CN110349425B - Important target generation method for vehicle-road cooperative automatic driving system - Google Patents
Important target generation method for vehicle-road cooperative automatic driving system Download PDFInfo
- Publication number
- CN110349425B CN110349425B CN201910745048.8A CN201910745048A CN110349425B CN 110349425 B CN110349425 B CN 110349425B CN 201910745048 A CN201910745048 A CN 201910745048A CN 110349425 B CN110349425 B CN 110349425B
- Authority
- CN
- China
- Prior art keywords
- information
- target
- degree
- behavior
- calculating
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides an important target generation method for a vehicle-road cooperative automatic driving system, and belongs to the field of automatic driving. The important target generation method comprises the following steps: acquiring related information of a plurality of targets around the vehicle; sequentially calculating behavior characteristic information and attribute characteristic information of each target according to the related information; calculating the overall importance of the target according to the behavior characteristic information and the attribute characteristic information; arranging the targets with the overall importance degrees larger than a first threshold value in a descending order according to the overall importance degrees to form a list to be selected; and sequentially selecting the targets with the number not more than a preset number from the top item to the back item in the list to be selected so as to form an important target list. The important target generation method of the invention can finely analyze targets around the vehicle to obtain the important target list.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to an important target generation method for a vehicle-road cooperative automatic driving system.
Background
The automatic driving technology is a technical hotspot of the current automobile industry, and is mainly divided into six automatic driving grades of L0-L5 at present according to the automatic driving grade of SAE, wherein the grade L0 refers to vehicles without any automatic driving function, the grade L1-L2 automatic driving is still A Driving Assistance System (ADAS) per se, the grade L3 automatic driving can be called a quasi-automatic driving system, and the grade L4-L5 automatic driving can be considered as a truly meaningful automatic driving system.
In a conventional L1-L2-level automatic driving vehicle, vehicle-mounted sensors (GPS, IMU, wheel speed sensor, etc.) and sensing sensors (forward radar, forward looking camera, ultrasonic radar, etc.) are mainly used to implement auxiliary driving functions in simple scenes, such as acc (adaptive Cruise control), AEB, TJA, HWA, etc. With the improvement of the automatic driving function and the safety level, the vehicle needs to have more accurate sensing and positioning capability, more reliable and stable decision control capability and capability of processing more complex scenes. Therefore, higher requirements are put on the self-vehicle and peripheral environment perception capabilities, for example, the autonomous vehicle of L3-L5 realizes the environment perception capabilities of high-precision map/positioning, dynamic and static target detection and tracking, lane road edge detection, traffic sign identification and the like by adding a forward laser radar, a plurality of angle radars and side radars, a high-pixel forward-looking camera, a side-looking camera, a rear-looking camera, a high-precision map server and the like.
In the vehicle-road cooperative system, vehicles or roadbed facilities can acquire peripheral target information through a perception sensor, wherein most targets are common targets, and simply targets which do not have great influence on the whole vehicle running; some of the targets are important targets, simply targets that are likely to affect the normal driving of the host vehicle. For important targets, the automatic driving vehicle needs to be monitored in a focused mode to acquire information such as position, speed, acceleration, course angle and the like, so that the important targets can be synchronously tracked and locked in the direction with concentrated sensing capability of the sensor. Therefore, a more detailed analysis of the targets in the area is required to obtain the list of important targets.
Disclosure of Invention
An object of the present invention is to provide an important target generation method for a vehicle-road cooperative automatic driving system, which is capable of finely analyzing targets around a vehicle to obtain an important target list.
In particular, the invention provides an important target generation method for a vehicle-road cooperative automatic driving system, which comprises the following steps:
acquiring related information of a plurality of targets around the vehicle;
sequentially calculating behavior characteristic information and attribute characteristic information of each target according to the related information;
calculating the overall importance of the target according to the behavior characteristic information and the attribute characteristic information;
arranging the targets with the overall importance degrees larger than a first threshold value in a descending order according to the overall importance degrees to form a list to be selected;
and sequentially selecting the targets with the number not more than a preset number from the top item to the back item in the list to be selected so as to form an important target list.
Optionally, the behavior feature information includes: behavioral anomaly, behavioral reckimy, and collision risk of the target;
the attribute feature information includes: the target's own vulnerability, significant threat and additional interest.
Optionally, calculating the overall importance of the target according to the behavior feature information and the attribute feature information includes:
weighting and taking the maximum of the behavioral abnormality degree, the behavioral reckless degree, the collision risk degree, the self-vulnerability degree, the significant threat degree and the additional interest degree of the target as the overall importance degree of the target.
Optionally, weighting and taking the maximum of the behavioral abnormality, the behavioral reckless degree, the collision risk, the self-vulnerability, the significant threat degree and the additional interestingness of the target as the overall importance of the target, comprising:
the weighting coefficients of the collision risk degree and the additional interestingness degree are both larger than the weighting coefficients of the behavior abnormality degree, the behavior reckless degree, the self-vulnerability degree or the significant threat degree.
Optionally, sequentially calculating behavior feature information and attribute feature information of each target according to the related information, including:
acquiring traffic rule information of the current position of the target;
acquiring the current traffic behavior information of the target;
and calculating the behavior abnormality degree according to the traffic rule information and the traffic behavior information.
Optionally, sequentially calculating behavior feature information and attribute feature information of each target according to the related information, including:
acquiring the change rate information of the motion information of the target;
and calculating the action reckimic degree according to the movement information change rate information.
Optionally, sequentially calculating behavior feature information and attribute feature information of each target according to the related information, including:
calculating a risk value of collision of the target with the vehicle;
and calculating the collision risk degree according to the risk value.
Optionally, sequentially calculating behavior feature information and attribute feature information of each target according to the related information, including:
acquiring classification information, appearance information and size information of the target;
and calculating the self-fragility according to the classification information, the appearance information and the size information.
Optionally, sequentially calculating behavior feature information and attribute feature information of each target according to the related information, including:
acquiring classification information, appearance information, size information and plug-in information of the target;
and calculating the significant threat degree according to the classification information, the appearance information, the size information and the plug-in information.
Optionally, sequentially calculating behavior feature information and attribute feature information of each target according to the related information, including:
receiving a target list which needs extra attention and is sent by a third-party interest correlator;
calculating the additional interestingness according to the target list.
The invention analyzes whether the target has significant influence on the vehicle or not according to the behavior characteristic information and the attribute characteristic information of the target, namely calculates the overall importance, selects a certain number of important targets according to the influence (namely the overall importance), and forms an important target list in descending order for the subsequent analysis and calculation of the vehicle. The method obtains the important target list by finely analyzing the targets around the vehicle.
Further, the invention provides a new method for obtaining importance subdivision metrics of the target, which comprises the steps of calculating six metrics of the behavior abnormality degree, the behavior reckless degree, the collision risk degree, the self fragility degree, the significant threat degree and the additional interest degree of the target, finally obtaining the importance of the target in a weighted average mode, and finally outputting the target with high importance to form an important target list.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter, by way of illustration and not limitation, with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
FIG. 1 is a flow diagram of a method of important object generation, according to one embodiment of the present invention.
Detailed Description
FIG. 1 is a flow diagram of a method of important object generation, according to one embodiment of the present invention. As shown in fig. 1, the present invention provides an important target generation method for a vehicle-road cooperative automatic driving system, which may generally include the steps of:
s10: information on a plurality of objects in the periphery of the vehicle is acquired.
The related information may include three-dimensional position information of the object (X, Y, Z coordinate values in a global positioning coordinate system or a geodetic coordinate system), three-dimensional size information of the object (length, width, height), three-dimensional heading angle information of the object (rotation angle around X-axis, rotation angle around Y-axis, rotation angle around Z-axis), three-dimensional speed information of the object (X-speed, Y-speed, Z-speed), three-dimensional acceleration information of the object (X-acceleration, Y-acceleration, Z-acceleration), three-axis angular speed information of the object (rotation angular speed around X-axis, rotation angular speed around Y-axis, rotation angular speed around Z-axis), category information of the object (category of car, pedestrian, bicycle, truck, motorcycle, unknown, etc.), confidence information of the object (ultra-low, high, and the like), Low, medium, high, super high, etc.), detection probability information of the target (a probability value of 0 or more and 1 or less), special behavior information of the target (e.g., the target walks to see the mobile phone, the target drives to doze, etc.), and the like.
S20: and sequentially calculating the behavior characteristic information and the attribute characteristic information of each target according to the related information.
The behavior characteristic information is used for representing the behavior characteristics of the target, and the attribute characteristic information is used for representing the characteristics of the target.
S30: and calculating the overall importance of the target according to the behavior characteristic information and the attribute characteristic information.
S40: and arranging the targets with the overall importance degrees larger than the first threshold value in a descending order according to the overall importance degrees to form a list to be selected.
S50: and sequentially selecting the targets with the number not more than the preset number from the top item to the back item in the list to be selected so as to form an important target list.
According to the important target generation method, whether the target has a significant influence on the vehicle is analyzed according to the behavior characteristic information and the attribute characteristic information of the target, namely, the overall importance is calculated, a certain number of important targets are selected according to the influence (namely, the overall importance), and an important target list in descending order is formed for subsequent analysis and calculation of the vehicle. The method obtains the important target list by finely analyzing the targets around the vehicle.
In one embodiment, the behavior feature information includes: behavioral anomaly, behavioral reckless degree, and collision risk of the target.
In another embodiment, the attribute feature information includes: the vulnerability of the target itself, significant threat and additional interest.
In one embodiment, the calculating of the degree of behavioral abnormality in S30 includes the steps of:
acquiring traffic rule information of a current position of a target;
acquiring current traffic behavior information of a target;
and calculating the behavior abnormality degree according to the traffic regulation information and the traffic behavior information.
According to the high-precision map information (lane line information, ground identification information, traffic signal light information and the like) and the positioning information (position information and posture information) of the target, the position and the traffic scene of the target in the high-precision map can be obtained so as to obtain the traffic regulation information of the current position of the target, namely, the position at which the vehicle should run according to what traffic regulation. According to the perception information (category, course information, speed information, acceleration information, angular speed information and the like) of the target, the specific traffic behavior information of the target can be obtained. And then, whether the target is abnormal or not can be judged according to the traffic rule information of the relevant position in the high-precision map and the specific traffic behavior information of the target.
In one embodiment, the behavior abnormality can be expressed in three forms, one is that the traffic behavior of the target violates the traffic regulations, is easy to cause traffic accidents, and needs high focus attention; the other is that although the behavior does not violate the traffic rules, the target is located in a potential traffic risk area, which may cause potential traffic accidents, and needs important attention; the other is that the attention of the target is not concentrated during the process of participating in the traffic, so that dangerous behaviors can be performed to cause traffic accidents, and the important attention is also needed.
First class of behavioral anomalies-targets violate traffic rules: for example, in a high speed functional scenario, if the vehicle is driving in reverse, the intersection rule is violated; in the scene of an urban traffic intersection, if a pedestrian crosses the road in a red state of a pedestrian signal lamp, the traffic regulations are violated. In addition, there are many ways to determine whether a target violates a traffic regulation. Degree of behavioral abnormality ρ of a first type of targetabn1The traffic rule can be calculated according to the position of the target, the traffic rule of the high-precision map at the position of the target, the specific traffic behavior of the target and other information.
The second category of behavioral anomalies-targets in potential traffic risk areas: for example, in a highway scene, a vehicle with double-flash is parked on the shoulder of a road, and although the vehicle does not violate the traffic regulations, other traffic participants need to pay high attention when passing by so as to prevent sudden start of the parked vehicle or sudden traffic accidents caused by the pedestrian moving out of the vehicle or behind the vehicle. In addition, there are many ways to determine whether an abnormal behavior of a target may lead to a potential traffic accident. Degree of behavioral abnormality ρ of target of second kindabn2The information can be obtained by calculating the characteristics of the position of the target, the category attribute behavior of the target and the like, the potential risk level of the position of the target on the high-precision map and the like.
A third category of behavioral anomalies-target inattention: for example, pedestrians read books or mobile phones while walking, drivers of vehicles read mobile phones while driving, and so on. In addition, there are many ways to determine whether a target is behaving inattentively. Degree of abnormality ρ of the third kind of behavior of the targetabn3The position of the target can be calculated through information such as the position of the target, special behavior information of the target, and position characteristics of the target on a high-precision map.
Degree of behavioral abnormality ρ of targetabnThe above information weighting calculation can be used, and the calculation formula is as follows:
ρabn＝αabn1·ρabn1+αabn2·ρabn2+αabn3·ρabn3 (1)
where α isabniThe weighted value of the i-th-1, 2,3, … … class abnormal behavior degree (satisfying alpha)abn1≥2αabn2≥6αabn3And αabn1+αabn2+αabn31 means that the first class of behavioral abnormality degree has the highest weight, and the third class of behavioral abnormality degree has the lowest weight, for example, α may be takenabn1＝0.6，αabn2＝0.3，αabn3＝0.1)，ρabniThe i-th class behavioral abnormality degree (satisfying 0 ≦ ρ) obtained for the foregoing calculationabni1, for i ≦ 1,2,3 … …). Where the degree of behavioral abnormality of the object satisfies 0 ≦ ρabn≤1。
In one embodiment, the step of calculating the behavior reckimy degrees in S30 includes the steps of:
acquiring the change rate information of the motion information of the target;
and calculating the action reckimic degree according to the motion information change rate information.
The target behavior is reckless, which refers to the extreme behaviors of impatience, rough, impulsion, nervousness, uncontrolled and the like of a target in the process of participating in traffic. These reckimic behaviors are diverse, and may be due to the fact that the manipulator of the target (vehicle) compares reckimic results in reckimic target vehicle behaviors being manipulated, on the one hand, and due to the fact that the target stalls, overruns, overturns, etc. look like reckimic behaviors due to the failure of the devices of the target's brakes, steering, engines, etc. According to the perception information (category, course information, speed information, acceleration information, angular speed information and the like) of the target, whether the target acts reckless or not can be judged.
Reckimate rho of targetaggThe target behavior is considered to be reckless if at least more than one amplitude of the motion change rates exceeds a set threshold, and the reckless degree is higher if the more motion change rates exceed the threshold. Where the reckimic degree satisfies 0 ≦ ρagg≤1。
In one embodiment, the step of calculating the collision risk degree in S30 includes the steps of:
calculating a risk value of collision between the target and the vehicle;
and calculating the collision risk degree according to the risk value.
According to the perception information of the target and the vehicle-mounted bus information of the vehicle, whether the vehicle and the target potentially collide can be judged. The higher the threat of potential collision between the target and the host vehicle, the higher the risk of collision. For example, the traveling trajectory of the host vehicle and the movement trajectory of the target may be predicted, and if the two trajectories intersect and the time to reach the intersection is close, it may be determined that the host vehicle and the target may potentially collide.
Degree of collision risk ρ of targetcolThe information may be obtained from vehicle speed information, acceleration information, yaw rate information, position information of the target relative to the vehicle, relative speed information, relative acceleration information, and the like. Where the degree of risk of collision of the target satisfies 0. ltoreq. rhocol≤1。
In one embodiment, the step of calculating the self-vulnerability in S30 includes the steps of:
acquiring classification information, appearance information and size information of a target;
and calculating the self fragility according to the classification information, the appearance information and the size information.
According to the classification, appearance, volume and the like of the target, whether the target is fragile or not and whether additional protection is needed or not can be judged. For example, most non-motorized vehicles (pedestrians, bicycles, donkeys, etc.) are objects that require additional protection, as are some motorized vehicles (motorcycles, tricycles, mini-cars, etc.). The target importance degree which needs high additional protection degree is high according to different target types (children and old people need the highest protection degree, and adults need the low protection degree because the mobility, judgment and reaction speed of the children and the old people are weaker than those of the adults); the less protective the target is, the more fragile it is (the more exposed, thinner and less bulky the driver of the motor vehicle, the more fragile it is and the more vulnerable it is in a traffic accident).
Target's own vulnerability ρfrgMay be obtained by classification information, appearance information, size information, etc. of the object. Where the degree of self-weakness of the target satisfies 0 ≦ ρfrg≤1。
In one embodiment, the calculating of significant threat in S30 includes the steps of:
acquiring classification information, appearance information, size information and plug-in information of a target;
and calculating the significant threat degree according to the classification information, the appearance information, the size information and the plug-in information.
Based on the classification of the targets, it can be determined whether the targets are traffic participants that may pose a significant threat. For example, large vehicles (trucks, vans, buses, construction vehicles, etc.) are participants in traffic that can pose a significant threat. This is because these vehicles are bulky and heavy, have a limited viewing angle for drivers, may have objects such as protruding metal hung on the outside of the vehicle, and may cause great injury in case of collision with pedestrians, small vehicles, and the like.
Significant threat of the target ρthtThe external hanging information can be obtained through classification information, appearance information, size information, external hanging information and the like of the target. Where the significant threat level of the target satisfies 0 ≦ ρtht≤1。
In one embodiment, the calculating of the additional interestingness in S30 includes the steps of:
receiving a target list which needs extra attention and is sent by a third-party interest correlator;
additional interestingness is calculated from the target list.
Through wireless communication, vehicles may receive in real-time a list of targets that third-party stakeholders (e.g., other vehicles, infrastructure, traffic control, public safety, etc.) transmit to gain additional attention. For example, a traffic control department finds that the speed of an overspeed vehicle greatly exceeds the speed limit, and meanwhile, a monitoring system of a traffic police department and the vehicle cannot track the overspeed vehicle in time, so that the characteristics of the overspeed vehicle can be issued to the vehicle and roadbed facilities in the system through wireless communication of a vehicle-road cooperative system, and the overspeed vehicle can be detected by other traffic participants. Meanwhile, the system can also be used for tracking lost people, criminals and the like.
Additional interest level ρ of the objectintThe target can be calculated according to the characteristics of the target (such as appearance, size, identification, speed, license plate and the like), the attention level of a third party, the reward level and the like. Where the additional interest level of the target satisfies 0 ≦ ρint≤1。
In another embodiment, S30 includes:
weighting the behavior abnormality degree, the behavior reckless degree, the collision risk degree, the self fragility degree, the significant threat degree and the additional interest degree of the target and taking the maximum value as the overall importance degree of the target.
According to the subdivision measurement of the target, the overall importance rho of the target is calculated and obtained by the following methodimpThe calculation formula is as follows:
ρimp＝max(ρcol，ρint，(αabn·ρabn+αagg·ρagg+αfrg·ρfrg)) (2)
in one embodiment, the weighting factors for the risk of collision and the additional interestingness are both greater than the weighting factors for the behavioral abnormality, the behavioral reckless measure, the self-vulnerability or the significant threat. Namely, the collision risk and the extra interestingness are taken as the most important factors, and the behavior abnormality, the behavior reckless degree, the self vulnerability and the important threat are taken as relatively important factors.
The logic of calculation of the weighted importance here lies in the collision risk ρ of the targetcolMost importantly, if the vehicle collides with an object to generate a serious safety accident, the object is the most important object, the vehicle needs to pay attention and make corresponding control actions of braking, accelerating, steering and the like to avoid the collision. Additional interest level ρ of the objectintIt is also important that these additional objects of interest are potentially important for both traffic safety and public safety, where the vehicle is focused on to coordinate with law enforcement or related agencies. Degree of abnormality ρ of targetabnLushikimic degree rhoaggDegree of fragility ρfrgEqual relative importance, where the average importance is obtained by weighting, where the weight 0 ≦ αabn≥1，0≤αagg≤1,0≤αfrgAlpha is less than or equal to 1abn+αagg+αfrg1. And finally, acquiring the overall importance of the target which is the most important one of the several importance degrees by taking the maximum value.
After the area of the target of interest is determined, the importance of the target can be further judged according to the characteristics, behaviors and tracks of the target.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.
Claims (7)
1. An important target generation method for a vehicle-road cooperative automatic driving system is characterized by comprising the following steps:
acquiring related information of a plurality of targets around the vehicle;
sequentially calculating behavior characteristic information and attribute characteristic information of each target according to the related information;
calculating the overall importance of the target according to the behavior characteristic information and the attribute characteristic information;
arranging the targets with the overall importance degrees larger than a first threshold value in a descending order according to the overall importance degrees to form a list to be selected;
sequentially selecting the targets with the number not more than a preset number from the top item to the back item in the list to be selected so as to form an important target list;
the behavior feature information includes: the behavior abnormality degree, the behavior reckless degree and the collision risk degree of the target, and the attribute characteristic information comprises: the target self-vulnerability, the significant threat degree and the additional interest degree of the target are obtained through calculation of the characteristics of the target, the attention level of a third party or the appreciation level;
calculating the overall importance of the target according to the behavior characteristic information and the attribute characteristic information, wherein the calculation comprises the following steps:
weighting and taking the maximum of the behavioral abnormality degree, the behavioral reckless degree, the collision risk degree, the self-vulnerability degree, the significant threat degree and the additional interest degree of the target as the overall importance degree of the target.
2. The important objective generation method according to claim 1, wherein weighting and taking a maximum value of the degree of behavioral abnormality, the degree of behavioral reckless, the degree of collision risk, the degree of self-vulnerability, the degree of significant threat, and the degree of additional interest of the objective as the overall importance of the objective comprises:
the weighting coefficients of the collision risk degree and the additional interestingness degree are both larger than the weighting coefficients of the behavior abnormality degree, the behavior reckless degree, the self-vulnerability degree or the significant threat degree.
3. The method according to claim 1 or 2, wherein the step of sequentially calculating behavior feature information and attribute feature information of each target according to the related information comprises:
acquiring traffic rule information of the current position of the target;
acquiring the current traffic behavior information of the target;
and calculating the behavior abnormality degree according to the traffic rule information and the traffic behavior information.
4. The method according to claim 1 or 2, wherein the step of sequentially calculating behavior feature information and attribute feature information of each target according to the related information comprises:
acquiring the change rate information of the motion information of the target;
and calculating the action reckimic degree according to the movement information change rate information.
5. The method according to claim 1 or 2, wherein the step of sequentially calculating behavior feature information and attribute feature information of each target according to the related information comprises:
calculating a risk value of collision of the target with the vehicle;
and calculating the collision risk degree according to the risk value.
6. The method according to claim 1 or 2, wherein the step of sequentially calculating behavior feature information and attribute feature information of each target according to the related information comprises:
acquiring classification information, appearance information and size information of the target;
and calculating the self-fragility according to the classification information, the appearance information and the size information.
7. The method according to claim 1 or 2, wherein the step of sequentially calculating behavior feature information and attribute feature information of each target according to the related information comprises:
acquiring classification information, appearance information, size information and plug-in information of the target;
and calculating the significant threat degree according to the classification information, the appearance information, the size information and the plug-in information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745048.8A CN110349425B (en) | 2019-08-13 | 2019-08-13 | Important target generation method for vehicle-road cooperative automatic driving system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745048.8A CN110349425B (en) | 2019-08-13 | 2019-08-13 | Important target generation method for vehicle-road cooperative automatic driving system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110349425A CN110349425A (en) | 2019-10-18 |
| CN110349425B true CN110349425B (en) | 2020-11-13 |
Family
ID=68184902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910745048.8A Active CN110349425B (en) | 2019-08-13 | 2019-08-13 | Important target generation method for vehicle-road cooperative automatic driving system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110349425B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111599216A (en) * | 2020-05-18 | 2020-08-28 | 合肥杰代机电科技有限公司 | Auxiliary driving method, device and system based on image recognition and UWB (ultra-wideband) tag |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9058247B2 (en) * | 2010-09-08 | 2015-06-16 | Toyota Jidosha Kabushiki Kaisha | Risk potential calculation apparatus |
| CN104773177A (en) * | 2014-01-09 | 2015-07-15 | 株式会社理光 | Aided driving method and aided driving device |
| JP2016148971A (en) * | 2015-02-12 | 2016-08-18 | トヨタ自動車株式会社 | Operation support device |
| JP6776513B2 (en) * | 2015-08-19 | 2020-10-28 | ソニー株式会社 | Vehicle control device, vehicle control method, information processing device, and traffic information provision system |
| WO2018088224A1 (en) * | 2016-11-09 | 2018-05-17 | ソニー株式会社 | Information processing device, information processing method, program, and moving body |
| JP2018097590A (en) * | 2016-12-13 | 2018-06-21 | アイシン・エィ・ダブリュ株式会社 | Obstacle determination system and obstacle determination program |
| CN107316500B (en) * | 2017-06-06 | 2020-11-20 | 驭势（上海）汽车科技有限公司 | Threat degree calculation method in automatic driving, target selection method and application |
| CN108583571A (en) * | 2018-04-28 | 2018-09-28 | 深圳市商汤科技有限公司 | Collision control method and device, electronic equipment and storage medium |
-
2019
- 2019-08-13 CN CN201910745048.8A patent/CN110349425B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110349425A (en) | 2019-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11945448B2 (en) | Vehicle telematics based driving assessment | |
| CN113165652B (en) | Verifying predicted trajectories using a mesh-based approach | |
| JP7499256B2 (en) | System and method for classifying driver behavior - Patents.com | |
| CN109416873B (en) | Autonomous or partially autonomous motor vehicle with automated risk control system and corresponding method | |
| CN114375467B (en) | System and method for detecting an emergency vehicle | |
| CN109472975A (en) | Driving assist system, drive supporting device and driving support method | |
| JP2019535566A (en) | Unexpected impulse change collision detector | |
| US20150019447A1 (en) | Reverse event signature for identifying hit and run vehicles | |
| KR102210140B1 (en) | Use of map information to smooth objects generated from sensor data | |
| US11731661B2 (en) | Systems and methods for imminent collision avoidance | |
| KR20200066747A (en) | Early object detection for unprotected rotation | |
| US11104356B2 (en) | Display device and method for a vehicle | |
| Alluhaibi et al. | Driver behavior detection techniques: A survey | |
| US10977882B1 (en) | Driver health profile | |
| JP2023093660A (en) | Control device, control method, and program for control device | |
| US20220114815A1 (en) | Moving body collision avoidance device, collision avoidance method and electronic device | |
| US20220161849A1 (en) | Vehicle control device, vehicle control method, and non-transitory computer-readable recording medium recording program | |
| CN110349425B (en) | Important target generation method for vehicle-road cooperative automatic driving system | |
| US11628862B2 (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN114834477A (en) | Malicious event detection for autonomous vehicles | |
| Jyothi et al. | Driver assistance for safe navigation under unstructured traffic environment | |
| Balasubramani et al. | A predictive decision model for an efficient detection of abnormal driver behavior in intelligent transport system | |
| Tsai et al. | A safety driving assistance system by integrating in-vehicle dynamics and real-time traffic information | |
| Uchiyama et al. | Risky Traffic Situation Detection and Classification Using Smartphones | |
| CN114187764B (en) | Method for rapidly detecting collision risk degree aiming at VRU (virtual Router Unit) passing scene |
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 |