CN111968397B - Automatic driving behavior determination method - Google Patents
Automatic driving behavior determination method Download PDFInfo
- Publication number
- CN111968397B CN111968397B CN202010763555.7A CN202010763555A CN111968397B CN 111968397 B CN111968397 B CN 111968397B CN 202010763555 A CN202010763555 A CN 202010763555A CN 111968397 B CN111968397 B CN 111968397B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- current
- driving behavior
- lane
- information
- 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 26
- 230000006399 behavior Effects 0.000 claims abstract description 157
- 230000009191 jumping Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 5
- 230000008859 change Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to an automatic driving behavior determination method, comprising the steps of: acquiring an original information set; extracting a current scene element set from an original information set; comparing the extracted current scene element set with the sub scene element sets one by one, and if the extracted current scene element set and the sub scene element sets are not completely the same, keeping the current driving behavior unchanged; otherwise, judging the driving behavior at the next moment by adopting the completely same sub-scene element set; matching the sub-scene element set with the driving behavior at the next moment according to the matching rule, and if the sub-scene element set is not completely matched with the driving behavior at the next moment, keeping the current driving behavior unchanged; otherwise, outputting all the driving behaviors which are completely matched at the next moment; and evaluating the driving behavior at the next moment to obtain the best, and finally outputting the optimal driving behavior at the next moment. The invention does not need a large amount of complex logic operation, and the operation quantity requirement is extremely low; a large number of scenes, matching rules and driving behaviors can be preset, all conditions encountered in the automatic driving process can be covered, and accurate reaction can be made.
Description
Technical Field
The invention relates to the technical field of intelligent vehicles, in particular to an automatic driving behavior judgment method.
Background
For automatic driving behavior judgment, the road traffic danger situation around the vehicle needs to be accurately judged according to the current road environment perception information and the motion state of the vehicle, and meanwhile, timely and accurate judgment needs to be made among different driving behavior modes according to an automatic driving task target and a safe driving behavior criterion.
The most mainstream prior art in the technical field of the current intelligent vehicle is automatic driving behavior judgment realized based on a finite-state machine method; specifically, a logic relation and a state switching process among all driving behaviors are established based on a finite state machine method, then a driving scene where the automatic driving is located is judged according to the information after fusion processing, the driving scene is sent to a driving behavior decision module, and then the driving behavior decision module decides the driving behavior which accords with the traffic rule in real time according to the driving scene.
The prior art has the following disadvantages:
1. the core of the finite-state machine method lies in establishing a logical relationship and a state switching process among driving behaviors, namely, the switching of the driving behaviors is generated by state transition caused by an input basic trigger condition, and the state transition is realized by a large amount of digital logic operations and requires real-time operation, so that high operational capability is required; however, the operation capability of the vehicle-mounted computer is greatly compromised in order to ensure safe and stable operation, so that the operation capability requirement of the finite-state machine method cannot be completely met in practice, and the automatic driving judgment technology based on the finite-state machine method has a great distance from practical application;
2. a few existing technologies based on finite state machine methods reduce the computation demand by simplifying basic trigger conditions, for example, some existing technologies only judge whether a vehicle runs in an adjacent lane, but do so resulting in few basic trigger conditions, so that basic safety cannot be guaranteed, and the vehicle still cannot get on the road actually;
3. in the prior art based on the finite-state machine method, the computation demand is reduced by simplifying the scene, so that the information of the retrieval scene is incomplete, and the vehicle still cannot actually run on the road.
Disclosure of Invention
The invention aims at the problems and provides an automatic driving behavior judging method, which avoids the inherent requirement of a finite-state machine method on high computation amount by adopting the preset scene to search and match the preset driving behavior, and achieves the purposes of greatly reducing the computation amount requirement on one hand and greatly enriching the scene and the driving behavior on the other hand.
In order to solve the problems, the technical scheme provided by the invention is as follows:
an automatic driving behavior determination method comprising the steps of:
s100, acquiring an original information set; the original information set comprises original information which changes along with the running of the vehicle;
s200, extracting a current scene element set for describing a current scene from the original information set; the current scene element set comprises current lane obstacle information and adjacent lane obstacle information;
s300, comparing the extracted current scene element set with each pre-stored scene element set in the scene set one by one, and performing the following operations according to the comparison result:
if the sub scene element set which is completely the same as the current scene element set does not exist, prompting that the scene is unknown and keeping the current driving behavior unchanged;
otherwise, judging the driving behavior at the next moment by adopting the completely same pre-stored sub scene element set;
s400, matching the sub-scene element set with each next-moment driving behavior stored in a behavior set according to a matching rule prestored in a rule set, wherein each next-moment driving behavior comprises a priority value; then according to the matching result, the following operations are carried out:
if the driving behavior at the next moment completely matched with the sub scene element set does not exist, prompting that the scene is unknown and keeping the current driving behavior unchanged;
otherwise, outputting all the driving behaviors which are completely matched at the next moment;
s500, evaluating and optimizing all the completely matched driving behaviors at the next moment, and finally outputting the optimal driving behavior at the next moment.
Preferably, the current lane obstacle information and the adjacent lane obstacle information are read from the driving situation map in the original information set.
Preferably, the current scene element set comprises map information, road information, navigation information, positioning information, traffic information, vehicle information, driver operation information and system fault type information;
the road information is read from the driving situation map in the original information set;
the driver operation information and the system fault type information are acquired from system services by the scene information acquisition module;
the own vehicle information comprises the actual behavior of the current vehicle.
Preferably, the current lane obstacle information includes a current lane obstacle time interval, a current lane obstacle relative speed, a current lane obstacle type, a current lane obstacle size and a current lane obstacle collision time;
the adjacent lane obstacle information comprises the time distance of the adjacent lane obstacle, the relative speed of the adjacent lane obstacle, the type of the adjacent lane obstacle, the size of the adjacent lane obstacle and the collision time of the adjacent lane obstacle.
Preferably, the matching rule comprises:
if the actual behavior of the current vehicle is cruising, the information of the current lane obstacle is no obstacle, or the time distance of the current lane obstacle is not lower than a manually preset large time distance threshold, or the time distance of the current lane obstacle is not higher than a manually preset small time distance threshold, and the collision time of the current lane obstacle is higher than a manually preset large collision time threshold, determining that the driving behavior at the next moment is cruising;
if the actual behavior of the current vehicle is cruising, the time distance of the obstacle of the current lane is not higher than the small time distance threshold value, and the type of the obstacle of the current lane is a vehicle, judging that the driving behavior at the next moment is car following;
if the actual behavior of the current vehicle is car following, the time distance of the current lane obstacle is not higher than the small time distance threshold, the type of the current lane obstacle is a vehicle, and the relative speed of the current lane obstacle is lower than a manually preset safe speed threshold, judging that the driving behavior at the next moment is car following;
if the actual behavior of the current vehicle is following, the obstacle information of the current lane is no obstacle, or the obstacle time distance of the current lane is not lower than the large time distance threshold, or the obstacle time distance of the current lane is not higher than the small time distance threshold, and the collision time of the obstacle of the current lane is higher than the large collision time threshold, the driving behavior of the next moment is cruising;
if the actual behavior of the current vehicle is following, the time distance of the obstacle in the current lane is not higher than the small time distance threshold, the relative speed of the obstacle in the current lane is higher than the safe speed threshold, and the obstacle information of the adjacent lane is that no obstacle exists in the left lane or the time distance of the obstacle in the adjacent lane is not lower than the large time distance threshold, determining that the driving behavior at the next moment is left lane changing;
if the actual behavior of the current vehicle is following, the time distance of the obstacle in the current lane is not higher than the small time distance threshold, the relative speed of the obstacle in the current lane is higher than the safe speed threshold, and the obstacle information of the adjacent lane is that no obstacle exists in the right lane or the time distance of the obstacle in the adjacent lane is not lower than the large time distance threshold, the driving behavior at the next moment is judged to be right lane changing;
and if the actual behavior of the current vehicle is emergency braking, judging that the driving behavior at the next moment is emergency braking.
Preferably, the evaluating the driving behavior at the next moment and optimizing the driving behavior at the next moment, and finally outputting the optimal driving behavior at the next moment comprises the following steps:
s510, arranging all the completely matched driving behaviors at the next moment from large to small according to the priority value of each driving behavior at the next moment;
s520, taking the next moment driving behavior with the maximum priority value as the optimal next moment driving behavior, and finally outputting the optimal next moment driving behavior.
Preferably, the method further comprises the steps of:
s210, fuzzy range division is carried out on the boundary between the current lane obstacle time interval and the current lane obstacle relative speed by adopting a fuzzy rule so as to avoid frequent jump of the boundary between the current lane obstacle time interval and the current lane obstacle relative speed;
s220, fuzzy range division is carried out on the boundary between the adjacent lane obstacle time interval and the adjacent lane obstacle relative speed by adopting the fuzzy rule, so that frequent jumping near the boundary between the adjacent lane obstacle time interval and the adjacent lane obstacle relative speed is avoided.
Compared with the prior art, the invention has the following advantages:
1. according to the invention, the current scene and the driving behavior are retrieved and matched, and a large amount of complex logic operation is not needed, so that the requirement on the operation amount is extremely low, and the current vehicle-mounted computer can completely function;
2. the invention can preset mass scenes, matching rules and driving behaviors, thereby covering all conditions encountered in the automatic driving process within a considered range and making accurate response.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention;
FIG. 2 is a diagram illustrating a gradual increase of time intervals in a fuzzy rule according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a determination system to which an embodiment of the present invention is applied.
Detailed Description
The present invention is further illustrated by the following examples, which are intended to be purely exemplary and are not intended to limit the scope of the invention, as various equivalent modifications of the invention will occur to those skilled in the art upon reading the present disclosure and fall within the scope of the appended claims.
As shown in fig. 1, the automatic driving behavior determination method includes the steps of:
s100, acquiring an original information set; the original information set includes original information that changes as the vehicle travels.
S200, extracting a current scene element set for describing a current scene from the original information set.
The current scene element set comprises current lane obstacle information and adjacent lane obstacle information; the current scene element set also contains map information, road information, navigation information, positioning information, traffic information, own vehicle information, driver operation information, and system fault type information.
The current lane obstacle information and the adjacent lane obstacle information are read from the driving situation map in the original information set.
The current lane obstacle information comprises a current lane obstacle time distance, a current lane obstacle relative speed, a current lane obstacle type, a current lane obstacle size and a current lane obstacle collision time.
The adjacent lane obstacle information comprises the time distance of the adjacent lane obstacle, the relative speed of the adjacent lane obstacle, the type of the adjacent lane obstacle, the size of the adjacent lane obstacle and the collision time of the adjacent lane obstacle.
The road information is also read from the driving situation map in the original information set.
The driver operation information and the system fault type information are acquired from the system service by the scene information acquisition module.
The own vehicle information contains the current actual vehicle behavior.
In an actual working condition, the information extracted from the current scene element set cannot be directly used and needs to be formatted; in addition, in order to avoid frequent jump of the time distance and the relative speed between the self-vehicle and the obstacle near the boundary value, and thus frequent jump of the output result, fuzzy rules need to be adopted for dividing the ranges of the time distance and the relative speed. This fuzzy rule essentially adds a delay interval of state change around the boundary value.
Specifically, a section for delaying the state change is added near the value of the boundary: when the time distance of the obstacle is small, if the time distance changes from small to large, the time distance is not immediately judged to be large, but is judged to be medium or large only if the time distance has a continuous change and increase trend; when the time distance of the obstacle is large, if the time distance of the obstacle changes from large to small and has a trend of continuously decreasing, the time distance is judged to be large, medium or small. As shown in fig. 2, the time intervals represented from left to right of the four time intervals are: small, medium, large.
S210, fuzzy range division is carried out on the boundary between the current lane obstacle time distance and the current lane obstacle relative speed by adopting a fuzzy rule so as to avoid frequent jumping of the boundary between the current lane obstacle time distance and the current lane obstacle relative speed.
S220, fuzzy range division is carried out on the boundary between the time distance of the obstacle of the adjacent lane and the relative speed of the obstacle of the adjacent lane by adopting a fuzzy rule so as to avoid frequent jumping near the boundary between the time distance of the obstacle of the adjacent lane and the relative speed of the obstacle of the adjacent lane.
S300, comparing the extracted current scene element set with each pre-stored scene element set in the scene set one by one, and performing the following operations according to the comparison result:
and if the sub scene element set which is completely the same as the current scene element set does not exist, prompting that the scene is unknown and keeping the current driving behavior unchanged.
Otherwise, judging the driving behavior at the next moment by adopting the completely same pre-stored sub-scene element set.
S400, matching the sub-scene element set with each next-moment driving behavior stored in the behavior set according to a matching rule pre-stored in the rule set, wherein each next-moment driving behavior comprises a priority value.
In this particular embodiment, the high priority value characterizes a high priority; the priority is from high to low: emergency avoidance, parking by side, cruising, car following, lane changing and obstacle avoidance.
Then according to the matching result, the following operations are carried out:
and if the driving behavior at the next moment is not completely consistent with the sub-scene element set, prompting that the scene is unknown and keeping the current driving behavior unchanged.
Otherwise, outputting all the driving behaviors which are completely matched at the next moment.
S500, evaluating and optimizing all completely-matched driving behaviors at the next moment, and finally outputting the optimal driving behavior at the next moment.
The matching rule includes:
and if the actual behavior of the current vehicle is cruising, the information of the current lane obstacle is no obstacle, or the time distance of the current lane obstacle is not lower than a manually preset large time distance threshold, or the time distance of the current lane obstacle is not higher than a manually preset small time distance threshold and the collision time of the current lane obstacle is higher than a manually preset large collision time threshold, judging that the driving behavior at the next moment is cruising.
And if the actual behavior of the current vehicle is cruising, the time distance of the obstacle in the current lane is not higher than the small distance threshold value, and the type of the obstacle in the current lane is the vehicle, judging that the driving behavior at the next moment is car following.
And if the actual behavior of the current vehicle is vehicle following, the time interval of the current lane obstacle is not higher than the small time interval threshold, the type of the current lane obstacle is the vehicle, and the relative speed of the current lane obstacle is lower than an artificially preset safe speed threshold, judging that the driving behavior at the next moment is vehicle following.
And if the actual behavior of the current vehicle is following, the information of the current lane obstacle is no obstacle, or the time distance of the current lane obstacle is not lower than the large time distance threshold value, or the time distance of the current lane obstacle is not higher than the small time distance threshold value and the collision time of the current lane obstacle is higher than the large collision time threshold value, judging that the driving behavior at the next moment is cruising.
And if the actual behavior of the current vehicle is following, the time interval of the obstacle of the current lane is not higher than the small time interval threshold value, the relative speed of the obstacle of the current lane is higher than the safe speed threshold value, and the obstacle information of the adjacent lane is that no obstacle exists in the left lane or the time interval of the obstacle of the adjacent lane is not lower than the large time interval threshold value, judging that the driving behavior at the next moment is left lane change.
And if the actual behavior of the current vehicle is following, the time interval of the obstacle of the current lane is not higher than the small time interval threshold value, the relative speed of the obstacle of the current lane is higher than the safe speed threshold value, and the obstacle information of the adjacent lane is that no obstacle exists in the right lane or the time interval of the obstacle of the adjacent lane is not lower than the large time interval threshold value, judging that the driving behavior at the next moment is right lane change.
And if the actual behavior of the current vehicle is emergency braking, judging that the driving behavior at the next moment is emergency braking.
The method for evaluating the driving behavior at the next moment to obtain the best and finally outputting the optimal driving behavior at the next moment comprises the following steps:
and S510, arranging all the completely matched driving behaviors at the next moment from large to small according to the priority value of each driving behavior at the next moment.
S520, the next moment driving behavior with the maximum priority value is taken as the optimal next moment driving behavior, and the optimal next moment driving behavior is output finally.
A structure of a determination system to which the automatic driving behavior determination method of the present embodiment is applied is shown in fig. 3, in which:
a scene information acquisition module: the system is used for acquiring an original information set, consists of various sensors and belongs to hardware equipment; and the original information set acquired by the scene information acquisition module is sent to the scene understanding module for receiving and processing.
A scene understanding module: a current scene element set used for describing a current scene is extracted from the original information set; the scene understanding module is positioned on the vehicle-mounted MCU, and the extracted current scene element set is supplied to the behavior judging and optimizing module for use.
The scene behavior rule module comprises a scene set, a behavior set and a rule set, and is essentially three databases: the scene set is used for storing a sub-scene element set, the behavior set is used for storing the driving behavior at the next moment matched with the sub-scene element set, and the rule set is used for storing a matching rule; each next-time driving behavior comprises a priority value; the sub-scene element set, the next-moment driving behavior and the matching rule are composed of manually preset data, the scene element set, the next-moment driving behavior and the matching rule can be input infinitely under the condition that the database capacity is running, and the more the input is, the more detailed the consideration is, the higher the intelligent degree of judgment of the automatic driving vehicle is; the form, attribute and format of the current scene element set and the sub-scene element set are completely consistent, so that the form, attribute and format can be the basis of accurate matching.
A behavior judgment and optimization module: and the driving behavior module is used for acquiring the driving behavior at the next moment from the scene behavior rule module according to the current scene element set, evaluating the driving behavior at the next moment, optimizing the driving behavior at the next moment, and finally outputting the optimal driving behavior at the next moment.
The behavior judging and optimizing module is the core of the system, and the working principle is as follows: firstly, comparing the extracted current scene element set with each sub-scene element set prestored in the scene set one by one; thus, a sub-scene element set which is completely consistent with the acquired current scene element set can be obtained, and the sub-scene element set is unique; and then matching the acquired sub-scene element set with each next-moment driving behavior stored in the behavior set according to a matching rule pre-stored in the rule set. The result of this matching is one-to-many, i.e. the same set of sub-scene elements is likely to correspond to a plurality of different driving behaviors at the next time; however, only one driving behavior at the next moment is determined by the decision, so that the driving behavior at the next moment needs to be evaluated and optimized; the evaluation optimization is to arrange the priority from high to low according to the priority value of the driving behavior at each next moment; the high priority value in the embodiment represents high priority; the priority is from high to low: emergency avoidance, parking by side, cruising, car following, lane changing and obstacle avoidance; therefore, the next-time driving behavior with the highest priority can be taken as the optimal next-time driving behavior.
The optimal driving behavior at the next moment obtained by the behavior judging and optimizing module is provided for the motion planning subsystem of the self-vehicle to use; and the motion planning subsystem sends an instruction to the control system to complete the implementation of the automatic driving behavior.
The running processes of the automatic driving behavior judging system and the motion planning subsystem are monitored by the state monitoring module in real time;
the motion planning subsystem, the control system, and the state monitoring module are parts of the interface between the autonomous vehicle and the autonomous driving behavior determination system to which the present embodiment is applied, and do not belong to the content of the present invention.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. To those skilled in the art; various modifications to these embodiments will be readily apparent, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (1)
1. An automatic driving behavior determination method characterized by: comprises the following steps:
s100, acquiring an original information set; the original information set comprises original information which changes along with the running of the vehicle;
s200, extracting a current scene element set for describing a current scene from the original information set; the current scene element set comprises current lane obstacle information and adjacent lane obstacle information;
s300, comparing the extracted current scene element set with each pre-stored scene element set in the scene set one by one, and performing the following operations according to the comparison result:
if the sub scene element set which is completely the same as the current scene element set does not exist, prompting that the scene is unknown and keeping the current driving behavior unchanged;
otherwise, judging the driving behavior at the next moment by adopting the completely same pre-stored sub scene element set;
s400, matching the sub-scene element set with each next-moment driving behavior stored in a behavior set according to a matching rule prestored in a rule set, wherein each next-moment driving behavior comprises a priority value; then according to the matching result, the following operations are carried out:
if the driving behavior at the next moment completely matched with the sub scene element set does not exist, prompting that the scene is unknown and keeping the current driving behavior unchanged;
otherwise, outputting all the driving behaviors which are completely matched at the next moment;
s500, evaluating and optimizing all the completely matched driving behaviors at the next moment, and finally outputting the optimal driving behavior at the next moment;
the current lane obstacle information and the adjacent lane obstacle information are read from the driving situation map in the original information set;
the current scene element set comprises map information, road information, navigation information, positioning information, traffic information, self-vehicle information, driver operation information and system fault type information;
the road information is read from the driving situation map in the original information set;
the driver operation information and the system fault type information are acquired from system services by the scene information acquisition module;
the self-vehicle information comprises the actual behavior of the current vehicle;
the current lane obstacle information comprises a current lane obstacle time distance, a current lane obstacle relative speed, a current lane obstacle type, a current lane obstacle size and a current lane obstacle collision time;
the adjacent lane obstacle information comprises adjacent lane obstacle time distance, adjacent lane obstacle relative speed, adjacent lane obstacle type, adjacent lane obstacle size and adjacent lane obstacle collision time;
the matching rule includes:
if the actual behavior of the current vehicle is cruising, the information of the current lane obstacle is no obstacle, or the time distance of the current lane obstacle is not lower than a manually preset large time distance threshold, or the time distance of the current lane obstacle is not higher than a manually preset small time distance threshold, and the collision time of the current lane obstacle is higher than a manually preset large collision time threshold, determining that the driving behavior at the next moment is cruising;
if the actual behavior of the current vehicle is cruising, the time distance of the obstacle of the current lane is not higher than the small time distance threshold value, and the type of the obstacle of the current lane is a vehicle, judging that the driving behavior at the next moment is car following;
if the actual behavior of the current vehicle is car following, the time distance of the current lane obstacle is not higher than the small time distance threshold, the type of the current lane obstacle is a vehicle, and the relative speed of the current lane obstacle is lower than a manually preset safe speed threshold, judging that the driving behavior at the next moment is car following;
if the actual behavior of the current vehicle is following, the obstacle information of the current lane is no obstacle, or the obstacle time distance of the current lane is not lower than the large time distance threshold, or the obstacle time distance of the current lane is not higher than the small time distance threshold, and the collision time of the obstacle of the current lane is higher than the large collision time threshold, the driving behavior of the next moment is cruising;
if the actual behavior of the current vehicle is following, the time distance of the obstacle in the current lane is not higher than the small time distance threshold, the relative speed of the obstacle in the current lane is higher than the safe speed threshold, and the obstacle information of the adjacent lane is that no obstacle exists in the left lane or the time distance of the obstacle in the adjacent lane is not lower than the large time distance threshold, determining that the driving behavior at the next moment is left lane changing;
if the actual behavior of the current vehicle is following, the time distance of the obstacle in the current lane is not higher than the small time distance threshold, the relative speed of the obstacle in the current lane is higher than the safe speed threshold, and the obstacle information of the adjacent lane is that no obstacle exists in the right lane or the time distance of the obstacle in the adjacent lane is not lower than the large time distance threshold, the driving behavior at the next moment is judged to be right lane changing;
if the actual behavior of the current vehicle is emergency braking, judging that the driving behavior at the next moment is emergency braking;
the step of evaluating the driving behavior at the next moment to obtain the best and finally outputting the optimal driving behavior at the next moment comprises the following steps:
s510, arranging all the completely matched driving behaviors at the next moment from large to small according to the priority value of each driving behavior at the next moment;
s520, taking the next moment driving behavior with the maximum priority value as the optimal next moment driving behavior, and finally outputting the optimal next moment driving behavior;
further comprising the steps of:
s210, fuzzy range division is carried out on the boundary between the current lane obstacle time interval and the current lane obstacle relative speed by adopting a fuzzy rule so as to avoid frequent jump of the boundary between the current lane obstacle time interval and the current lane obstacle relative speed;
s220, fuzzy range division is carried out on the boundary between the adjacent lane obstacle time interval and the adjacent lane obstacle relative speed by adopting the fuzzy rule, so that frequent jumping near the boundary between the adjacent lane obstacle time interval and the adjacent lane obstacle relative speed is avoided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010763555.7A CN111968397B (en) | 2020-07-31 | 2020-07-31 | Automatic driving behavior determination method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010763555.7A CN111968397B (en) | 2020-07-31 | 2020-07-31 | Automatic driving behavior determination method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111968397A CN111968397A (en) | 2020-11-20 |
| CN111968397B true CN111968397B (en) | 2022-03-18 |
Family
ID=73364182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010763555.7A Active CN111968397B (en) | 2020-07-31 | 2020-07-31 | Automatic driving behavior determination method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111968397B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114261389B (en) * | 2021-11-29 | 2023-05-12 | 东风商用车有限公司 | Driving track collision risk analysis method for automatic driving commercial vehicle |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106800023B (en) * | 2016-12-13 | 2019-05-10 | 智车优行科技（北京）有限公司 | Method, apparatus and vehicle for adaptive cruise control |
| CN109213134B (en) * | 2017-07-03 | 2020-04-28 | 百度在线网络技术（北京）有限公司 | Method and device for generating automatic driving strategy |
| CN108189835B (en) * | 2017-12-28 | 2020-04-21 | 清华大学苏州汽车研究院（吴江） | Automatic driving collision avoidance control method and system |
| CN109669461B (en) * | 2019-01-08 | 2020-07-28 | 南京航空航天大学 | Decision-making system for automatically driving vehicle under complex working condition and track planning method thereof |
| CN110263709B (en) * | 2019-06-19 | 2021-07-16 | 百度在线网络技术（北京）有限公司 | Driving decision mining method and device |
| CN110395255B (en) * | 2019-07-03 | 2020-08-07 | 重庆长安汽车股份有限公司 | Method and system for judging transverse motion state of adjacent lane vehicle and computer readable storage medium |
-
2020
- 2020-07-31 CN CN202010763555.7A patent/CN111968397B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111968397A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110488802B (en) | Decision-making method for dynamic behaviors of automatic driving vehicle in internet environment | |
| CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
| CN110570538B (en) | Method, device and equipment for managing black box data in intelligent driving automobile | |
| CN110843789B (en) | Vehicle lane change intention prediction method based on time sequence convolution network | |
| CN101193768A (en) | Adaptive speed controller with situation-dependent dynamic matching | |
| CN113370996B (en) | Automatic driving lane change following decision method and system and automatic driving vehicle | |
| CN111338360B (en) | Method and device for planning vehicle driving state | |
| CN111932884A (en) | Traffic jam recognition method and device, vehicle and storage medium | |
| CN111968397B (en) | Automatic driving behavior determination method | |
| JP2024532675A (en) | Intelligent driving judgment method, vehicle driving control method and device, and vehicle | |
| CN116861678A (en) | Automatic driving expected function safety triggering condition generation and system optimization evaluation method | |
| CN116443046A (en) | Assistance system with a leader determination module for an automatic vehicle in a merge trajectory | |
| CN117058867A (en) | Car meeting method and related device | |
| KR102359110B1 (en) | The vehicle | |
| RU2782521C1 (en) | Method and system for planning of transverse trajectory of automatic change of car lane, car, and data carrier | |
| US20230311879A1 (en) | Autonomous driving control apparatus and method thereof | |
| CN117842073B (en) | Target vehicle lane change intention recognition method and device and vehicle | |
| CN113581172B (en) | Method for identifying driving scene cut into by intelligent driving vehicle facing target vehicle | |
| CN116394973A (en) | Intelligent Agent track planning control method and system based on HDMap | |
| CN116729203A (en) | Self-adaptive electric vehicle battery thermal management control method based on big data and driving habit | |
| CN114658552A (en) | Intelligent start-stop system and method | |
| CN118447700A (en) | Traffic cooperative control driving method, device, equipment and medium | |
| CN116142187A (en) | Cruise control method and device for automatic driving vehicle, vehicle and medium | |
| KR20240071425A (en) | Vehicle speed control apparatus and method | |
| CN117935532A (en) | Vehicle green wave passing planning method and device, electronic equipment and storage medium |
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 |