural diagram of a vehicle 400 according to an embodiment of the invention. The automobile 400 includes at least a communication module 401, a vehicle control module 402, and the in-vehicle intelligent management system 100. In one example, the communication module 401 may communicate with the road-side infrastructure on the road segment where the automobile is currently located and obtain digitized information from the road-side infrastructure for autopilot, e.g., where a variable intelligence board (VMS) is present on the current road segment, the automobile may obtain dynamic infrastructure information from the VMS in a digitized form via the communication module 401 to enhance autopilot capability. The in-vehicle intelligent management system 100 may determine a level of driving automation (e.g., L2+ a- > L3) for the vehicle on the current road segment based on the roadside infrastructure support level and the current vehicle support level, and make automated driving decisions (e.g., whether to switch driving modes, whether to be taken over by the driver, whether to voice prompt the driver, etc.) in conjunction with contextual parameters of road conditions, weather conditions, etc. The vehicle control module 402 may obtain the automated driving decisions made from the in-vehicle intelligent management system 100 and perform corresponding vehicle control actions according to the obtained decisions. Vehicle control actions include, for example, switching driving modes, activating an autonomous system, deactivating an autonomous system, prompting a driver to increase attention through voice or seat vibration, etc. In one example, the vehicle control module 402 may control the vehicle to deactivate the autonomous driving system based on an autonomous driving decision to switch driving modes and be taken over by the human driver at all authority, and prompt the driver to take over driving control.
What has been described above includes examples of aspects of the claimed subject matter. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the claimed subject matter, but one of ordinary skill in the art may recognize that many further combinations and permutations of the claimed subject matter are possible. Accordingly, the disclosed subject matter is intended to embrace all such alterations, modifications and variations that fall within the spirit and scope of the appended claims.
Claims (15)
1. An onboard intelligent management method, the method comprising:
acquiring a vehicle support level of a vehicle on a current driving road section for automatic driving;
determining a driving automation level of the vehicle performed on the current driving section based on the infrastructure support level of the current driving section and the acquired vehicle support level, wherein the driving automation level indicates an automatic driving capability of the vehicle on the current driving section; and
an automated driving decision is made based on the determined level of driving automation.
2. The method of claim 1, further comprising:
obtaining one or more contextual parameters relating to autonomous driving; and
adjusting the determined level of driving automation based on the obtained one or more contextual parameters.
3. The method of claim 2, wherein the contextual parameters comprise one or more of road conditions, road network type, road type, weather conditions.
4. The method of claim 1, wherein determining a level of driving automation performed by the vehicle on the current travel segment further comprises:
determining a driving automation level that can be met by the vehicle and the infrastructure of the current driving road section under cooperative sensing and calculation; and
determining the driving automation level that can be met as a driving automation level that the vehicle performs on the current driving road segment.
5. The method of claim 1, wherein determining a level of driving automation performed by the vehicle on the current travel segment further comprises:
inquiring a pre-maintained vehicle and road cooperative driving automation level table based on the infrastructure support level of the current running road section and the acquired vehicle support level, wherein the vehicle and road cooperative driving automation level table indicates driving automation levels corresponding to combinations of different infrastructure support levels and different vehicle support levels; and
and determining the inquired result as the driving automation level of the vehicle on the current driving road section.
6. The method of claim 1, wherein the autonomous driving decision comprises switching driving modes, maintaining driving modes, activating an autonomous driving system, or deactivating an autonomous driving system.
7. The method of claim 1, further comprising:
the user is notified of the automated driving decision made.
8. An in-vehicle intelligent management system, the system comprising:
a driving automation level determination module configured to:
acquiring a vehicle support level of a vehicle on a current driving road section for automatic driving;
determining a driving automation level of the vehicle performed on the current driving section based on the infrastructure support level of the current driving section and the acquired vehicle support level, wherein the driving automation level indicates an automatic driving capability of the vehicle on the current driving section; and
a decision-making module configured to make an automated driving decision based on the determined level of driving automation.
9. The system of claim 8, wherein the decision-making module is further configured to:
obtaining one or more contextual parameters relating to autonomous driving; and
adjusting the determined level of driving automation based on the obtained one or more contextual parameters.
10. The system of claim 9, wherein the contextual parameters include one or more of road conditions, road network type, road type, weather conditions.
11. The system of claim 8, wherein determining a level of driving automation performed by the vehicle on the current travel path further comprises:
determining a driving automation level that can be met by the vehicle and the infrastructure of the current driving road section under cooperative sensing and calculation; and
determining the driving automation level that can be satisfied as a driving automation level that the vehicle performs on the current driving section.
12. The system of claim 8, wherein determining a level of driving automation performed by the vehicle on the current travel segment further comprises:
inquiring a pre-maintained vehicle and road cooperative driving automation level table based on the infrastructure support level of the current running road section and the acquired vehicle support level, wherein the vehicle and road cooperative driving automation level table indicates driving automation levels corresponding to combinations of different infrastructure support levels and different vehicle support levels; and
and determining the inquired result as the driving automation level of the vehicle on the current driving road section.
13. The system of claim 8, wherein the autonomous driving decision comprises switching driving modes, maintaining driving modes, activating an autonomous driving system, or deactivating an autonomous driving system.
14. An automobile, the automobile comprising:
a communication module configured to obtain digitized infrastructure information from a roadside infrastructure for autonomous driving;
the in-vehicle intelligent management system of any of claims 8 to 13, configured to acquire the digitized infrastructure information via the communication module, determine the level of driving automation, and make an automated driving decision in conjunction with the acquired one or more contextual parameters; and
a vehicle control module configured to perform a respective vehicle control action based on the automated driving decision made.
15. The automobile of claim 14, wherein the vehicle control module is further configured to notify a user of the automated driving decision made.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901320.4A CN115892053A (en) | 2021-08-06 | 2021-08-06 | Vehicle-mounted intelligent management method and system for improving automatic driving performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901320.4A CN115892053A (en) | 2021-08-06 | 2021-08-06 | Vehicle-mounted intelligent management method and system for improving automatic driving performance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115892053A true CN115892053A (en) | 2023-04-04 |
Family
ID=86478230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110901320.4A Pending CN115892053A (en) | 2021-08-06 | 2021-08-06 | Vehicle-mounted intelligent management method and system for improving automatic driving performance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115892053A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116238527A (en) * | 2023-05-10 | 2023-06-09 | 江铃汽车股份有限公司 | Intelligent driving auxiliary protection method and device, electronic equipment and medium |
-
2021
- 2021-08-06 CN CN202110901320.4A patent/CN115892053A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116238527A (en) * | 2023-05-10 | 2023-06-09 | 江铃汽车股份有限公司 | Intelligent driving auxiliary protection method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11615706B2 (en) | System and method for driving assistance along a path | |
| KR102257112B1 (en) | Dynamic routing for autonomous vehicles | |
| US12005897B1 (en) | Speed planning for autonomous vehicles | |
| US10627825B2 (en) | Using discomfort for speed planning in autonomous vehicles | |
| US12005891B2 (en) | Early object detection for unprotected turns | |
| KR20180078973A (en) | Cooperative Adaptive Cruise Control based on Driving Pattern of Target Vehicle | |
| CN111629944B (en) | Vehicle control device, vehicle, and vehicle control method | |
| US11747815B2 (en) | Limiting function of a vehicle control device related to defective image | |
| JP2021088289A (en) | Drive assist device | |
| CN116034359A (en) | Method for environment detection with at least two mutually independent imaging environment detection sensors, device for carrying out the method, vehicle and correspondingly designed computer program | |
| CN111731318B (en) | Vehicle control device, vehicle control method, vehicle, and storage medium | |
| CN114248798A (en) | Improving passenger boarding and disembarking of autonomous vehicles using weather information | |
| CN113264042B (en) | Hidden danger situation warning | |
| CN115892053A (en) | Vehicle-mounted intelligent management method and system for improving automatic driving performance | |
| CN113226878B (en) | Iron road lamp detection | |
| US11590978B1 (en) | Assessing perception of sensor using known mapped objects | |
| US11899697B2 (en) | Information processing server, processing method for information processing server, and non-transitory storage medium | |
| CN113511218B (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN118545086A (en) | Vehicle operation judging method and device | |
| CN114084160A (en) | Driving assistance device, and corresponding vehicle, method, computer device, and medium | |
| CN116331192A (en) | Vehicle control device, vehicle control method, and storage medium | |
| Bahram et al. | Driver Assistance System for Curvy Roads Using Fuzzy logic. |
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 |