CN110733503A - Method for operating an automatic or driver assistance system of a vehicle and vehicle - Google Patents
Method for operating an automatic or driver assistance system of a vehicle and vehicle Download PDFInfo
- Publication number
- CN110733503A CN110733503A CN201911106460.1A CN201911106460A CN110733503A CN 110733503 A CN110733503 A CN 110733503A CN 201911106460 A CN201911106460 A CN 201911106460A CN 110733503 A CN110733503 A CN 110733503A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- distance
- host vehicle
- immediately
- host
- 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
- 230000006870 function Effects 0.000 claims description 22
- 230000008447 perception Effects 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000010801 machine learning 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
- 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
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- 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
- 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
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The present invention relates to methods for operating an automatic driving system or a driving assistance system of a vehicle, including the steps of receiving sensor data and processing the sensor data to identify a vehicle immediately in front of the host vehicle in a current lane of the host vehicle (S01), determining whether the identified vehicle immediately in front of the host vehicle is a vehicle with a loading function (S02), and if the identified vehicle immediately in front of the host vehicle is determined to be a vehicle with a loading function, setting a sensing module processing mode of the automatic driving system or the driving assistance system according to a distance between the host vehicle and the vehicle immediately in front of the host vehicle.
Description
Technical Field
The invention relates to a method for operating an automatic driving system or a driving assistance system of a vehicle and a vehicle.
Background
Autonomous vehicles recognize lane lines and objects through machine learning methods (e.g., deep learning algorithms). generally, classes of objects have small motor vehicles (cars), large motor vehicles (trucks), non-motor vehicles (tricycles, motorcycles, electric vehicles, bicycles), pedestrians, etc., and are represented as 2D or 3D bounding boxes with directional information.
CN109774707A discloses a control method and apparatus for an autonomous vehicle. The method comprises the following steps: acquiring parameter information of a preceding vehicle, the preceding vehicle being a vehicle in front of the current vehicle in an adjacent lane, the parameter information including: a longitudinal distance between the preceding vehicle and the current vehicle, a lateral distance between the preceding vehicle and the current vehicle, position information of the preceding vehicle, a type of the preceding vehicle; and controlling a lateral distance between a current vehicle and the preceding vehicle according to the parameter information of the preceding vehicle.
JP2017149377A discloses inter-vehicle distance control units and inter-vehicle distance control methods.an inter-vehicle distance control unit includes a preceding vehicle type determination unit, a vehicle speed measurement unit, an inter-vehicle distance measurement unit, and an acceleration/deceleration control unit.
However, no special consideration has been given to a vehicle having a loading function in the related art. In such a vehicle, since the size of the loaded items is larger than the cabin space, the loaded items may protrude out of the cabin space at both sides or the rear of the vehicle. If the automatic driving vehicle cannot recognize the objects protruding from the rear end or both sides of the vehicle in time, the automatic driving vehicle may feel uncomfortable due to sudden braking caused by too late recognition. And may even affect the safety of the autonomous vehicle.
Disclosure of Invention
The invention aims to improve a planning and control method for a vehicle automatic driving or driving assistance system so as to prevent a vehicle with a loading function in front of or beside the vehicle from bringing danger to the vehicle (the automatic driving vehicle or the vehicle with the driving assistance system).
A method for operating an autopilot system or a driver assistance system for a vehicle, comprising the steps of:
receiving the sensor data and processing it, recognizing a vehicle immediately in front of the host vehicle in the current lane of the host vehicle (S01),
determining whether the recognized vehicle immediately in front of the host vehicle is a vehicle having a loading function (S02),
and if the recognized vehicle which is immediately in front of the vehicle is judged to be the vehicle with the loading function, setting a processing mode of a perception module of an automatic driving system or an auxiliary driving system according to the distance between the vehicle and the vehicle which is immediately in front of the vehicle.
According to the method, different perception module processing modes can be set by perceiving and identifying that the nearest object in the path is a vehicle with loading capacity or a special vehicle with loading capacity, so that emergency braking or collision is avoided in aspect, driving experience is damaged, and in addition, the perception module processing mode can be properly selected in aspect, so that the waste of computing power is avoided.
In preferred embodiments, if it is determined that the distance between the host vehicle and the vehicle immediately in front of the host vehicle is less than the th distance, the perception module processing mode is set to an aggressive mode in which an object is recognized as a tracking object or obstacle upon detection.
In preferred embodiments, if it is determined that the distance between the host vehicle and the vehicle immediately in front of the host vehicle is not less than the th distance, the perception module processing mode is set to the -general mode, and in the -general mode, the detected object is identified as a tracking object or obstacle only when the detected object satisfies the predetermined -th size requirement and the relevant -th trajectory condition is provided in the predetermined -th window.
In preferred embodiments, the distance is a fixed value, or a value that varies with the relevant parameter, or a value that varies by a deep learning network.
In preferred embodiments, if it is determined that the recognized vehicle immediately in front of the host vehicle is a vehicle having a loading function, the following distance between the host vehicle and the vehicle immediately in front of the host vehicle or the control limit value of the following distance is automatically adjusted.
In preferred embodiments, it is determined whether or not a vehicle located beside the host vehicle in the adjacent lanes on both sides is a vehicle having a loading function, and if it is determined that the vehicle located beside the host vehicle is the vehicle having the loading function, the sensing module processing mode is set according to the distance between the host vehicle and the vehicle located beside the host vehicle.
In preferred embodiments, if it is determined that the distance between the host vehicle and the vehicle located beside the host vehicle is less than the second distance, the sensing module processing mode is set to an aggressive mode in which an object is recognized as a tracking object or an obstacle upon detection.
In preferred embodiments, if it is judged that the distance between the host vehicle and the vehicle located beside the host vehicle is not less than , the processing mode of the perception module is set to -way mode, and in -way mode, the detected object is identified as the tracking object or obstacle only when the detected object meets the predetermined -way size requirement and the -way condition is predetermined to have the -way track condition in the window.
In , if it is determined that the vehicle located beside the own vehicle is a vehicle having a loading function, a lateral distance between the own vehicle and the vehicle located beside the own vehicle or a control limit value of the lateral distance is automatically adjusted.
The invention further relates to vehicles having a control device for carrying out the method according to the invention.
Drawings
FIG. 1 shows a schematic view of a vehicle loaded with items beyond the cabin space.
Fig. 2 shows a flow chart of a method according to the invention.
Detailed Description
Fig. 1 schematically shows a vehicle having a loading function. The items loaded in the vehicle protrude out of the cabin space at the rear of the vehicle. In the case of a vehicle that starts an automatic driving system or a driving assistance system, if an object extending outward at the rear and/or near the vehicle of a vehicle having a loading function in front of the vehicle cannot be recognized in time, the vehicle may be recognized too late and may cause sudden braking, which may cause discomfort. And may even affect the safety of the vehicle and the vehicle-mounted personnel.
For example, an object tracking module uses a variety of information to generate object data including, but not limited to, 3D position, 2D image patch, 2D frame or deep learning ROI (Region of interest) features.
In the method of the present invention, the sensing module processing modes for determining a tracked object or obstacle are divided into three categories, namely an aggressive mode, an -like mode and a relaxed mode, and of the sensing module processing modes are selectively applied depending on the particular road conditions, in the aggressive mode an object is detected and identified as a tracked object or obstacle in the -like mode a detected object is identified as a tracked object or obstacle only if it meets a predefined size requirement and has an associated track condition within a predefined time window, and in the relaxed mode a detected object is identified as a tracked object or obstacle only if it meets a predefined second size requirement and has an associated second track condition within a predefined second time window, wherein the second size is greater than the size and/or the second time window is greater than the window, and/or the second track condition is more stringent than the track condition.
Under different road conditions, different perception algorithm modes are selected, and the calculation power and the recognition accuracy can be favorably considered, so that the calculation power is fully utilized to achieve the necessary recognition accuracy. Therefore, the method avoids the waste of computing power, reduces the energy consumption and saves the cost while ensuring the safety.
The slack mode may be set under certain good road traffic conditions, such as on motorways with few vehicles, etc. Or in the case of urban traffic where the vehicle speed is extremely slow, the relaxation mode may be set in advance.
preferred embodiments of the method according to the invention are described in detail below with reference to fig. 2. the method of the invention is carried out in a -like implementation of a sensing module and a decision module integrated in an automatic driving system or a driving assistance system of a vehicle on which the automatic driving system or the driving assistance system is activated.
First, the method starts (S00) and proceeds to step S01. In step S01, the sensor data is processed to recognize the types of vehicles or objects immediately in front of the host vehicle in the current lane of the host vehicle and vehicles or objects located beside the host vehicle in the adjacent lanes on both sides.
Then, the process proceeds to step S02, where it is determined whether or not the vehicle immediately in front of the host vehicle is a vehicle having a loading function, which is recognized in step S02. If it is determined in step S02 that the vehicle identified immediately in front of the host vehicle is a vehicle having a loading function, the routine proceeds to step S04.
In step S04, it is determined whether the distance between the host vehicle and the vehicle immediately in front of the host vehicle is less than a th distance, preferably, the th distance may be a fixed value, such as 5 meters, 4 meters, or 3 meters, but the th distance may also be a value that varies with a parameter related to vehicle conditions or external environmental conditions, such as a value related to host vehicle speed, and/or related to road conditions, and/or related to weather conditions (e.g., rainy or foggy conditions), and/or related to vehicle braking parameters.
If it is determined in step S04 that the distance between the host vehicle and the vehicle immediately in front of the host vehicle is less than the -th distance, the process proceeds to step S07. in step S07, the processing mode of the sensing module of the automatic driving system or the driving assistance system is set (including being switched to or held) to the aggressive mode. after step S07, the process proceeds to step S01, and the process is started again.
If it is determined in step S04 that the distance between the host vehicle and the vehicle immediately in front of the host vehicle is not less than the th distance, the process proceeds to step S06. in step S06, the perception module processing mode is set (including being switched to or held at) the -like mode. after step S06, the process proceeds to step S01, where the process is started again.
If it is determined in step S02 that the recognized vehicle immediately in front of the host vehicle is not a vehicle having a loading function, the routine proceeds to step S03. In step S03, it is determined whether or not the vehicle located on the side of the host vehicle in the adjacent lanes on both sides is a vehicle having a loading function. Here, "located beside the host vehicle" may be understood as meaning that the distance from the host vehicle is within a predetermined distance range (for example, 5 meters), and the range may be a distance value that varies depending on a parameter related to the vehicle condition or the external environmental condition.
If it is determined in step S03 that the vehicle on the side of the host vehicle is a vehicle with a loading function, then step S05 is reached, in step S05, it is determined whether the distance between the host vehicle and the vehicle on the side of the host vehicle is less than a second distance, preferably, the second distance may be a fixed value, such as 3 meters or 2 meters, but the th distance may also be a value that varies with a parameter related to the vehicle condition or an external environmental condition, such as a value related to the host vehicle speed, and/or related to a road condition, and/or related to a weather condition (e.g., a rainy or foggy condition), and/or related to a vehicle lateral stability parameter, and the th distance may also be a varying value derived through a deep learning network.
If it is judged in step S05: if the distance between the host vehicle and the vehicle located beside the host vehicle is smaller than the second distance, the process proceeds to step S07.
If it is determined in step S05 that the distance between the host vehicle and the vehicle located beside the host vehicle is not less than the second distance, the process proceeds to step S08. in step S08, the perception module processing mode is set (e.g., switched to or held at) -like mode, after step S08, the process proceeds to step S01, and the process is started again.
If it is determined in step S03 that the vehicle located on the side of the own vehicle is not a vehicle having a loading function, the routine proceeds to step S08.
Preferably, the distance is automatically adjusted if a vehicle immediately in front of the host vehicle in the current lane of the host vehicle or a vehicle located beside the host vehicle in adjacent lanes on both sides is determined to be a vehicle with loading capability. That is, the following distance to the vehicle immediately in front of the own vehicle or the control limit value of the following distance is automatically adjusted, or the lateral distance to the vehicle located on the side of the own vehicle or the control limit value of the lateral distance is automatically adjusted. Thereby avoiding emergency braking or collision and damaging the driving experience.
Claims (10)
1, a method for operating an autopilot or driver assistance system for a vehicle, comprising the steps of:
receiving the sensor data and processing it, recognizing a vehicle immediately in front of the host vehicle in the current lane of the host vehicle (S01),
determining whether the recognized vehicle immediately in front of the host vehicle is a vehicle having a loading function (S02),
and if the recognized vehicle which is immediately in front of the vehicle is judged to be the vehicle with the loading function, setting a processing mode of a perception module of an automatic driving system or an auxiliary driving system according to the distance between the vehicle and the vehicle which is immediately in front of the vehicle.
2. The method of claim 1, wherein if it is determined that the distance between the host vehicle and the vehicle immediately in front of the host vehicle is less than the th distance (S04), the sensing module processing mode is set to an aggressive mode (S07) in which an object is recognized as a tracking object or obstacle upon detection.
3. The method according to claim 1, wherein if it is judged that the distance between the host vehicle and the vehicle immediately in front of the host vehicle is not less than the th distance (S04), the perception module processing mode is set to -like mode (S06), and in -like mode, the detected object is recognized as the tracking object or the obstacle only when the detected object satisfies a predetermined th size requirement and a predetermined th time window has a relevant th trajectory condition.
4. A method according to claim 2 or 3, characterized in that the th distance is a fixed value, or a value that varies with the relevant parameter, or a varying value derived through a deep learning network.
5. The method according to claim 1, wherein if it is determined that the recognized vehicle immediately in front of the host vehicle is a vehicle with a loading function, a following distance between the host vehicle and the vehicle immediately in front of the host vehicle or a control limit value of the following distance is automatically adjusted.
6. The method according to claim 1, wherein it is determined whether the vehicle located beside the host vehicle in the adjacent lanes on both sides is a vehicle with a loading function (S03), and if it is determined that the vehicle located beside the host vehicle is a vehicle with a loading function, the sensing module processing mode is set according to a distance between the host vehicle and the vehicle located beside the host vehicle.
7. The method of claim 6, wherein if it is determined that the distance between the host vehicle and the vehicle located beside the host vehicle is less than the second distance (S05), the sensing module processing mode is set to an aggressive mode (S07) in which an object is detected to be recognized as a tracking object or an obstacle.
8. The method as claimed in claim 6, wherein if it is judged that the distance between the host vehicle and the vehicle located beside the host vehicle is not less than the th distance (S05), the perception module processing mode is set to -like mode (S08), and in -like mode, the detected object is recognized as a tracking object or obstacle only when the detected object satisfies a predetermined th size requirement and an associated th trajectory condition is provided in a window at a predetermined th time.
9. The method according to claim 6, wherein if it is determined that the vehicle located beside the own vehicle is a vehicle with a loading function, a lateral distance between the own vehicle and the vehicle located beside the own vehicle or a control limit value of the lateral distance is automatically adjusted.
10, vehicle having control means for performing the method according to any of claims 1-9, .
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911106460.1A CN110733503A (en) | 2019-11-13 | 2019-11-13 | Method for operating an automatic or driver assistance system of a vehicle and vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911106460.1A CN110733503A (en) | 2019-11-13 | 2019-11-13 | Method for operating an automatic or driver assistance system of a vehicle and vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110733503A true CN110733503A (en) | 2020-01-31 |
Family
ID=69272803
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911106460.1A Pending CN110733503A (en) | 2019-11-13 | 2019-11-13 | Method for operating an automatic or driver assistance system of a vehicle and vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110733503A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112232254A (en) * | 2020-10-26 | 2021-01-15 | 清华大学 | Pedestrian risk assessment method considering pedestrian acceleration rate |
-
2019
- 2019-11-13 CN CN201911106460.1A patent/CN110733503A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112232254A (en) * | 2020-10-26 | 2021-01-15 | 清华大学 | Pedestrian risk assessment method considering pedestrian acceleration rate |
CN112232254B (en) * | 2020-10-26 | 2021-04-30 | 清华大学 | Pedestrian risk assessment method considering pedestrian acceleration rate |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106537180B (en) | Method for mitigating radar sensor limitations with camera input for active braking of pedestrians | |
CN108216225B (en) | Collision avoidance assistance device | |
CN107782727B (en) | Fusion-based wet pavement detection | |
CN112389466B (en) | Method, device and equipment for automatically avoiding vehicle and storage medium | |
US9884645B2 (en) | Lane change control system | |
US9499171B2 (en) | Driving support apparatus for vehicle | |
US9493163B2 (en) | Driving support apparatus for vehicle | |
US10887568B2 (en) | Image processing apparatus, and image processing method | |
CN112208533B (en) | Vehicle control system, vehicle control method, and storage medium | |
US20140052357A1 (en) | Assistance system for a motor vehicle and method for controlling a motor vehicle | |
US11524680B2 (en) | Control device and control method for controlling behavior of motorcycle | |
US11217045B2 (en) | Information processing system and server | |
US11780433B2 (en) | Systems and methods for selectively modifying collision alert thresholds | |
KR102463722B1 (en) | Apparatus and method for setting velocity of vehicle | |
CN109318894B (en) | Vehicle driving assistance system, vehicle driving assistance method, and vehicle | |
CN108068809B (en) | Vehicle control device, vehicle control method, and storage medium | |
US20210316734A1 (en) | Vehicle travel assistance apparatus | |
US20210061350A1 (en) | Driving support device | |
US20220375349A1 (en) | Method and device for lane-changing prediction of target vehicle | |
CN107571858B (en) | Vehicle curve deceleration method and device | |
CN110733503A (en) | Method for operating an automatic or driver assistance system of a vehicle and vehicle | |
WO2020020525A1 (en) | Method for performing an overtaking maneuver including considering a safety distance, analyzing component, driver assistance system, as well as vehicle | |
EP3480075A1 (en) | A vision system and method for autonomous driving and/or driver assistance in a motor vehicle | |
CN113408320A (en) | Method, electronic device, and computer storage medium for vehicle collision avoidance | |
US11908200B2 (en) | System and method in the prediction of target vehicle behavior based on image frame and normalization |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200131 |