CN113370994A - Automatic driving behavior decision method based on surrounding vehicle behaviors - Google Patents
Automatic driving behavior decision method based on surrounding vehicle behaviors Download PDFInfo
- Publication number
- CN113370994A CN113370994A CN202110667450.6A CN202110667450A CN113370994A CN 113370994 A CN113370994 A CN 113370994A CN 202110667450 A CN202110667450 A CN 202110667450A CN 113370994 A CN113370994 A CN 113370994A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- self
- corresponding targets
- automatic driving
- 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 27
- 230000006399 behavior Effects 0.000 title abstract description 43
- 230000004927 fusion Effects 0.000 claims abstract description 9
- 230000009977 dual effect Effects 0.000 claims 1
- 230000004888 barrier function Effects 0.000 abstract description 2
- 230000008447 perception Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- 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
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of automatic driving, and discloses an automatic driving behavior decision method based on surrounding vehicle behaviors, which comprises the following steps: obtaining first information from respective targets around a vehicle, the respective targets including the vehicle and an obstacle; acquiring the relative relation between corresponding targets around the self-vehicle and the self-vehicle; acquiring second information of corresponding targets around the self-vehicle; and performing fusion comparison on the first information and the second information of the corresponding targets around the self vehicle and the relative relation between the corresponding targets and the self vehicle, and outputting a decision result. The invention improves the safety of driving and parking; the comfort level of passengers in the vehicle is increased, and the uncomfortable feeling of emergency braking caused by suddenly appearing barriers on a driving route is avoided; this can be done based on existing vehicle sensors, without additional sensor information.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving behavior decision method based on surrounding vehicle behaviors.
Background
The automatic driving system is an intelligent system capable of driving a vehicle independently, and can assist people and even replace people to drive the vehicle. According to the intelligence degree, the system can be generally divided into five levels of Level1-Level 5. At a lower level, people generally drive mainly, an automatic driving system is used for assisting, the driver can be reminded to carry out some operations, and at a high level, the driver can not intervene a steering wheel, an accelerator and a brake, or even can not sit in the vehicle, and the vehicle can automatically plan a driving destination and park. In general, in such a high-level automatic driving system, a behavior decision module is provided to guide the planning of the behavior of the own vehicle.
The existing behavior decision module generally decides the behavior of the vehicle at the next moment based on information such as the position, type, lane line, vehicle location line, deceleration strip, road condition and the like of surrounding obstacles. However, these methods lack an important information: intention information of objects in surrounding motion or ready for motion. The object in motion means, for example, a vehicle and a non-vehicle in motion, a person in motion, and the like. The object to be moved is a vehicle which is stopped at the roadside and is ready to start after turning on a turn signal. The behaviors of the objects often contain important information which can be used by the decision module, for example, a vehicle in the same lane ahead suddenly turns on a left steering lamp or a right steering lamp or a double flashing lamp, the speed of the vehicle is often reduced, so that the speed of the current vehicle (hereinafter referred to as the vehicle) is reduced in advance, or when the vehicle is about to change lanes, the vehicle in front suddenly turns on the steering lamp, and the vehicle is required to take corresponding measures to deal with the situation, but the situation that the vehicle is directly changed lanes like the current traditional decision module is avoided, so that the potential safety hazard is certainly increased. The other point is that the current decision module generally considers the obstacle information outside the driving route only and mostly considers the obstacle information on the current driving track only, so that if very quick obstacles appear on the driving track of the self vehicle around, potential safety hazards are possibly caused, or vehicles on the side lanes change from the driving track to the driving track suddenly, and the self vehicle is difficult to decelerate and avoid in advance due to lack of the information of the side vehicles. Therefore, the new generation of behavior decision modules must be able to utilize the movement and intent information of surrounding obstacles in addition to the traditional sensor information.
Disclosure of Invention
The invention aims to provide an automatic driving behavior decision method based on surrounding vehicle behaviors so as to solve the existing problems.
In order to achieve the purpose, the invention provides the following technical scheme: an automatic driving behavior decision method based on surrounding vehicle behaviors, comprising the steps of:
obtaining first information from respective targets around a vehicle, the respective targets including the vehicle and an obstacle;
acquiring the relative relation between corresponding targets around the self-vehicle and the self-vehicle;
acquiring second information of corresponding targets around the self-vehicle;
and performing fusion comparison on the first information and the second information of the corresponding targets around the self vehicle and the relative relation between the corresponding targets and the self vehicle, and outputting a decision result.
As a method for deciding an automatic driving behavior based on a behavior of a surrounding vehicle of the present invention, it is preferable that the first information and the second information each include vehicle information and obstacle category information.
As a method for deciding an automatic driving behavior based on the behavior of a surrounding vehicle according to the present invention, it is preferable that the vehicle information includes a turn signal lamp, a double flash lamp, and a brake lamp.
As an automatic driving behavior decision method based on surrounding vehicle behaviors according to the present invention, preferably, the obstacle category information includes a speed bump, a wall, a pillar, and a railing.
As a method for deciding an automatic driving behavior based on the behavior of a surrounding vehicle according to the present invention, it is preferable that the relative relationship includes a relative position relationship, a relative speed relationship, and a relative moving direction.
As an automatic driving behavior decision method based on surrounding vehicle behavior of the present invention, it is preferable that first information of corresponding targets around the own vehicle is acquired by a camera.
As an automatic driving behavior decision method based on surrounding vehicle behavior of the present invention, it is preferable that the second information of the corresponding target around the vehicle is obtained by an ultrasonic radar, a millimeter wave radar, and a laser radar.
As an automatic driving behavior decision method based on surrounding vehicle behaviors of the present invention, preferably, the method comprises the steps of, after performing fusion comparison on the first information and the second information of the corresponding target around the host vehicle and the relative relationship between the corresponding target and the host vehicle, and outputting a decision result: and planning the driving behavior of the self-vehicle according to the decision result.
Compared with the prior art, the invention has the following beneficial effects: the invention improves the safety of driving and parking; the comfort level of passengers in the vehicle is increased, and the uncomfortable feeling of emergency braking caused by suddenly appearing barriers on a driving route is avoided; this can be done based on existing vehicle sensors, without additional sensor information.
Drawings
FIGS. 1-2 are flow diagrams of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: an automatic driving behavior decision method based on surrounding vehicle behaviors, comprising the steps of:
s100, obtaining first information of corresponding targets around a vehicle, wherein the corresponding targets comprise the vehicle and an obstacle;
s200, acquiring a relative relation between corresponding targets around the self-vehicle and the self-vehicle;
s300, acquiring second information of corresponding targets around the self-vehicle;
s400, fusion comparison is carried out on the first information and the second information of the corresponding targets around the self vehicle and the relative relation between the corresponding targets and the self vehicle, and a decision result is output.
In this embodiment, since the behavior decision algorithm depends on the input of the sensor, the perception processing module, and the fusion module, the automatic driving decision algorithm based on the surrounding vehicle behavior includes the following contents:
the input of the perception module is real world results sensed by a camera, an ultrasonic radar, a millimeter wave radar and a laser radar, and the post-processing results are output to a subsequent module on the input results, but the sensors required by the perception module are not all required at the same time, and the behavior decision module can adapt to the results of different sensors according to the sensor assembly scheme of an actual vehicle, namely, for example, if the vehicle only has the camera, the information of steering lamps, double flashing lamps and brake lamps of surrounding vehicles sensed by the camera is used for judging. If only the ultrasonic radar is used, the method is used in a low-speed parking scene, and the decision is made by utilizing the relative motion relation between surrounding obstacles sensed by the ultrasonic radar and the self-vehicle. For modern vehicle models, a general camera and an ultrasonic radar are standard, and the millimeter wave radar and the laser radar may exist only on a specific vehicle model. The following is all deployed with all of these 4 sensors mounted on the vehicle.
The new generation of decision-making module needs a camera to additionally provide information of a steering lamp, a double-flashing lamp and a brake lamp of surrounding vehicles besides sensor information required by the traditional method, and the ultrasonic radar/millimeter wave radar/laser radar additionally provides information of speed, direction and position of surrounding obstacles relative to the vehicle after respective detection and processing.
The results of the four main sensors of the sensing module are fused and judged, and the data such as the ID, the category, the size, the relative motion relation and the like of the obstacles detected by the sensing module are compared to filter noise and interference, so that the lamp which is turned on by which obstacle is accurately positioned, the speed of which obstacle to drive in which direction is determined, and the position of which obstacle is reached at which time. And outputs this information to the behavioral decision module.
And the behavior decision algorithm makes the behavior of the next moment of the self-vehicle in real time according to the fused information.
Specifically, the first information and the second information each include vehicle information and obstacle category information.
Specifically, the vehicle information includes a turn light, a double flashing light, and a brake light.
Specifically, the obstacle category information includes speed bumps, walls, pillars, and railings.
Specifically, the relative relationship includes a relative position relationship, a relative speed relationship, and a relative movement direction.
Specifically, first information of corresponding targets around the own vehicle is acquired through the camera.
Specifically, the second information from the respective targets around the vehicle is obtained by the ultrasonic radar, the millimeter wave radar, and the laser radar.
Specifically, in the step S400, the first information and the second information of the corresponding target around the own vehicle and the relative relationship between the corresponding target and the own vehicle are fused and compared, and after a decision result is output, the method includes the steps of: and S500, planning the driving behavior of the self-vehicle according to the decision result.
Another embodiment of the invention: based on camera, ultrasonic radar, millimeter wave radar and laser radar fusion result, set up the destination on jia Min high frame after, let the self-car independently cruise, specifically include:
cameras, ultrasonic radars, millimeter wave radars and laser radars have been installed on the self-vehicle.
And extracting the turn lights, the double flashing lights, the brake lights and the obstacle type information of the surrounding vehicles from the camera.
And extracting the relative position, the relative speed, the motion direction and the obstacle type information of the corresponding target and the self vehicle from the ultrasonic radar, the millimeter wave radar and the laser radar.
And outputting the sensing processing results of the sensors to a fusion module.
And after the fusion module integrates the information of the sensors, the final result is output to the decision module.
And the behavior decision module plans the behavior of the self vehicle according to the information. When the lane of the front next door is turned and the lane of the vehicle is changed, the vehicle needs to be decelerated, and when the lane of the opposite vehicle is changed, the speed is recovered according to the actual distance and the relative speed.
The invention has the advantages of forethought, and forethought of surrounding obstacles; the safety is high, and the potential safety hazard is reduced; the universality is strong, and the judgment mode of a human driver is better met; independent of a single specific sensor, in the case of the absence of any one sensor, the decision can be made depending on the information of the other sensors.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. An automatic driving behavior decision method based on surrounding vehicle behavior, characterized by comprising the steps of:
s100, obtaining first information of corresponding targets around a vehicle, wherein the corresponding targets comprise the vehicle and an obstacle;
s200, acquiring a relative relation between corresponding targets around the self-vehicle and the self-vehicle;
s300, acquiring second information of corresponding targets around the self-vehicle;
s400, fusion comparison is carried out on the first information and the second information of the corresponding targets around the self vehicle and the relative relation between the corresponding targets and the self vehicle, and a decision result is output.
2. The method of claim 1, wherein the first information and the second information each comprise vehicle information and obstacle category information.
3. The method of claim 1, wherein the vehicle information comprises turn signals, dual flashing lights, and brake lights.
4. The automated driving behavior decision method based on surrounding vehicle behavior of claim 1, characterized in that the obstacle category information comprises speed bumps, walls, pillars and railings.
5. The method of claim 1, wherein the relative relationship comprises a relative position relationship, a relative velocity relationship, and a relative direction of motion.
6. The automatic driving behavior decision method based on surrounding vehicle behavior as claimed in claim 1, characterized in that the first information of the corresponding targets around the own vehicle is obtained by a camera.
7. The automatic driving behavior decision method based on surrounding vehicle behavior according to claim 1, characterized in that the second information from the corresponding targets around the vehicle is obtained by ultrasonic radar, millimeter wave radar and lidar.
8. The method according to claim 1, wherein the step of S400 fusion-comparing the first information and the second information of the corresponding target around the host vehicle and the relative relationship between the corresponding target and the host vehicle, and outputting the decision result comprises: and S500, planning the driving behavior of the self-vehicle according to the decision result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667450.6A CN113370994A (en) | 2021-06-16 | 2021-06-16 | Automatic driving behavior decision method based on surrounding vehicle behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667450.6A CN113370994A (en) | 2021-06-16 | 2021-06-16 | Automatic driving behavior decision method based on surrounding vehicle behaviors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113370994A true CN113370994A (en) | 2021-09-10 |
Family
ID=77572851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110667450.6A Pending CN113370994A (en) | 2021-06-16 | 2021-06-16 | Automatic driving behavior decision method based on surrounding vehicle behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113370994A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114261389A (en) * | 2021-11-29 | 2022-04-01 | 东风商用车有限公司 | Running track collision risk analysis method of automatic driving commercial vehicle |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105575150A (en) * | 2016-01-29 | 2016-05-11 | 深圳市美好幸福生活安全***有限公司 | Driving safety behavior analysis method, driving safety early-warning method, driving safety behavior analysis device and driving safety early-warning device |
| CN105711586A (en) * | 2016-01-22 | 2016-06-29 | 江苏大学 | Front collision avoiding system based on driving behavior of front vehicle driver and vehicle collision avoiding algorithm |
| JP2019128954A (en) * | 2018-01-25 | 2019-08-01 | 广州大学 | Method and system of controlling linkage between driver and vehicle active safety technology |
| CN110682864A (en) * | 2019-09-26 | 2020-01-14 | 浙江吉利汽车研究院有限公司 | Early warning method and device for preventing rear-end collision in abnormal braking and vehicle |
| CN110775069A (en) * | 2019-10-29 | 2020-02-11 | 长安大学 | Vehicle driving mode recognition device and method in mixed driving mode |
| WO2020216316A1 (en) * | 2019-04-26 | 2020-10-29 | 纵目科技（上海）股份有限公司 | Driver assistance system and method based on millimetre wave radar, terminal, and medium |
| CN112633124A (en) * | 2020-12-17 | 2021-04-09 | 东风汽车有限公司 | Target vehicle judgment method for automatic driving vehicle and electronic equipment |
-
2021
- 2021-06-16 CN CN202110667450.6A patent/CN113370994A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105711586A (en) * | 2016-01-22 | 2016-06-29 | 江苏大学 | Front collision avoiding system based on driving behavior of front vehicle driver and vehicle collision avoiding algorithm |
| CN105575150A (en) * | 2016-01-29 | 2016-05-11 | 深圳市美好幸福生活安全***有限公司 | Driving safety behavior analysis method, driving safety early-warning method, driving safety behavior analysis device and driving safety early-warning device |
| JP2019128954A (en) * | 2018-01-25 | 2019-08-01 | 广州大学 | Method and system of controlling linkage between driver and vehicle active safety technology |
| WO2020216316A1 (en) * | 2019-04-26 | 2020-10-29 | 纵目科技（上海）股份有限公司 | Driver assistance system and method based on millimetre wave radar, terminal, and medium |
| CN110682864A (en) * | 2019-09-26 | 2020-01-14 | 浙江吉利汽车研究院有限公司 | Early warning method and device for preventing rear-end collision in abnormal braking and vehicle |
| CN110775069A (en) * | 2019-10-29 | 2020-02-11 | 长安大学 | Vehicle driving mode recognition device and method in mixed driving mode |
| CN112633124A (en) * | 2020-12-17 | 2021-04-09 | 东风汽车有限公司 | Target vehicle judgment method for automatic driving vehicle and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114261389A (en) * | 2021-11-29 | 2022-04-01 | 东风商用车有限公司 | Running track collision risk analysis method of automatic driving commercial vehicle |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102295392B1 (en) | Preparing autonomous vehicles for turns | |
| JP6156333B2 (en) | Automated driving vehicle system | |
| WO2019171576A1 (en) | Vehicle control device, vehicle control method, and program | |
| CN110281920B (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN110060467B (en) | Vehicle control device | |
| CN110053617B (en) | Vehicle control device, vehicle control method, and storage medium | |
| JP6641583B2 (en) | Vehicle control device, vehicle control method, and program | |
| CN111583711B (en) | Behavior control method and behavior control device | |
| AU2017302462A1 (en) | Determining drivability of objects for autonomous vehicles | |
| CN110116726B (en) | Vehicle control device, vehicle control method, and storage medium | |
| KR20180086632A (en) | Apparatus amd method of determining action of an autonomous vehicle | |
| JP2019159426A (en) | Vehicle control device, vehicle control method, and program | |
| CN110271544B (en) | Vehicle control device, vehicle control method, and storage medium | |
| US11348463B2 (en) | Travel control device, travel control method, and storage medium storing program | |
| JP2019137189A (en) | Vehicle control system, vehicle control method, and program | |
| JP2019159427A (en) | Vehicle control device, vehicle control method, and program | |
| CN112193246A (en) | Vehicle and method for performing inter-vehicle distance control | |
| JP2020147139A (en) | Vehicle control device, vehicle control method, and program | |
| JP2019160031A (en) | Vehicle control device, vehicle control method, and program | |
| US11926260B2 (en) | Method for operating a parking assistance function of a motor vehicle | |
| CN111605545A (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN113370994A (en) | Automatic driving behavior decision method based on surrounding vehicle behaviors | |
| CN116524721A (en) | Vehicle intersection decision method, device, equipment and storage medium | |
| WO2022130701A1 (en) | Vehicle control device | |
| CN215322519U (en) | Automatic driving behavior decision system based on surrounding vehicle behaviors |
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: 20210910 |