CN113320545A - Intersection behavior prediction decision method based on line-control intelligent vehicle - Google Patents
Intersection behavior prediction decision method based on line-control intelligent vehicle Download PDFInfo
- Publication number
- CN113320545A CN113320545A CN202110746627.1A CN202110746627A CN113320545A CN 113320545 A CN113320545 A CN 113320545A CN 202110746627 A CN202110746627 A CN 202110746627A CN 113320545 A CN113320545 A CN 113320545A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driving
- intersection
- behavior
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000008859 change Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 2
- 230000006399 behavior Effects 0.000 abstract description 41
- 230000008569 process Effects 0.000 abstract description 4
- 238000011160 research Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012508 change request Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W10/00—Conjoint control of vehicle sub-units of different type or different function
- B60W10/04—Conjoint control of vehicle sub-units of different type or different function including control of propulsion units
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W10/00—Conjoint control of vehicle sub-units of different type or different function
- B60W10/18—Conjoint control of vehicle sub-units of different type or different function including control of braking systems
- B60W10/184—Conjoint control of vehicle sub-units of different type or different function including control of braking systems with wheel brakes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W10/00—Conjoint control of vehicle sub-units of different type or different function
- B60W10/20—Conjoint control of vehicle sub-units of different type or different function including control of steering systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
A pre-crossing behavior decision method based on a drive-by-wire intelligent vehicle is used for carrying out overall scene evaluation on surrounding roads, obstacles, traffic marks, traffic lights and global navigation information aiming at a pre-crossing scene with the most complex working condition, and establishing a behavior rule base to ensure the safety, the legality and the validity of unmanned driving behaviors. The method carries out hierarchical classification and ordered judgment on the pre-intersection scene decision factors with complex working conditions through a behavior decision method based on a hierarchical finite state machine and knowledge logical reasoning, reduces the possibility of information combination confusion, and effectively accelerates the judgment speed. The method considers the effectiveness of the whole driving process, takes the global navigation information as an important part in the judgment of the rule base, and organically combines the effectiveness, the safety and the legality, so that the decision of the whole behavior is more reasonable.
Description
Technical Field
The invention relates to the field of automatic driving control, in particular to a pre-crossing behavior decision method based on a drive-by-wire intelligent vehicle.
Background
The birth and development of automobiles have been over a hundred years of history so far, and the traffic mode constructed by the automobiles is one of the important signs of civilization in the modern society. With the rapid development of the automobile industry, various automobiles run on the road, and the increasingly serious road congestion and the frequent occurrence of traffic accidents follow the various automobiles. Both the driving comfort of the vehicle and the driving safety of the driver face serious challenges. In recent years, technologies such as electronic technology, information interaction, intelligent control and the like have been developed rapidly, and more advanced technologies and research concepts are applied to the field of automobiles. The intelligent automobile is a robot vehicle, is used as a carrier for advanced vehicle control, senses the information of the current driving environment through a vehicle-mounted information sensing system (millimeter wave radar, ultrasonic waves, laser radar and the like), models the environment, and controls an executing mechanism to respond to the change of the environment information and make a corresponding reaction based on the driving behavior of the intelligent automobile at the current moment, so that the intelligent automobile assists a driver in driving to a certain extent or completely replaces the driver to drive actively, the operation intensity of the driver is reduced, and further traffic accidents are reduced.
The driving behavior decision is a decision process which is started from a driver per se and comprises intersection of multiple disciplines such as psychology, cognition, statistics and the like, and the purpose of the driving behavior decision is to research 'how the driver actually makes the decision' and 'why the driver makes the decision'. However, in an actual driving environment, many factors affecting the decision of the intelligent vehicle behavior have influence on the accuracy and the reasonability of the vehicle behavior, including the variability of the outdoor environment, the inaccuracy of environmental detection, the constraint of traffic regulations, the unpredictability of pedestrians and other vehicle behaviors, and the bad weather such as rain, fog and the like. How to eliminate the influence of these factors to the greatest extent will be the research focus of the behavior decision module. Therefore, despite the many studies conducted by engineers, many problems still remain to be solved in the field of smart driving.
At the road pre-intersection, all possible logic rules to be executed by the unmanned vehicle are the most, and various environments and other factors which need to be sensed and judged are the most complex, so the behavior decision method at the pre-intersection is always a difficult problem which needs to be solved emphatically in the unmanned research.
Disclosure of Invention
The invention provides a behavior decision method based on a line-control intelligent vehicle and a layered finite state machine aiming at a pre-intersection scene with the most complex working condition, which is used for carrying out overall scene evaluation on surrounding roads, obstacles, traffic signs, traffic lights and global navigation information, establishing a behavior rule base and ensuring the safety, the legality and the effectiveness of unmanned driving behaviors.
A pre-intersection behavior decision method based on a drive-by-wire intelligent vehicle comprises the following steps:
step 2, the vehicle judges the position of the current vehicle through global navigation information, the vehicle-mounted camera detects a lane stop line, judges the distance between the vehicle and the stop line, identifies the current driving scene, and enters a pre-intersection decision mode when the current driving scene is judged to be a pre-intersection scene;
step 3, after entering a pre-intersection scene decision mode, reading surrounding environment information and vehicle self information according to given system input through a vehicle-mounted sensor and a prior database, and processing input original information according to requirements to complete definition of system input;
step 4, carrying out hierarchical classification matching on the system input, calling a rule base in stages, and outputting a corresponding driving behavior mode according to a rule table;
step 5, planning a specific driving path according to the currently executed driving mode, and controlling a chassis driving, steering and braking component of the vehicle by the motion controller for the drive-by-wire control vehicle to generate transverse and longitudinal motion output;
and 6, detecting the surrounding scene and the vehicle pose information in real time, refreshing the system input, and matching the corresponding driving behavior mode.
Further, in step 1, the driving scene of the urban area is divided into three normal driving scenes, namely, a road, a pre-crossing and a crossing.
Further, a road within 50 meters of the stop line in the driving scene of the urban area is set as a pre-intersection.
Further, in step 3, the vehicle-mounted sensor comprises a GPS/INS, a millimeter wave radar, a vehicle-mounted camera, a laser radar and a wheel speed sensor.
Further, in step 3, the given system input includes the relative distance between the vehicle and the obstacle in eight directions, i.e., front-back, left-front, left-back, front-front, right-back, front-back, left-back, front-front, left-back, front-back, right-back, and the vehicle, the speed of the vehicle, the lane information and the information of the left and right lane lines where the vehicle is located, the speed limit sign of the road, the distance between the stop line of the intersection and the vehicle, the traffic light information, and the global navigation information.
Further, in step 4, the output driving behavior modes include straight driving and lane changing, wherein the straight driving includes three modes of lane keeping, following mode and braking and collision avoidance.
Further, in step 4, the rule base classifies and sorts all input conditions by a method of a hierarchical finite state machine, the rule table in the rule base comprises a table 1 and a table 2, firstly, the judgment is carried out according to the table 1, and when the input in the table 1 meets a straight-going condition, the judgment is carried out in the table 2.
Further, in table 1, a behavior pattern including a straight line, a left lane change, or a right lane change is output through scene recognition, demand determination, security evaluation, and feasibility determination.
Further, in table 2, behavior patterns including lane keeping, deceleration braking, acceleration following, constant speed following, deceleration following, and emergency braking are output through scene recognition, obstacle recognition, safety evaluation, traffic light recognition, speed limit determination, and relative speed.
The invention has the beneficial effects that:
(1) according to the method, the pre-intersection scene decision factors with complex working conditions are judged in a layered, classified and ordered manner through the behavior decision method based on the layered finite state machine, so that the possibility of information combination disorder is reduced, and the judgment speed is effectively accelerated.
(2) The invention considers the effectiveness of the whole driving process, takes the global navigation information as an important ring in the judgment of the rule base, and organically combines the effectiveness, the safety and the legality, so that the decision of the whole behavior is more reasonable.
Drawings
Fig. 1 is a schematic flow chart of a pre-intersection behavior decision method in an embodiment of the present invention.
FIG. 2 is a diagram illustrating processing logic in a rule base according to an embodiment of the present invention.
Fig. 3 is a table 1 of decision-making rules for driving behavior pattern output in the embodiment of the present invention.
Fig. 4 is a table 2 of decision-making rules for driving behavior pattern output in the embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the drawings in the specification.
The invention aims to solve the problem of a behavior decision method of an unmanned vehicle based on drive-by-wire control when the unmanned vehicle runs to a road pre-crossing. At the road pre-intersection, all possible logic rules to be executed by the unmanned vehicle are the most, and various environments and other factors which need to be sensed and judged are the most complex, so the behavior decision method at the pre-intersection is always a difficult problem which needs to be solved emphatically in the unmanned research. The method comprises the steps of carrying out overall scene evaluation on surrounding roads, obstacles, traffic signs, traffic lights and global navigation information, establishing a behavior rule base, and ensuring the safety, the legality and the effectiveness of unmanned driving behaviors.
And setting the road distance within 50 meters from the stop line as a pre-crossing.
Referring to fig. 1, the method flow is as follows:
And 2, judging the position of the current vehicle by the vehicle through the global navigation information and judging the distance between the vehicle and the stop line by detecting the lane stop line by the vehicle-mounted camera to identify the current driving scene, and entering a pre-intersection decision mode when the pre-intersection scene is judged to be true.
And 3, after entering a pre-intersection scene decision mode, reading surrounding environment information and vehicle information according to given system input through a vehicle-mounted sensor (GPS/INS, a millimeter wave radar, a vehicle-mounted camera, a laser radar and a wheel speed sensor) and a priori database, and processing input original information according to requirements to complete definition of system input.
And 4, carrying out hierarchical classification matching on the system input, calling the rule base 1 and the rule base 2 respectively in stages, and outputting corresponding driving behavior modes according to the rule table 1 and the rule table 2.
And 5, planning a specific driving path according to the currently executed driving mode, wherein the vehicle is a drive-by-wire control vehicle, and the motion controller controls a chassis driving part, a steering part and a braking part of the vehicle to generate transverse motion and longitudinal motion output.
And 6, detecting the surrounding scene and the vehicle pose information in real time, refreshing the system input, and matching the corresponding driving behavior mode.
The system input judgment factors comprise: the relative distance between the vehicle (or the obstacle) and the vehicle in eight directions, namely front, back, left front, left back, right front and back; the speed of eight azimuth vehicles (or obstacles) in front, back, left front, left back, right front, right back; the running speed of the vehicle; the lane information and the left and right lane line information (whether left and right lanes and lane lines are virtual or real) of the vehicle; a road speed limit sign; distance between the intersection stop line and the vehicle; traffic light information; global navigation information.
The driving modes output by the system include: and (3) straight going: (1) lane keeping, (2) following mode, (3) braking and collision avoidance; and (6) changing the channel.
The processing logic in the rule base is shown in fig. 2. Due to the fact that system input judgment conditions are complex, the number of factors needing to be judged is large, excessive condition input judgment processes are long, condition coupling and information combination confusion are prone to being caused, and therefore scene evaluation is conducted on the pre-intersection driving scene in a layering and grading mode from the three aspects of effectiveness, safety and legality. When the current vehicle is judged to drive into the scene of the pre-crossing, firstly, the effective driving of the vehicle is ensured, namely, the global navigation information is checked, whether the current crossing has a lane change requirement or not is judged, if the current crossing has the lane change requirement, preparation is carried out for the lane change, and if the current crossing does not have the lane change requirement, the vehicle keeps going straight. In the lane change preparation stage, lane change feasibility needs to be evaluated, safety and legality are judged respectively, whether vehicles or obstacles exist in a target lane or not is considered, and adjacent lane lines are solid lines or dotted lines. If the lane line between the lane to be changed is real or collision possibility exists after lane change, the current lane change request is rejected, and the vehicle keeps going straight. And in the straight-driving mode, selectively switching among a lane keeping mode, a following mode ACC and a braking and collision avoiding mode according to the stop line position information, the traffic light information and the obstacle information.
Table 1 and table 2 of the generation behavior decision rule are shown in fig. 3 and fig. 4. The invention adopts a method of a layered finite state machine to sort all input conditions, and in a rule base, firstly, the input conditions are judged according to the table 1, and when the input conditions in the table 1 meet the straight-going conditions, the input conditions enter the table 2 for judgment. The hierarchical judgment method can effectively reduce the condition input quantity, prevent the information combination explosion caused by the complexity of the matching rules due to excessive input conditions, and remarkably accelerate the logic judgment speed of the rule base. The specific entries in the table are defined in detail below.
1. Pre-intersection determination A: defining a distance D from the stop line, wherein when D is less than or equal to 50m, A is 1; when D is more than 50m, A is 0.
2. Navigation information B: left turn requirement, B ═ 00; the requirement of right turn, B is 01; the straight-moving requirement is that B is 10; and B equals 11 when the destination is reached.
3. The current lane C: sequentially sequencing from left to right, wherein C is 00; two lanes, C ═ 01; three lanes, C ═ 10; four lanes, C ═ 11.
4. Lane line false and true D: solid line D is 1; the dotted line D is 0.
5. Traffic light information E: red, yellow and green lights flash for reading second, and E is 1; green light, E ═ 0.
6. And (4) speed limit judgment F: defining the current road speed limit V0And the current vehicle speed V, when V<V0When F is 0; v>V0When F is 1.
7. Safety evaluation G: TTC and TIV were introduced here for security assessment for each zone. The time to collision TTC is the time from the start of collision to the occurrence of collision, and a smaller TTC indicates that the two vehicles are more likely to collide. The TIV is a supplement to the TTC to prevent the danger caused by sudden braking of the front vehicle under the conditions of approaching vehicle distance and the same vehicle speed.
Wherein DiIs the relative distance between the following vehicle and the followed vehicle i, V is the speed of the following vehicle, ViIs the speed of the followed vehicle.
Giving a safety threshold TTCtAnd TIVtAnd when the calculated collision time t is greater than the safety threshold value, the current vehicle running is safe, and otherwise, the current vehicle running is dangerous. 0 indicates current zone safety and 1 indicates current zone danger.
The TTC evaluation formula is as follows:
the TIV evaluation formula is as follows:
the safety evaluation formula of a certain area is as follows:
the position represents the azimuth, and the eight azimuths are front (F), back (B), left (L), right (R), Left Front (LF), Left Back (LB), Right Front (RF) and Right Back (RB) in sequence.
7.1 evaluation of safety of Current Lane G1：
I.e. when the current lane is safe, G 10; when the current lane is dangerous, G1＝1。
7.2 left lane safety assessment G2：
Since the left lane is divided into three parts, when a vehicle is present right to the left, it is directly determined as dangerous, and the output is 1.
I.e. the left lane is safe, G 20; when the left lane is dangerous, G2＝1。
7.3 Right Lane safety assessment G3：
The same principle is that:
i.e. the right lane is safe, G 30; in danger on the right lane, G3＝1。
8. Front obstacle determination H: when a vehicle or an obstacle exists ahead, H is 1; when there is no vehicle or obstacle ahead, H is 0.
9. Relative speed to preceding vehicle I: defining the current vehicle speed V and the front vehicle speed ViWhen V is<0.9ViWhen I is 00; when (0.9V)i≤V≤1.1Vi) When I is 01; when V is>1.1ViWhen I is 10. (no is also defined in Table 2, and it is not clear what state the expression for no specifies the relative speed of the vehicle ahead.) no means that this term need not be considered
Thus, the following decision rules can be derived in conjunction with the various definitions above and the rule tables of FIGS. 3-4:
in table 1, after it is first determined that the scene is a pre-intersection, that is, the distance from the stop line is greater than 50m, when the navigation information is satisfied as a left-turn request, the current lane is safe and is in the two-lane, lane dotted line, and left lane safety, the behavior mode is a left lane change. And when the requirements that the navigation information is the right-turn requirement, the current lane is safe and is positioned in two lanes, the lane dotted line and the right lane safety are met, the behavior mode is left lane changing. In other cases, the straight line is performed.
In table 2, after it is determined that the scene is a pre-intersection, that is, the distance from the stop line is greater than 50m, when there is no vehicle or obstacle in the front and the current lane is safe, if the traffic light is green and the current vehicle speed is less than the road speed limit, the lane keeping action is performed, and if the red light, the yellow light, and the green light flash for a second or the current vehicle speed is greater than the road speed limit although the green light is read, the deceleration braking action is performed. When a vehicle or an obstacle exists in front, if the conditions that the current lane is safe, the traffic light is a green light and the current speed is less than the road speed limit are met, when the speed of the vehicle is less than 0.9 times the speed of the vehicle in front, the accelerating following behavior is carried out, when the speed of the vehicle is more than 1.1 times the speed of the vehicle in front, the decelerating following behavior is carried out, and under other traffic light conditions and speed limit conditions, the constant speed following behavior is carried out as long as the current speed is within the range of 0.9 times and 1.1 times the speed of the vehicle in front. (see Table 2 for whether it should be when V>1.1ViWhen I is 10, the current speed of the vehicle is too high, and should beAdopt speed reduction to follow and instead of following at the uniform velocity, please confirm) when the front and back face is reversed and there is vehicle or barrier in the front, judge the danger in the current lane at the same time, then directly carry on the emergency braking action.
The above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above embodiment, but equivalent modifications or changes made by those skilled in the art according to the present disclosure should be included in the scope of the present invention as set forth in the appended claims.
Claims (9)
1. A pre-intersection behavior decision method based on a drive-by-wire intelligent vehicle is characterized by comprising the following steps: the method comprises the following steps:
step 1, a vehicle enters an automatic driving mode, a layered finite state machine decision method is adopted to divide a driving scene into three top-level states of a country, an urban area and a high speed, and the current driving scene is judged;
step 2, the vehicle judges the position of the current vehicle through global navigation information, the vehicle-mounted camera detects a lane stop line, judges the distance between the vehicle and the stop line, identifies the current driving scene, and enters a pre-intersection decision mode when the current driving scene is judged to be a pre-intersection scene;
step 3, after entering a pre-intersection scene decision mode, reading surrounding environment information and vehicle self information according to given system input through a vehicle-mounted sensor and a prior database, and processing input original information according to requirements to complete definition of system input;
step 4, carrying out hierarchical classification matching on the system input, calling a rule base in stages, and outputting a corresponding driving behavior mode according to a rule table;
step 5, planning a specific driving path according to the currently executed driving mode, and controlling a chassis driving, steering and braking component of the vehicle by the motion controller for the drive-by-wire control vehicle to generate transverse and longitudinal motion output;
and 6, detecting the surrounding scene and the vehicle pose information in real time, refreshing the system input, and matching the corresponding driving behavior mode.
2. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 1, characterized in that: in the step 1, urban driving scenes are divided into three conventional driving scenes, namely, road, pre-crossing and crossing.
3. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 2, characterized in that: and setting the road distance within 50 meters from the stop line in the driving scene of the urban area as a pre-intersection.
4. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 1, characterized in that: in step 3, the vehicle-mounted sensor comprises a GPS/INS, a millimeter wave radar, a vehicle-mounted camera, a laser radar and a wheel speed sensor.
5. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 1, characterized in that: in step 3, the given system input includes the relative distance between the vehicle or the obstacle in eight directions, namely front-back, left-front, left-back, front-right, and back-right, the speed of the vehicle or the obstacle in eight directions, the driving speed of the vehicle, the lane information of the vehicle, the information of the left and right lane lines, the speed limit sign of the road, the distance between the stop line of the intersection and the vehicle, the traffic light information, and the global navigation information.
6. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 1, characterized in that: in the step 4, the output driving behavior modes comprise straight driving and lane changing, wherein the straight driving comprises lane keeping, following and braking and collision avoiding.
7. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 1, characterized in that: in step 4, the rule base classifies and sorts all input conditions by adopting a method of a layered finite state machine, the rule table in the rule base comprises a table 1 and a table 2, firstly, the judgment is carried out according to the table 1, and when the input in the table 1 meets a straight-going condition, the judgment is carried out in the table 2.
8. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 7, characterized in that: in table 1, a behavior pattern including straight, left lane change, or right lane change is output through scene recognition, demand determination, security evaluation, and feasibility determination.
9. The pre-intersection behavior decision method based on the drive-by-wire intelligent vehicle as claimed in claim 7, characterized in that: in table 2, behavior patterns including lane keeping, deceleration braking, acceleration following, constant speed following, deceleration following, and emergency braking are output through scene recognition, obstacle recognition, safety assessment, traffic light recognition, speed limit determination, and relative speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110746627.1A CN113320545A (en) | 2021-07-01 | 2021-07-01 | Intersection behavior prediction decision method based on line-control intelligent vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110746627.1A CN113320545A (en) | 2021-07-01 | 2021-07-01 | Intersection behavior prediction decision method based on line-control intelligent vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113320545A true CN113320545A (en) | 2021-08-31 |
Family
ID=77425422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110746627.1A Pending CN113320545A (en) | 2021-07-01 | 2021-07-01 | Intersection behavior prediction decision method based on line-control intelligent vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113320545A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114644016A (en) * | 2022-04-14 | 2022-06-21 | 中汽创智科技有限公司 | Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium |
| CN115082900A (en) * | 2022-07-19 | 2022-09-20 | 湖南大学无锡智能控制研究院 | Intelligent vehicle driving decision system and method in parking lot scene |
| CN115257807A (en) * | 2022-07-27 | 2022-11-01 | 武汉大学 | Urban on-road scene automatic driving decision-making method and equipment based on knowledge graph |
| CN115366888A (en) * | 2022-08-25 | 2022-11-22 | 武汉大学 | Crossing information system construction method and device for automatic driving navigation |
| TWI793894B (en) * | 2021-12-03 | 2023-02-21 | 荷蘭商荷蘭移動驅動器公司 | Driving assistance method based on hd map and vehicle intercommunication system |
| CN117238159A (en) * | 2023-08-04 | 2023-12-15 | 华南理工大学 | Urban road-oriented intelligent network vehicle-connected behavior decision method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170248959A1 (en) * | 2016-02-29 | 2017-08-31 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device and vehicle control method |
| CN107272687A (en) * | 2017-06-29 | 2017-10-20 | 深圳市海梁科技有限公司 | A kind of driving behavior decision system of automatic Pilot public transit vehicle |
| CN108225364A (en) * | 2018-01-04 | 2018-06-29 | 吉林大学 | A kind of pilotless automobile driving task decision system and method |
| CN110562258A (en) * | 2019-09-30 | 2019-12-13 | 驭势科技（北京）有限公司 | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium |
| CN110667578A (en) * | 2018-12-29 | 2020-01-10 | 长城汽车股份有限公司 | Lateral decision making system and lateral decision making determination method for automatic driving vehicle |
| CN110979327A (en) * | 2019-03-18 | 2020-04-10 | 长城汽车股份有限公司 | Longitudinal control method and system for automatic driving vehicle |
| CN111103882A (en) * | 2019-12-30 | 2020-05-05 | 合肥一辂汽车科技有限公司 | Autonomous following control method for unmanned electric vehicle |
| CN111383474A (en) * | 2018-12-29 | 2020-07-07 | 长城汽车股份有限公司 | Decision making system and method for automatically driving vehicle |
| CN111645691A (en) * | 2020-04-29 | 2020-09-11 | 云南安之骅科技有限责任公司 | Driving behavior evaluation system based on comprehensive environment perception |
| CN112382054A (en) * | 2020-11-11 | 2021-02-19 | 大连理工大学 | Automobile driving early warning prompting system and method based on vehicle-road cooperation |
-
2021
- 2021-07-01 CN CN202110746627.1A patent/CN113320545A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170248959A1 (en) * | 2016-02-29 | 2017-08-31 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device and vehicle control method |
| CN107272687A (en) * | 2017-06-29 | 2017-10-20 | 深圳市海梁科技有限公司 | A kind of driving behavior decision system of automatic Pilot public transit vehicle |
| CN108225364A (en) * | 2018-01-04 | 2018-06-29 | 吉林大学 | A kind of pilotless automobile driving task decision system and method |
| CN110667578A (en) * | 2018-12-29 | 2020-01-10 | 长城汽车股份有限公司 | Lateral decision making system and lateral decision making determination method for automatic driving vehicle |
| CN111383474A (en) * | 2018-12-29 | 2020-07-07 | 长城汽车股份有限公司 | Decision making system and method for automatically driving vehicle |
| CN110979327A (en) * | 2019-03-18 | 2020-04-10 | 长城汽车股份有限公司 | Longitudinal control method and system for automatic driving vehicle |
| CN110562258A (en) * | 2019-09-30 | 2019-12-13 | 驭势科技（北京）有限公司 | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium |
| CN111103882A (en) * | 2019-12-30 | 2020-05-05 | 合肥一辂汽车科技有限公司 | Autonomous following control method for unmanned electric vehicle |
| CN111645691A (en) * | 2020-04-29 | 2020-09-11 | 云南安之骅科技有限责任公司 | Driving behavior evaluation system based on comprehensive environment perception |
| CN112382054A (en) * | 2020-11-11 | 2021-02-19 | 大连理工大学 | Automobile driving early warning prompting system and method based on vehicle-road cooperation |
Non-Patent Citations (2)
| Title |
|---|
| 冀杰等: "基于有限状态机的车辆自动驾驶行为决策分析", 《汽车技术》 * |
| 张效宇等: "自动驾驶汽车的智能决策模型研究", 《汽车实用技术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI793894B (en) * | 2021-12-03 | 2023-02-21 | 荷蘭商荷蘭移動驅動器公司 | Driving assistance method based on hd map and vehicle intercommunication system |
| CN114644016A (en) * | 2022-04-14 | 2022-06-21 | 中汽创智科技有限公司 | Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium |
| CN115082900A (en) * | 2022-07-19 | 2022-09-20 | 湖南大学无锡智能控制研究院 | Intelligent vehicle driving decision system and method in parking lot scene |
| CN115082900B (en) * | 2022-07-19 | 2023-06-16 | 湖南大学无锡智能控制研究院 | Intelligent vehicle driving decision system and method in parking lot scene |
| CN115257807A (en) * | 2022-07-27 | 2022-11-01 | 武汉大学 | Urban on-road scene automatic driving decision-making method and equipment based on knowledge graph |
| CN115257807B (en) * | 2022-07-27 | 2024-01-30 | 武汉大学 | Urban road scene automatic driving decision-making method and device based on knowledge graph |
| CN115366888A (en) * | 2022-08-25 | 2022-11-22 | 武汉大学 | Crossing information system construction method and device for automatic driving navigation |
| CN117238159A (en) * | 2023-08-04 | 2023-12-15 | 华南理工大学 | Urban road-oriented intelligent network vehicle-connected behavior decision method |
| CN117238159B (en) * | 2023-08-04 | 2024-08-27 | 华南理工大学 | Urban road-oriented intelligent network vehicle-connected behavior decision method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113320545A (en) | Intersection behavior prediction decision method based on line-control intelligent vehicle | |
| CN110667578B (en) | Lateral decision making system and lateral decision making determination method for automatic driving vehicle | |
| US20220187834A1 (en) | Generating trajectories for autonomous vehicles | |
| US20190220030A1 (en) | Vehicle controller | |
| US20220234615A1 (en) | In-vehicle device and driving assist method | |
| CN111583711B (en) | Behavior control method and behavior control device | |
| US20210269040A1 (en) | Driving assist method and driving assist device | |
| CN111361564A (en) | Lane change system considering benefit maximization and comprehensive decision method | |
| Nobe et al. | An overview of recent developments in automated lateral and longitudinal vehicle controls | |
| CN111731294B (en) | Travel control device, travel control method, and storage medium storing program | |
| CN113525360A (en) | Vehicle and method of controlling the same | |
| WO2021054051A1 (en) | Electronic control device | |
| CN111731296A (en) | Travel control device, travel control method, and storage medium storing program | |
| CN113895459B (en) | Barrier screening method and system | |
| CN109910880B (en) | Vehicle behavior planning method and device, storage medium and terminal equipment | |
| US11807234B2 (en) | Automated driving trajectory generating device and automated driving device | |
| CN111731295A (en) | Travel control device, travel control method, and storage medium storing program | |
| CN110737261B (en) | Automatic stop control method and system for vehicle | |
| CN112249016A (en) | U-turn control system and method for autonomous vehicle | |
| US20210284142A1 (en) | Control device and vehicle | |
| WO2022118788A1 (en) | Vehicle control device | |
| CN114954452A (en) | Vehicle speed control method and system based on adaptive cruise | |
| CN112026774B (en) | Surrounding vehicle sideslip identification method based on own vehicle camera and radar sensing information | |
| US11697413B2 (en) | Vehicle control device | |
| US20210261132A1 (en) | Travel control apparatus, travel control method, and computer-readable storage medium storing program |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210831 |
|
| RJ01 | Rejection of invention patent application after publication |