CN110262521A - A kind of automatic Pilot control method - Google Patents
A kind of automatic Pilot control method Download PDFInfo
- Publication number
- CN110262521A CN110262521A CN201910672528.6A CN201910672528A CN110262521A CN 110262521 A CN110262521 A CN 110262521A CN 201910672528 A CN201910672528 A CN 201910672528A CN 110262521 A CN110262521 A CN 110262521A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- front obstacle
- automatic pilot
- sides
- data
- 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 39
- 230000004438 eyesight Effects 0.000 claims abstract description 56
- 230000033001 locomotion Effects 0.000 claims description 27
- 230000000007 visual effect Effects 0.000 claims description 25
- 230000004888 barrier function Effects 0.000 claims description 21
- 230000001133 acceleration Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The present embodiments relate to a kind of automatic Pilot control methods, comprising: the initial position message and target position information for obtaining vehicle generate automatic Pilot path in navigation map；Judge whether vehicle is in preset normal condition；Obtain two sides obstacle distance data and front obstacle binocular vision data；Judge vehicle two sides with the presence or absence of collision trend；3D modeling is carried out to front obstacle；Front obstacle is identified according to front obstacle 3D model data；Recognition result according to vehicle at a distance from front obstacle and to front obstacle determines risk of collision peak；Judge whether risk of collision peak is lower than preset threshold；When vehicle is in normal condition, vehicle two sides there is no collision trend and risk of collision peak is lower than preset threshold, continue to drive according to automatic Pilot path.This method precision is high, and when vehicle high-speed drives, data can be transmitted to processor without reducing frame per second.
Description
Technical field
The present invention relates to automatic Pilot field more particularly to a kind of automatic Pilot control methods.
Background technique
With the continuous promotion of scientific and technological level in recent years, artificial intelligence rapid development, extensive utilization to every field it
In.Wherein, since automatic driving vehicle can efficiently utilize traffic resource, alleviate traffic congestion, reduce carbon emission, automatic Pilot
Technology increasingly becomes people's focus of interest.
Automatic driving vehicle is closed by artificial intelligence, vision calculating, radar, monitoring device and global positioning system collaboration
Make, computer is allowed can to operate motor vehicles to automatic safe under the operation of nobody class active.For example, passing through packet
The monitoring devices such as visual sensor, radar sensor and airborne laser range finder are included to obtain the traffic condition of surrounding, and pass through one
A detailed electronic map navigates to the road in front.Wherein, visual sensor is typically mounted near vehicle mirrors,
Traffic lights for identification, and mobile barrier is distinguished under the auxiliary of computer, for example, front vehicles, bicycle or
Pedestrian.
Since precision of the current visual sensor for obstacles around the vehicle Image Acquisition is lower, error is generally several
In cm range, thus for barrier at a distance from vehicle, the description precision of the motion profile of barrier etc. it is lower, Wu Faman
Precision required by sufficient automatic driving vehicle.In addition, due to current visual sensor to car-mounted computer transmission image frame
Rate highest is only capable of reaching 60 frames, and when the vehicle runs at a high speed, which is unable to satisfy the demand of running at high speed of vehicle.If
Frame per second is reduced in order to pass image back in time, it will the description precision to barrier is further decreased, to be easy to cause
Safety accident.
Summary of the invention
The purpose of the present invention is in view of the drawbacks of the prior art, providing a kind of automatic Pilot control method, it is not only able to full
Precision required by sufficient automatic driving vehicle, and when vehicle needs scorch, without reducing frame per second, that is, collectable
Data are returned to processor in time.
In view of this, the embodiment of the invention provides a kind of automatic Pilot control methods, comprising:
The initial position message and target position information for obtaining vehicle generate automatic Pilot path in navigation map；
After starting driving according to the automatic Pilot path, judge that vehicle is according to the information that sensor on vehicle acquires
It is no to be in preset normal condition；
Obtain two sides obstacle distance data and front obstacle binocular vision data；
Judge vehicle two sides with the presence or absence of collision trend according to the two sides obstacle distance data；
3D modeling is carried out to front obstacle according to the front obstacle binocular vision data；
The headstock 3D model data obtained according to the front obstacle 3D model data of foundation and in advance calculates vehicle with before
The distance of square barrier；
Front obstacle is identified according to the front obstacle 3D model data；
Recognition result according to vehicle at a distance from front obstacle and to the front obstacle, determines risk of collision most
High level；
Judge whether the risk of collision peak is lower than preset threshold；
When vehicle is in normal condition, collision trend is not present in vehicle two sides and risk of collision peak is lower than preset threshold
When, continue to drive according to the automatic Pilot path.
It is preferably, described that automatic Pilot path is generated in navigation map, comprising:
According to the initial position message of vehicle, initial alignment of the vehicle in navigation map is obtained；
According to the target position information of vehicle, target positioning of the destination in navigation map is obtained；
It is positioned according to the initial alignment and target, automatic Pilot path is generated in navigation map.
Preferably, the method also includes:
Obtain the GPS positioning information of vehicle in driving；
Judge whether the GPS positioning information obtained matches with the automatic Pilot path；
When the GPS positioning information with the automatic Pilot route matching, vehicle are in normal condition, vehicle two sides are not deposited
When colliding trend and risk of collision peak and being lower than preset threshold, then continue to drive according to the automatic Pilot path.
It is preferably, described that 3D modeling is carried out to front obstacle according to front obstacle binocular vision data, comprising:
According to the vision data for the front obstacle that First look sensor obtains, First look sensor and front are calculated
The first distance of each vision collecting point on barrier；
According to the vision data for the front obstacle that the second visual sensor obtains, the second visual sensor and front are calculated
The second distance of each vision collecting point on barrier；
According to the first distance and the second distance, it is based on same 3D coordinate system, establishes the 3D mould of front obstacle
Type.
Preferably, the method also includes:
When vehicle two sides are more than preset threshold there are collision trend and/or with the risk of collision peak of front obstacle
When, then according to the two sides Robot Bar Movement Track, the front obstacle 3D model data and the traffic rules that obtain in advance
Information obtains evacuation driving path；
Continue to drive according to the evacuation driving path；
Believe when according to the two sides Robot Bar Movement Track, the front obstacle 3D model data and the traffic rules
When breath determines that vehicle meets default Parking condition, then stop driving, and alert.
Preferably, described to judge vehicle two sides with the presence or absence of collision trend, packet according to the two sides obstacle distance data
It includes:
The two sides obstacle distance data are handled, obtain two sides barrier respectively at a distance from vehicle, and, two sides obstacle
Motion profile, movement velocity and the acceleration of motion of object；
According to the motion profile, movement velocity, acceleration of motion and preset condition for determining collision trend, judgement
Vehicle two sides whether there is collision trend.
Preferably, the binocular vision sensor gathers front by being made of two visual sensors based on global shutter
Barrier binocular vision data.
The embodiment of the present invention provides a kind of automatic Pilot control method, and this method advises the Xilinx isomery of grade by meeting vehicle
It manages device to execute, realizes the real-time processing to the acquired data of various kinds of sensors on vehicle, and be with sensor existing on vehicle
Basis, the binocular vision data of the binocular vision sensor gathers front obstacle using at least one set based on global shutter, from
And 3D modeling is carried out to front obstacle according to binocular vision data, can not only obtain can clear, accurately preceding object
Object 3D model data, moreover it is possible to solve the problems, such as the low frame transmission of existing front camera.As it can be seen that this method is not only able to meet automatically
Drive precision required by vehicle, and when vehicle needs scorch, without reduce frame per second, that is, collectable data and
When be returned to processor.
Detailed description of the invention
Fig. 1 is a kind of automatic Pilot control method flow chart provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram of binocular vision sensor gathers front obstacle information provided in an embodiment of the present invention；
Fig. 3 be computation vision sensor provided in an embodiment of the present invention in front obstacle at a distance from vision collecting point
Schematic diagram.
Specific embodiment
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
The embodiment of the present invention provides a kind of automatic Pilot control method, and this method advises the Xilinx isomery of grade by meeting vehicle
It manages device to execute, realizes the real-time processing to the acquired data of various kinds of sensors on vehicle, and be with sensor existing on vehicle
Basis, the binocular vision data of the binocular vision sensor gathers front obstacle using at least one set based on global shutter, and
And 3D modeling is carried out to front obstacle according to binocular vision data, can not only obtain can clear, accurately preceding object
Object 3D model data, moreover it is possible to solve the problems, such as the low frame transmission of existing front camera.This method is not only able to meet automatic Pilot
Precision required by vehicle, and when vehicle needs scorch, in time without reduction frame per second, that is, collectable data
It is returned to processor.
It should be noted that above-mentioned Xilinx heterogeneous processor can be built in car-mounted computer, the car-mounted computer
It further include with communication function transceiver, for being communicated with sensor on vehicle.Device through this process, to thunderous on vehicle
It reaches, the information of the sensors acquisition such as binocular vision sensor is handled in real time, and then automatic according to processing result control vehicle
It drives.
According to the development of processor, the processor that can complete above-mentioned real-time processing data at present is mostly to be based on FPGA
The framework of (Field-Programmable Gate Array, i.e. field programmable gate array).This is because non-FPGA architecture
Treatment mechanism be essentially interrupt mechanism, system is counted by a clock counter, under general faster speed, can be counted within 1 second
Count to 5GHz i.e. 500,000,000 time.However, interrupting all is after sometime point triggering, down trigger, processor will refer to the counter
It goes to execute interrupt event, until completing the event.In contrast to this, the processor based on FPGA architecture can have multiple countings
Device reaches each event and corresponds to a counter, so that processor can go to handle multiple events simultaneously, processing speed is more
Fastly, real-time is higher.
Based on the above analysis, Xilinx (match Sentos) heterogeneous processor used in the embodiment of the present invention, by FPGA+ARM+
GPU etc. is constituted, at the same the advantages of possess the serial high speed of ARM, the high-speed floating point operation of GPU the advantages of and FPGA parallel computation
The advantages of, while also meeting vehicle rule grade requirement.
Fig. 1 is a kind of automatic Pilot control method flow chart provided in an embodiment of the present invention, as shown in Figure 1, this method can
To include:
Step 101, the initial position message and target position information for obtaining vehicle, generate automatic Pilot in navigation map
Path.
Automatic driving vehicle has GPS (Global Positioning System, global positioning system) Differential positioning system
System when GPS differential position system works, by communicating with GPS difference base station, obtains the GPS information of vehicle position.Here
Initial position message refer to automatic Pilot stroke initial position GPS information, target position information then refers to automatic Pilot
The GPS information of the destination locations of stroke.Wherein, target position information can be according to user in aforementioned GPS differential position system
The destination name acquiring of middle input obtains.For example, the user interface interaction that user and GPS differential position system provide, voice
Or text inputs destination information.
According to the initial position message and target position information of vehicle, automatic Pilot road can be generated in navigation map
Diameter.When specific implementation, first according to the initial position message of vehicle, initial alignment of the vehicle in navigation map is obtained；Then
According to the target position information of vehicle, target positioning of the destination in navigation map is obtained；Finally according to the initial alignment
It is positioned with target, automatic Pilot path is generated in navigation map.
After the initial alignment and target of vehicle, which position, to be determined, one or more optional automatic Pilot road can be formed
Diameter.When there are a plurality of optional automatic Pilot path, one can be therefrom selected as final according to preset screening conditions
Automatic Pilot path.For example, default driving time is screening conditions, the shortest path of driving time is selected as final oneself
Dynamic driving path.
Step 102, after starting driving according to the automatic Pilot path, sentenced according to the information that sensor on vehicle acquires
Whether disconnected vehicle is in preset normal condition.
There are multiple sensors, such as visual sensor, left back wheel sensor, reversing radar sense on automatic driving vehicle
Device, side radars sensor etc., for another example various inspections such as engine condition detector, IMU, GPS, wheel speed meter, oil meter and water-level gauge
Instrument is surveyed, these sensors will acquire the corresponding information of vehicle, such as the oil level of oil meter detection after vehicle starts driving in real time
The status datas such as the engine temperature of data, the waterlevel data of water-level gauge detection or the detection of engine condition detector.According to
The information that sensor acquires on vehicle may determine that whether vehicle is in normal condition.Wherein, normal condition is a default shape
State determines that vehicle is in normal condition when all data of vehicle meets the preset state, and otherwise, vehicle is in abnormal shape
State.
While executing step 102, step 103 is executed, two sides obstacle distance data is obtained and front obstacle is double
Mesh vision data.
Specifically, acquiring the distance of vehicle arranged on left and right sides barrier in real time by the radar sensor of vehicle arranged on left and right sides
Data, and real-time Transmission is to processor；Preceding object is acquired in real time by two visual sensors being arranged on vehicle headstock
Object binocular vision data, and real-time Transmission is to processor；Two visual sensors constitute structure binocular vision sensor.
It should be noted that the embodiment of the present invention passes through by two visions based on global shutter (global shutter)
The binocular vision sensor gathers front obstacle binocular vision data of sensor composition.
Visual sensor is all made of block of pixels (pix), and each block of pixels is a most basic photodiode,
There are two types of the size of one block of pixels is current, one is the pix of the 0.8um based on rolling shutter, another kind is to be based on
The pix of the 3.0um of global shutter.Since the visual sensor based on rolling shutter is being placed on locomotive
When photographs object, the object of shooting can be elongated, and need to carry out calibration repair process to it in the later period, therefore be based on
The visual sensor of rolling shutter needs additional data handling procedure, and the vision based on global shutter
Sensor does not need then.In addition, since the visual sensor based on global shutter can be realized ROI (region of
Interest, area-of-interest) it extracts, thus there is lesser volume of transmitted data, so that the low frame for solving other sensors passes
Defeated problem is particularly suitable for the scene of scorch.
Step 104, judge vehicle two sides with the presence or absence of collision trend according to the two sides obstacle distance data.
Specifically, handle the two sides obstacle distance data according to existing algorithm, obtain two sides barrier respectively with vehicle
Distance, and, motion profile, movement velocity and the acceleration of motion of two sides barrier.According to the motion profile, movement speed
Degree, acceleration of motion and the preset condition for determining collision trend judge vehicle two sides with the presence or absence of collision trend.
Step 105,3D modeling is carried out to front obstacle according to the front obstacle binocular vision data.
Front obstacle binocular vision data are acquired in real time by binocular vision sensor and are transferred to processor, binocular vision
Sensor includes First look sensor and the second visual sensor or the first camera and second camera.Fig. 2 is this hair
The schematic diagram for the binocular vision sensor gathers front obstacle information that bright embodiment provides, as shown in Fig. 2, each vision passes
Sensor can capture barrier multiple spot information with moment and much be higher by laser radar substantially between 10 ten thousand to million points and had
Some orders of magnitude.
When step 105 implements, the vision data of the front obstacle obtained first according to First look sensor, meter
Calculate the first distance of each vision collecting point in First look sensor and front obstacle；Also, according to the second visual sensing
The vision data for the front obstacle that device obtains calculates each vision collecting point in the second visual sensor and front obstacle
Second distance；Then according to the first distance and the second distance, it is based on same 3D coordinate system, establishes front obstacle
3D model.
Fig. 3 be computation vision sensor provided in an embodiment of the present invention in front obstacle at a distance from vision collecting point
Schematic diagram.As shown in figure 3, according to the arm of angle angle principle of triangle, it is known that the distance between the angle of b and c and two sensors,
The distance between vision collecting point and First look sensor can be calculated, while vision collecting point and can also be calculated
The distance between two visual sensors；In turn, the coordinate (x, y, z) of vision collecting point under different coordinates can be determined.It will barrier
Hinder the coordinate of each vision collecting point of object to calculate in this way, 3 of barrier under each visual sensor can be obtained
3 dimension module of barrier under two visual sensors is matched to the same coordinate system, the 3D mould of barrier can be obtained by dimension module
Type.
Step 106, the headstock 3D model data obtained according to the front obstacle 3D model data of foundation and in advance calculates
Vehicle is at a distance from front obstacle.
Based on the method that step 105 is recorded, headstock 3D model data is obtained in advance, headstock 3D model data here can be with
It is interpreted as the 3D model data on the common visual vehicle head of two visual sensors.
Front obstacle 3D model data and headstock 3D model data are calculated according to existing algorithm, available vehicle
At a distance from front obstacle.
Step 107, front obstacle is identified according to the front obstacle 3D model data.
It, can be by front obstacle 3D model data and pre-stored database number as a kind of possible implementation
According to aspect ratio pair is carried out, to identify to front obstacle, recognition result can be pedestrian, vehicle or bicycle etc..
Step 108, the recognition result according to vehicle at a distance from front obstacle and to the front obstacle, determination are touched
Hit risk peak.
It can be further calculated to obtain motion profile, the movement of front obstacle at a distance from front obstacle according to vehicle
The information such as speed calculate the peak of risk of collision according to existing algorithm, i.e., in conjunction with the recognition result to front obstacle
The worst situation.
Step 109, judge whether the risk of collision peak is lower than preset threshold.
Step 110, when vehicle is in normal condition, vehicle two sides there is no collision trend and risk of collision peak is lower than
When preset threshold, continue to drive according to the automatic Pilot path.
By the real time data processing process of step 102-109, when vehicle is in normal condition, vehicle two sides are not deposited for judgement
When colliding trend and risk of collision peak and being lower than preset threshold, then continue to be driven according to automatic Pilot path.
Conversely, then stopping driving, and alert when vehicle is when in an abnormal state.
In a further embodiment, when vehicle is in normal condition, there are collision trend, and/or and fronts for vehicle two sides
When the risk of collision peak of barrier is more than preset threshold, then hindered according to the two sides Robot Bar Movement Track, the front
The traffic rule information for hindering object 3D model data and obtaining in advance obtains evacuation driving path；According to the evacuation driving path
Continue to drive；
Meanwhile when according to the two sides Robot Bar Movement Track, the front obstacle 3D model data and the traffic
When Rule Information determines that vehicle meets default Parking condition, then stop driving, and alert.
In a further embodiment, provided in an embodiment of the present invention after starting driving according to the automatic Pilot path
Control method, further includes: obtain the GPS positioning information of vehicle in driving；The GPS positioning information that judgement obtains is driven automatically with described
Sail whether path matches.
Correspondingly, when the GPS positioning information and the automatic Pilot route matching, vehicle are in normal condition, vehicle
Then continue to drive according to the automatic Pilot path there is no collision trend and when risk of collision peak is lower than preset threshold in two sides
It sails.
The embodiment of the present invention provides a kind of automatic Pilot control method, and this method advises the Xilinx isomery of grade by meeting vehicle
It manages device to execute, realizes the real-time processing to the acquired data of various kinds of sensors on vehicle, and be with sensor existing on vehicle
Basis, the binocular vision data of the binocular vision sensor gathers front obstacle using at least one set based on global shutter, from
And 3D modeling is carried out to front obstacle according to binocular vision data, can not only obtain can clear, accurately preceding object
Object 3D model data, moreover it is possible to solve the problems, such as the low frame transmission of existing front camera.As it can be seen that this method is not only able to meet automatically
Drive precision required by vehicle, and when vehicle needs scorch, without reduce frame per second, that is, collectable data and
When be returned to processor.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (7)
1. a kind of automatic Pilot control method, which is characterized in that the described method includes:
The initial position message and target position information for obtaining vehicle generate automatic Pilot path in navigation map；
After starting driving according to the automatic Pilot path, judge whether vehicle is located according to the information that sensor on vehicle acquires
In preset normal condition；
Obtain two sides obstacle distance data and front obstacle binocular vision data；
Judge vehicle two sides with the presence or absence of collision trend according to the two sides obstacle distance data；
3D modeling is carried out to front obstacle according to the front obstacle binocular vision data；
The headstock 3D model data obtained according to the front obstacle 3D model data of foundation and in advance, calculates vehicle and front hinders
Hinder the distance of object；
Front obstacle is identified according to the front obstacle 3D model data；
Recognition result according to vehicle at a distance from front obstacle and to the front obstacle, determines risk of collision highest
Value；
Judge whether the risk of collision peak is lower than preset threshold；
When vehicle is in normal condition, vehicle two sides there is no collision trend and risk of collision peak is lower than preset threshold,
Continue to drive according to the automatic Pilot path.
2. automatic Pilot control method according to claim 1, which is characterized in that described to be generated automatically in navigation map
Driving path, comprising:
According to the initial position message of vehicle, initial alignment of the vehicle in navigation map is obtained；
According to the target position information of vehicle, target positioning of the destination in navigation map is obtained；
It is positioned according to the initial alignment and target, automatic Pilot path is generated in navigation map.
3. automatic Pilot control method according to claim 1, which is characterized in that the method also includes:
Obtain the GPS positioning information of vehicle in driving；
Judge whether the GPS positioning information obtained matches with the automatic Pilot path；
When the GPS positioning information is in normal condition with the automatic Pilot route matching, vehicle, there is no touch for vehicle two sides
When hitting trend and risk of collision peak lower than preset threshold, then continue to drive according to the automatic Pilot path.
4. automatic Pilot control method according to claim 1, which is characterized in that described according to front obstacle binocular vision
Feel that data carry out 3D modeling to front obstacle, comprising:
According to the vision data for the front obstacle that First look sensor obtains, First look sensor and preceding object are calculated
The first distance of each vision collecting point on object；
According to the vision data for the front obstacle that the second visual sensor obtains, the second visual sensor and preceding object are calculated
The second distance of each vision collecting point on object；
According to the first distance and the second distance, it is based on same 3D coordinate system, establishes the 3D model of front obstacle.
5. automatic Pilot control method according to claim 1, which is characterized in that the method also includes:
When vehicle two sides are more than preset threshold there are collision trend and/or with the risk of collision peak of front obstacle, then
According to the two sides Robot Bar Movement Track, the front obstacle 3D model data and the traffic rule information that obtains in advance,
Obtain evacuation driving path；
Continue to drive according to the evacuation driving path；
Sentence when according to the two sides Robot Bar Movement Track, the front obstacle 3D model data and the traffic rule information
When determining vehicle and meeting default Parking condition, then stop driving, and alert.
6. automatic Pilot control method according to claim 1, which is characterized in that it is described according to the two sides barrier away from
Judge vehicle two sides with the presence or absence of collision trend from data, comprising:
The two sides obstacle distance data are handled, obtain two sides barrier respectively at a distance from vehicle, and, two sides barrier
Motion profile, movement velocity and acceleration of motion；
According to the motion profile, movement velocity, acceleration of motion and preset condition for determining collision trend, vehicle is judged
Two sides whether there is collision trend.
7. automatic Pilot control method according to claim 1, which is characterized in that
Pass through the binocular vision sensor gathers front obstacle binocular being made of two visual sensors based on global shutter
Vision data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910672528.6A CN110262521A (en) | 2019-07-24 | 2019-07-24 | A kind of automatic Pilot control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910672528.6A CN110262521A (en) | 2019-07-24 | 2019-07-24 | A kind of automatic Pilot control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110262521A true CN110262521A (en) | 2019-09-20 |
Family
ID=67928103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910672528.6A Pending CN110262521A (en) | 2019-07-24 | 2019-07-24 | A kind of automatic Pilot control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110262521A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827578A (en) * | 2019-10-23 | 2020-02-21 | 江苏广宇协同科技发展研究院有限公司 | Vehicle anti-collision prompting method, device and system based on vehicle-road cooperation |
| CN111469836A (en) * | 2020-02-28 | 2020-07-31 | 广东中科臻恒信息技术有限公司 | Obstacle avoidance method and device based on vehicle-mounted unit and road side unit, and storage medium |
| CN111813116A (en) * | 2020-07-09 | 2020-10-23 | 海南发控智慧环境建设集团有限公司 | Obstacle avoidance auxiliary system based on three-dimensional model |
| CN113561992A (en) * | 2021-07-30 | 2021-10-29 | 广州文远知行科技有限公司 | Method, device, terminal device and medium for generating trajectory of automatic driving vehicle |
| CN113734120A (en) * | 2020-05-28 | 2021-12-03 | 比亚迪股份有限公司 | Vehicle control method and device and vehicle |
| CN113968216A (en) * | 2020-07-25 | 2022-01-25 | 华为技术有限公司 | Vehicle collision detection method and device and computer readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130128001A1 (en) * | 2011-11-18 | 2013-05-23 | Ganmei YOU | Method and system for detecting object on a road |
| CN103587524A (en) * | 2013-10-25 | 2014-02-19 | 江苏大学 | Lateral active collision avoidance system and control method thereof |
| CN104210488A (en) * | 2014-07-30 | 2014-12-17 | 浙江吉利控股集团有限公司 | Method and device for preventing vehicle from colliding with road edge |
| CN104943689A (en) * | 2015-06-03 | 2015-09-30 | 奇瑞汽车股份有限公司 | Control method for active automobile anti-collision system |
| CN205490841U (en) * | 2016-02-24 | 2016-08-17 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle and many meshes image module that uses thereof |
| CN106394555A (en) * | 2016-08-29 | 2017-02-15 | 无锡卓信信息科技股份有限公司 | Unmanned automobile obstacle avoidance system and method based on 3D camera |
| CN106926843A (en) * | 2017-03-17 | 2017-07-07 | 奇瑞汽车股份有限公司 | A kind of automatic Pilot control system and control method for electric automobile of going sightseeing |
| CN107487288A (en) * | 2016-10-17 | 2017-12-19 | 宝沃汽车（中国）有限公司 | A kind of vehicle and its driving safety system |
| CN109017786A (en) * | 2018-08-09 | 2018-12-18 | 北京智行者科技有限公司 | Vehicle obstacle-avoidance method |
| CN109374008A (en) * | 2018-11-21 | 2019-02-22 | 深动科技（北京）有限公司 | A kind of image capturing system and method based on three mesh cameras |
| CN109785428A (en) * | 2019-01-21 | 2019-05-21 | 苏州大学 | A kind of handheld three-dimensional method for reconstructing based on polymorphic constrained Kalman filter |
-
2019
- 2019-07-24 CN CN201910672528.6A patent/CN110262521A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130128001A1 (en) * | 2011-11-18 | 2013-05-23 | Ganmei YOU | Method and system for detecting object on a road |
| CN103587524A (en) * | 2013-10-25 | 2014-02-19 | 江苏大学 | Lateral active collision avoidance system and control method thereof |
| CN104210488A (en) * | 2014-07-30 | 2014-12-17 | 浙江吉利控股集团有限公司 | Method and device for preventing vehicle from colliding with road edge |
| CN104943689A (en) * | 2015-06-03 | 2015-09-30 | 奇瑞汽车股份有限公司 | Control method for active automobile anti-collision system |
| CN205490841U (en) * | 2016-02-24 | 2016-08-17 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle and many meshes image module that uses thereof |
| CN106394555A (en) * | 2016-08-29 | 2017-02-15 | 无锡卓信信息科技股份有限公司 | Unmanned automobile obstacle avoidance system and method based on 3D camera |
| CN107487288A (en) * | 2016-10-17 | 2017-12-19 | 宝沃汽车（中国）有限公司 | A kind of vehicle and its driving safety system |
| CN106926843A (en) * | 2017-03-17 | 2017-07-07 | 奇瑞汽车股份有限公司 | A kind of automatic Pilot control system and control method for electric automobile of going sightseeing |
| CN109017786A (en) * | 2018-08-09 | 2018-12-18 | 北京智行者科技有限公司 | Vehicle obstacle-avoidance method |
| CN109374008A (en) * | 2018-11-21 | 2019-02-22 | 深动科技（北京）有限公司 | A kind of image capturing system and method based on three mesh cameras |
| CN109785428A (en) * | 2019-01-21 | 2019-05-21 | 苏州大学 | A kind of handheld three-dimensional method for reconstructing based on polymorphic constrained Kalman filter |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827578A (en) * | 2019-10-23 | 2020-02-21 | 江苏广宇协同科技发展研究院有限公司 | Vehicle anti-collision prompting method, device and system based on vehicle-road cooperation |
| CN110827578B (en) * | 2019-10-23 | 2022-05-10 | 江苏广宇协同科技发展研究院有限公司 | Vehicle anti-collision prompting method, device and system based on vehicle-road cooperation |
| CN111469836A (en) * | 2020-02-28 | 2020-07-31 | 广东中科臻恒信息技术有限公司 | Obstacle avoidance method and device based on vehicle-mounted unit and road side unit, and storage medium |
| CN113734120A (en) * | 2020-05-28 | 2021-12-03 | 比亚迪股份有限公司 | Vehicle control method and device and vehicle |
| CN111813116A (en) * | 2020-07-09 | 2020-10-23 | 海南发控智慧环境建设集团有限公司 | Obstacle avoidance auxiliary system based on three-dimensional model |
| CN113968216A (en) * | 2020-07-25 | 2022-01-25 | 华为技术有限公司 | Vehicle collision detection method and device and computer readable storage medium |
| CN113968216B (en) * | 2020-07-25 | 2023-11-17 | 华为技术有限公司 | Vehicle collision detection method and device and computer readable storage medium |
| CN113561992A (en) * | 2021-07-30 | 2021-10-29 | 广州文远知行科技有限公司 | Method, device, terminal device and medium for generating trajectory of automatic driving vehicle |
| CN113561992B (en) * | 2021-07-30 | 2023-10-20 | 广州文远知行科技有限公司 | Automatic driving vehicle track generation method, device, terminal equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262521A (en) | A kind of automatic Pilot control method | |
| US11834040B2 (en) | Recognition and prediction of lane constraints and construction areas in navigation | |
| CN110001658B (en) | Path prediction for vehicles | |
| CN112154455B (en) | Data processing method, equipment and movable platform | |
| EP2372308B1 (en) | Image processing system and vehicle control system | |
| EP2372309B1 (en) | Vehicle position detection system | |
| JP2018152056A (en) | Risk-based driver assistance for approaching intersections with limited visibility | |
| CN110103967A (en) | A kind of automatic lane change method of vehicle and vehicle control system, vehicle | |
| JP6834704B2 (en) | Driving support device and computer program | |
| CN106485233A (en) | Drivable region detection method, device and electronic equipment | |
| CN107563256A (en) | Aid in driving information production method and device, DAS (Driver Assistant System) | |
| CN107444406A (en) | Vehicle DAS (Driver Assistant System) and method | |
| CN111595357B (en) | Visual interface display method and device, electronic equipment and storage medium | |
| CN111986128A (en) | Off-center image fusion | |
| CN103748622A (en) | Driving assistance device | |
| CN116529783A (en) | System and method for intelligent selection of data for building machine learning models | |
| JP6520740B2 (en) | Object detection method, object detection device, and program | |
| WO2020029706A1 (en) | Dummy lane line elimination method and apparatus | |
| CN116710976A (en) | Autonomous vehicle system for intelligent on-board selection of data for training a remote machine learning model | |
| EP3690396A1 (en) | Method and device for providing advanced pedestrian assistance system to protect pedestrian distracted by their smartphone | |
| CN107408338A (en) | Driver assistance system | |
| CN112560567A (en) | Vehicle risk identification and avoidance | |
| CN111968376A (en) | Road condition prompting method and device, electronic equipment and storage medium | |
| KR101568745B1 (en) | Vehicle assistant apparatus and method based on infrared images | |
| EP4281345A1 (en) | Apparatus and method for assisting an autonomous vehicle and/or a driver of a vehicle |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant after: Beijing Idriverplus Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant before: Beijing Idriverplus Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |