CN106644503A - Intelligent vehicle planning capacity testing platform - Google Patents
Intelligent vehicle planning capacity testing platform Download PDFInfo
- Publication number
- CN106644503A CN106644503A CN201610939638.0A CN201610939638A CN106644503A CN 106644503 A CN106644503 A CN 106644503A CN 201610939638 A CN201610939638 A CN 201610939638A CN 106644503 A CN106644503 A CN 106644503A
- Authority
- CN
- China
- Prior art keywords
- intelligent vehicle
- planning
- test
- test system
- path
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C25/00—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass
Abstract
The invention discloses an intelligent vehicle planning capacity testing platform, which comprises a disk, a planning capacity testing system and an intelligent vehicle to be tested, and is characterized in that the disk is used for storing sample data, task files, reference answers, scoring rules and test results; the planning capacity testing system is a software system which performs a test on the planning capacity of the intelligent vehicle, and is mainly composed by the following three parts: a test question database, test process visualization and a test result and quantitative evaluation method; and the intelligent vehicle to be tested comprises a planning and decision-making unit, a control unit and a vehicle-mounted execution mechanism, and the intelligent vehicle to be tested performs communication with the planning capacity testing system through a network interface. The vehicle-environment closed-loop system based semi-physical simulation testing platform provided by the invention enables the planning capacity of an intelligent vehicle to be tested safely and effectively in a controllable space with experiment conditions being variable and easy to repeat at a relatively moderate cost.
Description
Technical field
The present invention relates to intelligent vehicle analysis test evaluation technical field, more particularly to a kind of planning aptitude tests of intelligent vehicle are put down
Platform.
Background technology
Unmanned intelligent vehicle, integrates the functions such as environment sensing, decision rule and control, is the heat of recent research
Point.Decision rule system is most important part in intelligent vehicle, when its algorithm performance directly determines that intelligent vehicle is travelled
Safety and reliability.In order to build the reliable planning system of performance, need sufficiently to test it in development process,
With various design defect present in exposure system.Conventional real train test is difficult to meet intelligent vehicle autonomous driving proficiency testing
Demand, first, the safety problem of intelligent vehicle is not also effectively verified;Secondly, the road needed for intelligent vehicle test
Condition is higher, the cost for needing input higher.Find a kind of repeatable, efficient and safe method of testing be it is current in the urgent need to
The problem of solution.
The content of the invention
The object of the invention is exactly to make up the defect of prior art, there is provided a kind of survey that ability is planned for intelligent vehicle
Examination platform and its evaluation method, for the analysis of intelligent vehicle planning system, design and checking a kind of important thinking and method are provided.
The present invention is achieved by the following technical solutions:
A kind of intelligent vehicle plans aptitude tests platform, including disk, planning capacity test system and intelligent vehicle to be measured.
Described disk is used for stored samples data, assignment file, Key for Reference, code of points, test result.
Described planning capacity test system is the software systems tested for the planning ability of intelligent vehicle, mainly
It is made up of three parts:Test examination question exam pool, test process visual Simulation, test result and method for quantitatively evaluating;
Described intelligent vehicle to be measured includes programmed decision-making unit, control unit, vehicle body hanger and vehicle-mounted executing agency.Treat
It is the test object for planning capacity test system to survey intelligent vehicle, is communicated by network interface between the two.
The described sample data being stored in disk, is the grating map for planning aptitude tests, can pass through two kinds of sides
Formula is obtained.First, in advance by sensory perceptual system, the contextual data that such as camera, radar sensor are obtained and the planning for changing into
Map, i.e. grating map;Second, in a test system, tester can voluntarily draw grating map according to testing requirement.
Described grating map is test system for path planning test for simulated scenario environment one kind two-dimensionally
Figure.With the lower right corner as the origin of coordinates, the coordinate of each grid is expressed as (x to grating mapn,yn), its property value -2, dynamic disorder
Thing;- 1, static-obstacle thing;0, can traffic areas;1, the path planning not driven to;2, the path planning for having run over;3, it is quick
Sensillary area domain.The wherein planning in path is carried out in non-barrier region.Identified not with different marks in grating map simultaneously
Same object, the such as starting point of path planning, terminal, task point and intelligent vehicle model.
Described planning map is divided into three kinds:Sector planning map, Global motion planning map and Dynamic Programming map.Advise local
It is 500px × 500px to draw map size, with the actual scene environment of certain proportion correspondence, such as actual scene be 100m ×
100m, then each 1px × 1px cell represents the scene in 1m × 1m regions.Global motion planning map is multiple sector planning ground
Figure is spliced, i.e., larger range of scene environment, according to the real-time Regeneration planning map of traveling-position of intelligent vehicle.Dynamic
Planning map is that test system dynamically adds barrier on the basis of sector planning map or Global motion planning map, specifically
Ground, when intelligent vehicle model driving is to a certain sensitizing range, test system is on the basis of initial planning path in specified position
Put the corresponding barrier of addition.Described sensitizing range is grating map to be set in initialization, itself and addition barrier
Position be one-to-one, that is, determine a certain sensitizing range HotArean:{(xa1,ya1),(xa2,ya2) ..., (xan,
yan), the region DynamicObstacle of its corresponding addition barriern:{(xb1, yb1), (xb2, yb2) ..., (xbn, ybn)}
Also determine that simultaneously.
Described intelligent vehicle model, is true intelligent vehicle to be measured dummy model in a test system, dynamically instead
The transport condition of intelligent vehicle to be measured is reflected, its attribute has:The information of position, speed, course and barrier all around.
Described test examination question exam pool, according to three kinds of different types of grating map local, global and dynamic three can be divided into
Plant different types of planning aptitude tests.
Described sector planning aptitude tests are to be based on single frames local grid map M, must Jing point NESS={ (xs,ys),
(xg,yg), (xs,ys) and (xg,yg) Origin And Destination is respectively, sector planning returns the path P={ (x of plannings,ys),(x1,
y1),(x2,y2),...,(xn,yn),(xg,yg), (xn,yn) be the cell for successively passing through coordinate.
Described Global motion planning aptitude tests are global grating map M, must Jing point NESS={ (xs,ys),(xt1,yt1),
(xt2,yt2),...,(xtn,ytn),(xg,yg), (xs,ys) and (xg,yg) Origin And Destination is respectively, (xt1,yt1),(xt2,
yt2),...,(xtn,ytn) be must Jing task point, it is desirable to Global motion planning return path P={ (xs,ys),(x1,y1),(x2,
y2),...,(xn,yn),(xg,yg) must sequentially pass through these task points, i.e.,(xn,yn) it is the cell for successively passing through
Coordinate.
Described Dynamic Programming aptitude tests be intelligent vehicle during locally or globally planning ability is carried out, work as intelligence
Can vehicle when driving to a certain sensitizing range of grating map, test system according to initial planning path grating map specific bit
Put and dynamically add barrier, according to test assignment, may have two kinds of path plannings A and B by starting point S to terminal E, when test system
When system detects intelligent vehicle model driving to sensitizing range A, add dynamic barrier A on grating map immediately, by unit
Lattice property value makes (x inton,yn)=- 2, cancels afterwards the setting of sensitizing range A and sensitizing range B associated with it, by cell
Property value makes (x inton,yn)=0.For the incidence relation of so-called sensitizing range is for its corresponding dynamic barrier, it is exactly
Say that with the addition of the corresponding dynamic barrier A in sensitizing range cannot add the corresponding dynamic barrier B of sensitizing range B, with the addition of
Dynamic barrier B cannot add dynamic barrier A, otherwise just can not path to terminal E from starting point S.At the same time, survey
Grating map change information is passed through network signals intelligent vehicle to be measured by test system so as to change path planning in time, to reach
The weight-normality to scene transition for detecting intelligent vehicle to be measured in real time draws ability.
Described test process visualization formulation, it is characterised in that test system feeds back according to intelligent vehicle to be measured
Information is on grating map using its motion state of intelligent vehicle model Dynamic Announce and track.Test system will test examination question letter
Breath, including original grating map and test assignment etc. be sent to intelligent vehicle to be measured by network, vehicle to be measured cooks up traveling
Path, further controls the vehicle executing agency output actions such as steering column, throttle, braking, gear.Meanwhile, these are performed
The action message of mechanism periodically feeds back to test system, and test system is according to the information such as speed, the course fed back, control intelligence
Auto model carries out corresponding synchronization action.During Dynamic Programming aptitude tests, test system is being continuously updated intelligent vehicle
While the position of model and movement locus, the obstacle information to adding is continuously updated, and dynamically shows to be measured
The result that the path planning of intelligent vehicle is drawn with weight-normality, reaches the effect of visualization of motion process.
Described test result and evaluation method, be test system when intelligent vehicle to be measured completes test assignment, for
The path planning of submission and other test datas are analyzed and evaluated, and are scored for its reasonability and optimality.Give below
Some specific quantitatively evaluating indexs are gone out:
A) path
B) task situation is completed
By testing the motion planning path of vehicle whether in assignment file starting point, terminal and task point etc., come
Judge whether to complete planning tasks success,
C) risk of collision (Risk, R) in path
Whether met less than most with the minimum distance of peripheral obstacle by per in the motion planning path for calculating vehicle
Little collision distance judging path with the presence or absence of risk,
D) time-consuming T is planned
T=TE-TS (4)
TSIt is designated as the test assignment data time that intelligent vehicle to be measured receives test system, TEIt is designated as intelligent vehicle to be measured
Test assignment is completed, to test system the time that task completes to mark is sent.
Described several evaluation indexes, it is as follows that PTS computational methods are often inscribed in (weight) planning in path:
wiRepresent the weight of every kind of test index, SiRepresent the score of every kind of test index.
Described intelligent vehicle to be measured is to collect network communication interface, decision making function module, control function module to hold with vehicle-mounted
Row structure is in the unmanned intelligent vehicle of one.Intelligent vehicle is received after test assignment, is held with control module control by decision-making
Row mechanism response action, while the motion change result for detecting fed back to into test system, test system is by its dynamic change
On intelligent vehicle model of the process reaction in virtual scene.Intelligent vehicle to be measured is placed on test-bed in process of the test,
Wheel is rolled on rotary drum, carry out simulated automotive and travel on road, during motion, the position of car body itself does not have
Change.Thus meet and complete various testing experiments in relatively narrow and small lab space.
It is an advantage of the invention that:The semi-physical simulation test platform based on " car-environment " closed-loop system that the present invention is provided,
That has abandoned that unmanned vehicle tested in the middle of actual environment is a variety of limited so that intelligent vehicle can be controlled, real at one
The condition of testing be easy to repeat it is variable, ability is safely and effectively surveyed to be planned to it with a relatively appropriate cost and space
Examination;
Present invention eliminates vehicle-mounted hardware sense part separately wins the probabilistic interference for taking environmental data, by means of real ring
Real test scene and sensing data in border, so more pointedly only examine to the planning ability of intelligent vehicle
Survey.Test system is dynamically become to scene environment directly using the grating map data for having changed storage in disk
More, so it is satisfied with the repeatability of test environment and the requirement of polytropy;
The present invention visualizes the motion state of intelligent vehicle in test process in test system, in virtual simulation environment
In, real-time dynamicly more intuitively monitor the motion change situation of intelligent vehicle;
A kind of method that the present invention proposes analysis and assessment for the planning ability of intelligent vehicle, from overall performance,
The comprehensive more efficient planning ability for assessing intelligent vehicle exactly.
Description of the drawings
Fig. 1 is that intelligent vehicle plans capacity test system general frame figure.
Fig. 2 is cell attribute information in grating map.
Fig. 3 is the set-up mode of dynamic barrier and sensitizing range in grating map.
Fig. 4 (a) is the design flow diagram of Dynamic Programming aptitude tests;Fig. 4 (b) adds the determination flow chart of barrier.
Fig. 5 is the driving path of T moment intelligent vehicle preliminary planning to be measured.
Fig. 6 is the driving path that the T+n moment adds that intelligent vehicle weight-normality to be measured is drawn after dynamic barrier.
Specific embodiment
A kind of intelligent vehicle plans aptitude tests platform, including disk, planning capacity test system and intelligent vehicle to be measured.
Described disk is used for stored samples data, assignment file, Key for Reference, code of points, test result.
Described planning capacity test system is the software systems tested for the planning ability of intelligent vehicle, mainly
It is made up of three parts:Test examination question exam pool, test process visual Simulation, test result and method for quantitatively evaluating;
As shown in figure 1, described intelligent vehicle to be measured includes programmed decision-making unit, control unit, vehicle body hanger and vehicle-mounted
Executing agency.Intelligent vehicle to be measured is the test object for planning capacity test system, is communicated by network interface between the two.
The described sample data being stored in disk, is the grating map for planning aptitude tests, can pass through two kinds of sides
Formula is obtained.First, in advance by sensory perceptual system, the contextual data that such as camera, radar sensor are obtained and the planning for changing into
Map, i.e. grating map;Second, in a test system, tester can voluntarily draw grating map according to testing requirement.
Described grating map is test system for path planning test for simulated scenario environment one kind two-dimensionally
Figure.With the lower right corner as the origin of coordinates, the coordinate of each grid is expressed as (x to grating mapn,yn), its property value is as shown in Figure 2:-
2, dynamic barrier;- 1, static-obstacle thing;0, can traffic areas;1, the path planning not driven to;2, the planning for having run over
Path;3, sensitizing range.The wherein planning in path is carried out in non-barrier region.Simultaneously with different marks in grating map
To identify different objects, the such as starting point of path planning, terminal, task point and intelligent vehicle model.
Described planning map is divided into three kinds:Sector planning map, Global motion planning map and Dynamic Programming map.Advise local
It is 500px × 500px to draw map size, with the actual scene environment of certain proportion correspondence, such as actual scene be 100m ×
100m, then each 1px × 1px cell represents the scene in 1m × 1m regions.Global motion planning map is multiple sector planning ground
Figure is spliced, i.e., larger range of scene environment, according to the real-time Regeneration planning map of traveling-position of intelligent vehicle.Dynamic
Planning map is that test system dynamically adds barrier on the basis of sector planning map or Global motion planning map, specifically
Ground, when intelligent vehicle model driving is to a certain sensitizing range, test system is on the basis of initial planning path in specified position
Put the corresponding barrier of addition.Described sensitizing range is grating map to be set in initialization, itself and addition barrier
Position be one-to-one, shown in such as Fig. 4 (b), that is, determine a certain sensitizing range HotArean:{(xa1,ya1),(xa2,
ya2) ..., (xan,yan), the region DynamicObstacle of its corresponding addition barriern:{(xb1, yb1), (xb2,
yb2) ..., (xbn, ybn) while also determining that.
Described intelligent vehicle model, is true intelligent vehicle to be measured dummy model in a test system, dynamically instead
The transport condition of intelligent vehicle to be measured is reflected, its attribute has:The information of position, speed, course and barrier all around, such as schemes
Shown in 2.
Described test examination question exam pool, according to three kinds of different types of grating map local, global and dynamic three can be divided into
Plant different types of planning aptitude tests.
Described sector planning aptitude tests are to be based on single frames local grid map M, must Jing point NESS={ (xs,ys),
(xg,yg), (xs,ys) and (xg,yg) Origin And Destination is respectively, sector planning returns the path P={ (x of plannings,ys),(x1,
y1),(x2,y2),...,(xn,yn),(xg,yg), (xn,yn) be the cell for successively passing through coordinate.
Described Global motion planning aptitude tests are global grating map M, must Jing point NESS={ (xs,ys),(xt1,yt1),
(xt2,yt2),...,(xtn,ytn),(xg,yg), (xs,ys) and (xg,yg) Origin And Destination is respectively, (xt1,yt1),(xt2,
yt2),...,(xtn,ytn) be must Jing task point, it is desirable to Global motion planning return path P={ (xs,ys),(x1,y1),(x2,
y2),...,(xn,yn),(xg,yg) must sequentially pass through these task points, i.e.,(xn,yn) it is the cell for successively passing through
Coordinate.
Described Dynamic Programming aptitude tests be intelligent vehicle during locally or globally planning ability is carried out, work as intelligence
Can vehicle when driving to a certain sensitizing range of grating map, test system according to initial planning path grating map specific bit
Put and dynamically add barrier.As shown in figure 3, according to test assignment, by starting point S to terminal E may have two kinds of path planning A and
B, when test system detects intelligent vehicle model driving to sensitizing range A, adds dynamic disorder on grating map immediately
Thing A, makes cell property value into (xn,yn)=- 2, cancels afterwards setting for sensitizing range A and sensitizing range B associated with it
Put, make cell property value into (xn,yn)=0.The incidence relation of so-called sensitizing range is for its corresponding dynamic barrier
For, that is with the addition of the corresponding dynamic barrier A in sensitizing range cannot add the corresponding dynamic disorders of sensitizing range B
Thing B, with the addition of dynamic barrier B cannot add dynamic barrier A, otherwise just can not path to terminal E from starting point S.
At the same time, grating map change information is passed through network signals intelligent vehicle to be measured by test system so as to change planning in time
Path, to reach the weight-normality to scene transition for detecting intelligent vehicle to be measured in real time ability is drawn.Fig. 4 (a) is Dynamic Programming energy
The design flow diagram of power test.
Described test process visualization formulation, it is characterised in that test system feeds back according to intelligent vehicle to be measured
Information is on grating map using its motion state of intelligent vehicle model Dynamic Announce and track.Test system will test examination question letter
Breath, including original grating map and test assignment etc. be sent to intelligent vehicle to be measured by network, vehicle to be measured cooks up traveling
Path, further controls the vehicle executing agency output actions such as steering column, throttle, braking, gear.Meanwhile, these are performed
The action message of mechanism periodically feeds back to test system, and test system controls intelligence according to information such as speed, the courses fed back
Energy auto model carries out corresponding synchronization action.During Dynamic Programming aptitude tests, test system is being continuously updated intelligence
While the position of auto model and movement locus, the obstacle information to adding is continuously updated, and dynamically shows and treats
The result that the path planning of intelligent vehicle is drawn with weight-normality is surveyed, the effect of visualization of motion process is reached.
Described test result and evaluation method, be test system when intelligent vehicle to be measured completes test assignment, for
The path planning of submission and other test datas are analyzed and evaluated, and are scored for its reasonability and optimality.Give below
Some specific quantitatively evaluating indexs are gone out:
E) path
F) task situation is completed
By testing the motion planning path of vehicle whether in assignment file starting point, terminal and task point etc., come
Judge whether to complete planning tasks success,
G) risk of collision (Risk, R) in path
Whether met less than most with the minimum distance of peripheral obstacle by per in the motion planning path for calculating vehicle
Little collision distance judging path with the presence or absence of risk,
H) time-consuming T is planned
T=TE-TS (9)
TSIt is designated as the test assignment data time that intelligent vehicle to be measured receives test system, TEIt is designated as intelligent vehicle to be measured
Test assignment is completed, to test system the time that task completes to mark is sent.
Described several evaluation indexes, it is as follows that PTS computational methods are often inscribed in (weight) planning in path:
wiRepresent the weight of every kind of test index, SiRepresent the score of every kind of test index.
Described intelligent vehicle to be measured is to collect network communication interface, decision making function module, control function module to hold with vehicle-mounted
Row structure is in the unmanned intelligent vehicle of one.Intelligent vehicle is received after test assignment, is held with control module control by decision-making
Row mechanism response action, while the motion change result for detecting fed back to into test system, test system is by its dynamic change
On intelligent vehicle model of the process reaction in virtual scene.Intelligent vehicle to be measured is placed on test-bed in process of the test,
Wheel is rolled on rotary drum, carry out simulated automotive and travel on road, during motion, the position of car body itself does not have
Change.Thus meet and complete various testing experiments in relatively narrow and small lab space.
Step 1, intelligent vehicle to be measured is travelled to test-bed.To plan capacity test system as server, with to be measured
Intelligent vehicle is to take ICP/IP protocol to be communicated between the two in client, LAN.
Step 2, selects test examination question, test system that the grating map of the test question is read from disk according to examination question, and
Display starting point, task point, the positional information of terminal are carried out in visual Simulation module.
Step 3, builds virtual test auto model, as shown in Fig. 2 its attribute has:Position (xn,yn), speed v, course ω
And cell attribute information all around, in adding it to the grating map in previous step, initial position rising for task
Point, remains static.Test system opens more new thread, receives the status information from true intelligent vehicle output to be measured,
Dynamically reflect its driving path and motion state.
Step 4, test system is opened and sends thread, and grating map and mission bit stream are sent to into intelligence to be measured by network
Vehicle.Now timing is TSMoment.
Step 5, intelligent vehicle to be measured is entered by itself programmed decision-making unit to the test assignment that test system is sended over
Row analysis, draws the path from original position S to final position E, if having if task point, path must sequentially pass through in order appoints
Business point.
Path planning result is sent to test system by step 6, intelligent vehicle to be measured by network.
Step 7, the program results that test system is sended over according to intelligent vehicle to be measured marks one in grating map
Bar path planning, i.e. (xn,yn)=1, as shown in Figure 5.During ensuing intelligent vehicle is advanced, position is travelled according to it
Put, update the position of intelligent vehicle model, and the path that path planning is labeled as having driven to, i.e. (xn,yn)=2, such as Fig. 6
It is shown.
Step 8, intelligent vehicle to be measured is by own control systems according to path planning to steering, throttle, braking and gearshift
Control command is sent etc. vehicle-mounted executing agency.Car body is while rotary drum stage motion, and the transmission thread of intelligent vehicle to be measured is every
Every the t times by the status information feedback of executing agency to test system.
Step 9, test system according to return come executing agency information, according to displacement S and orientation ω come not
The disconnected position for updating auto model in simulated environment.Wherein displacement is calculated:
Wherein VnowFor the velocity amplitude that current time return comes, VpreFor the velocity amplitude that previous moment return comes, take both
Average speed, t is the time interval for receiving the two speed.
Wherein orientation ω is 360 ° of directions centered on auto model, as shown in Figure 2.
Step 10, the newly-built queue of test system during intelligent vehicle model sport, records its traveling process Jing
The point crossed, i.e. (xn,ynThe coordinate of)=2.
Step 11, during Dynamic Programming aptitude tests, test system during the traveling of intelligent vehicle model,
Constantly judge whether paths traversed is sensitizing range, i.e. (xn,yn)=3.Once sensitizing range is entered into, test system
Send to intelligent vehicle to be measured immediately and slow down or halt instruction, while the specified location addition dynamic disorder in grating map
Thing, will its cell property value (xn,ynMake (x in)=1n,yn)=-, 2 and is updated in visualization view.
Step 12, test system completes to add after dynamic barrier, cancels the sensitizing range and sensitizing range associated with it
The setting in domain, i.e. cell property value (xn,ynMake (x in)=3n,yn)=0, notes the driving path recorded in step 10 queue
Cell attribute it is constant.Meanwhile, the grating map information after renewal is sent to intelligent vehicle to be measured by test system.
Step 13, intelligent vehicle to be measured is received after the information of grating map renewal, is confirmed the dynamic barrier of addition and is
Whether the no driving path to initial planning has an impact, if having an impact, decision package cooks up one with current location as starting point, again
Bar and sends back to test system to the optimal path of terminal.
Step 14, test system Regeneration planning path, as shown in Figure 6.Step 7 is returned to until reaching terminal.
Step 15, after test vehicle is reached home, to test system task completion signal is sent.
Step 16, test system receives task completion signal, and now timing is TEMoment.
Step 17, to previous step, intelligent vehicle to be measured completes a test examination question.Test system is tied to this test
Fruit is analyzed and evaluation, and step is as follows:
Step 1001, according to formula (1), by the coordinate of the passing point preserved in queue in step 10, draws vehicle movement
Geometric locus, obtains the total length of path planning.
Whether step 1002, according to formula (2), all through starting point, terminal and appointed by testing vehicle path curves
It is engaged in point to judge the performance of test assignment.
Step 1003, according to formula (3), by calculating and the minimum of periphery barrier at per of vehicle movement geometric locus
Whether distance is less than minimum collision distance to judge the risk of collision coefficient of path planning.
Step 1004, according to formula (4), the time value recorded by step 4 and step 16, calculates this subtask and completes institute
The time of consumption.
Step 1005, the result drawn by above-mentioned 4 steps, with reference to the different weighted values that each distributes, according to formula (5)
Calculate the overall assessment fraction of this test examination question.
Step 18, the above-mentioned intelligent detecting and evaluating algorithms to test result are automatically performed in test system by software, its
Fraction completes to be displayed on test system interface after testing examination question, for tester's reference.
Claims (10)
1. a kind of intelligent vehicle plans aptitude tests platform, it is characterised in that:Include disk, planning capacity test system and treat
Survey intelligent vehicle;
Described disk is used for stored samples data, assignment file, Key for Reference, code of points and test result;
Described planning capacity test system is the software systems tested for the planning ability of intelligent vehicle, by three portions
Divide and constitute:Test examination question exam pool, test process visualization and test result and method for quantitatively evaluating;
Described intelligent vehicle to be measured includes programmed decision-making unit, control unit and vehicle-mounted executing agency, and intelligent vehicle to be measured is
The test object of planning capacity test system, is led between intelligent vehicle to be measured and planning capacity test system by network interface
Letter.
2. a kind of intelligent vehicle according to claim 1 plans aptitude tests platform, it is characterised in that:Described is stored in
Sample data in disk, is the grating map for planning aptitude tests, can be obtained by two ways:First, logical in advance
The planning map crossed the contextual data of sensory perceptual system acquisition and change into;Second, in a test system, tester is according to test
Demand can voluntarily draw grating map.
3. a kind of intelligent vehicle according to claim 2 plans aptitude tests platform, it is characterised in that:Described grid ground
Figure, is that test system is directed to a kind of two-dimensional map of the path planning test for simulated scenario environment, and grating map is with the lower right corner
For the origin of coordinates, the coordinate of each grid is expressed as (xn,yn), its property value is:- 2, dynamic barrier;- 1, static-obstacle thing;
0, can traffic areas;1, the path planning not driven to;2, the path planning for having run over;3, sensitizing range, wherein path
Planning is carried out in non-barrier region, while identifying different objects in grating map with different marks.
4. a kind of intelligent vehicle according to claim 2 plans aptitude tests platform, it is characterised in that:Described planning ground
Figure is divided into three kinds:Sector planning map, Global motion planning map and Dynamic Programming map;Sector planning map size be 500px ×
500px, with the actual scene environment of certain proportion correspondence;Global motion planning map is that multiple sector planning maps are spliced, i.e.,
Larger range of scene environment, according to the real-time Regeneration planning map of traveling-position of intelligent vehicle;Dynamic Programming map is to survey
Test system dynamically adds barrier on the basis of sector planning map or Global motion planning map, when intelligent vehicle model row
When sailing to a certain sensitizing range, test system adds corresponding barrier on the basis of initial planning path in specified position,
Described sensitizing range is grating map to be set in initialization, its be with the position of addition barrier it is one-to-one,
Determine a certain sensitizing range HotArean:{(xa1,ya1),(xa2,ya2) ..., (xan,yan), its corresponding addition barrier
Region DynamicObstaclen:{(xb1,yb1),(xb2,yb2) ..., (xbn,ybn) while also determining that.
5. a kind of intelligent vehicle according to claim 4 plans aptitude tests platform, it is characterised in that:Described intelligent vehicle
Model, is true intelligent vehicle to be measured dummy model in a test system, dynamically reflects the traveling of intelligent vehicle to be measured
State, its attribute has:The information of position, speed, course and barrier all around.
6. a kind of intelligent vehicle according to claim 1 plans aptitude tests platform, it is characterised in that:Described test examination
Topic exam pool, according to three kinds of different types of grating map local, global and dynamic three kinds of different types of planning abilities can be divided into
Test;
Sector planning aptitude tests are to be based on single frames local grid map M, must Jing point NESS={ (xs,ys),(xg,yg), (xs,
ys) and (xg,yg) Origin And Destination is respectively, sector planning returns the path P={ (x of plannings,ys),(x1,y1),(x2,
y2),...,(xn,yn),(xg,yg), (xn,yn) be the cell for successively passing through coordinate;
Global motion planning aptitude tests are global grating map M, must Jing point NESS={ (xs,ys),(xt1,yt1),(xt2,yt2),...,
(xtn,ytn),(xg,yg), (xs,ys) and (xg,yg) Origin And Destination is respectively, (xt1,yt1),(xt2,yt2),...,(xtn,
ytn) be must Jing task point, it is desirable to Global motion planning return path P={ (xs,ys),(x1,y1),(x2,y2),...,(xn,
yn),(xg,yg) must sequentially pass through these task points, i.e.,(xn,yn) it is the cell for successively passing through
Coordinate;
Dynamic Programming aptitude tests be intelligent vehicle during locally or globally planning ability is carried out, when intelligent vehicle traveling
To grating map a certain sensitizing range when, specified location of the test system according to initial planning path in grating map dynamically adds
Plus barrier, according to test assignment, may there are two kinds of path plannings A and B by starting point S to terminal E, when test system detects intelligence
When energy auto model drives to sensitizing range A, add dynamic barrier A on grating map immediately, cell property value is changed
Into (xn,yn)=- 2, cancels afterwards the setting of sensitizing range A and sensitizing range B associated with it, by cell property value (xn,
ynMake (x in)=3n,yn)=0;The incidence relation of described sensitizing range is to the addition of the corresponding dynamic barriers of sensitizing range A
A cannot add the corresponding dynamic barrier B of sensitizing range B, and with the addition of dynamic barrier B cannot add dynamic barrier A,
Otherwise from starting point S to terminal E just without can path, at the same time, the information that test system change grating map is by net
Network informs intelligent vehicle to be measured so as to change path planning in time, with reach detect in real time intelligent vehicle to be measured to scene
The weight-normality of transition draws ability.
7. a kind of intelligent vehicle according to claim 1 plans aptitude tests platform, it is characterised in that:Described test
Journey visual Simulation, test system utilizes intelligent vehicle mould according to the information that intelligent vehicle to be measured feeds back on grating map
Its motion state of type Dynamic Announce and track, test system will test test question information, including original grating map and test assignment
Intelligent vehicle to be measured is sent to by network, vehicle to be measured cooks up driving path, further controls steering column, the oil of vehicle
The vehicle executing agency such as door, braking, gear output action, meanwhile, the action message of these executing agencies is periodically fed back to
Test system, according to speed, the course information of feedback, control intelligent vehicle model carries out corresponding synchronization action to test system,
During Dynamic Programming aptitude tests, test system is same the position and movement locus for being continuously updated intelligent vehicle model
When, the obstacle information to adding is continuously updated, and the path planning and weight-normality for dynamically showing intelligent vehicle to be measured is drawn
Result, reach the effect of visualization of motion process.
8. a kind of intelligent vehicle according to claim 1 plans aptitude tests platform, it is characterised in that:Described test knot
Fruit and method for quantitatively evaluating, be test system when intelligent vehicle to be measured completes test assignment, for submit to path planning and
Other test datas are analyzed and evaluated, and are scored for its reasonability and optimality, shown below is some specific amounts
Change evaluation index:
(1) path L
(2) task situation M is completed
Judged by testing the motion planning path of vehicle whether in assignment file starting point, terminal and task point etc.
Whether planning tasks success is completed;
(3) risk of collision (Risk, R) in path
Touched less than minimum with whether the minimum distance of peripheral obstacle meets by per in the motion planning path for calculating vehicle
Hit distance to judge that path whether there is risk;
(4) time-consuming T is planned
T=TE-TS (4)
TSIt is designated as the test assignment data time that intelligent vehicle to be measured receives test system, TEIt is designated as intelligent vehicle to be measured to complete
Test assignment, to test system the time that task completes to mark is sent.
9. a kind of intelligent vehicle according to claim 8 plans aptitude tests platform, it is characterised in that:Described quantization is commented
Valency index, it is as follows that path planning often inscribes PTS computational methods:
wiRepresent the weight of every kind of test index, SiRepresent the score of every kind of test index.
10. a kind of intelligent vehicle according to claim 1 plans aptitude tests platform, it is characterised in that:Described is to be measured
Intelligent vehicle, be integrate network communication interface, decision making function module, control function module with it is vehicle-mounted execution structure nobody
Intelligent vehicle, intelligent vehicle is received after test assignment, and by decision-making and control module executing agency's response action is controlled, while
The motion change result for detecting is fed back to into test system, test system reacts its dynamic changing process in virtual scene
Intelligent vehicle model on, intelligent vehicle to be measured is placed on test-bed in process of the test, wheel is rolled on rotary drum, come
Simulated automotive is travelled on road, and during motion, the position of car body itself does not change, and meets relatively narrow and small
Various testing experiments are completed in lab space.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610939638.0A CN106644503B (en) | 2016-10-24 | 2016-10-24 | A kind of intelligent vehicle planning aptitude tests platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610939638.0A CN106644503B (en) | 2016-10-24 | 2016-10-24 | A kind of intelligent vehicle planning aptitude tests platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106644503A true CN106644503A (en) | 2017-05-10 |
CN106644503B CN106644503B (en) | 2019-04-09 |
Family
ID=58821224
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610939638.0A Active CN106644503B (en) | 2016-10-24 | 2016-10-24 | A kind of intelligent vehicle planning aptitude tests platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106644503B (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107678306A (en) * | 2017-10-09 | 2018-02-09 | 驭势(上海)汽车科技有限公司 | Dynamic scene information is recorded and emulation back method, device, equipment and medium |
CN107729878A (en) * | 2017-11-14 | 2018-02-23 | 智车优行科技(北京)有限公司 | Obstacle detection method and device, equipment, vehicle, program and storage medium |
CN108088686A (en) * | 2017-12-21 | 2018-05-29 | 驭势科技(浙江)有限公司 | Test emulation method and apparatus, computer storage media and electronic equipment |
CN108829087A (en) * | 2018-07-19 | 2018-11-16 | 山东省科学院自动化研究所 | A kind of intelligent test system and test method of autonomous driving vehicle |
CN108983633A (en) * | 2017-06-02 | 2018-12-11 | 北京图森未来科技有限公司 | Simulation system, the method and apparatus of more objects in a kind of virtual environment |
CN109141924A (en) * | 2018-09-12 | 2019-01-04 | 五方智能车科技有限公司 | A kind of examination and test method of intelligent vehicle basic performance |
CN109141929A (en) * | 2018-10-19 | 2019-01-04 | 重庆西部汽车试验场管理有限公司 | Intelligent network joins automobile emulation test system and method |
CN109211575A (en) * | 2017-07-05 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | Pilotless automobile and its field test method, apparatus and readable medium |
CN109764881A (en) * | 2018-12-07 | 2019-05-17 | 北京掌行通信息技术有限公司 | Pilotless automobile test method, device, electronic equipment and medium |
CN109839925A (en) * | 2017-11-24 | 2019-06-04 | 东莞产权交易中心 | A kind of dynamic route of vehicle and speed general control strategy |
CN110456767A (en) * | 2019-08-02 | 2019-11-15 | 上海哲奥实业有限公司 | A kind of vehicle operating system framework based on ecological chain and industrial chain |
CN110595798A (en) * | 2019-09-19 | 2019-12-20 | 北京百度网讯科技有限公司 | Test method and device |
CN110633905A (en) * | 2019-09-06 | 2019-12-31 | 武汉理工大学 | Reliability calculation method for cloud platform of intelligent vehicle |
CN110673590A (en) * | 2019-10-21 | 2020-01-10 | 安徽江淮汽车集团股份有限公司 | Method, device and equipment for judging reliability of automatic driving system and storage medium |
WO2020014951A1 (en) * | 2018-07-20 | 2020-01-23 | 深圳市道通智能航空技术有限公司 | Method and apparatus for building local obstacle map, and unmanned aerial vehicle |
TWI684085B (en) * | 2019-04-24 | 2020-02-01 | 揚昇育樂事業股份有限公司 | Self-driving travel path central controlling device of self-driving car |
CN111007834A (en) * | 2019-12-13 | 2020-04-14 | 北京经纬恒润科技有限公司 | Laboratory test system and method for ADAS path planning function |
CN111443702A (en) * | 2018-12-29 | 2020-07-24 | 沈阳新松机器人自动化股份有限公司 | Method for verifying robot path consistency |
CN111581102A (en) * | 2020-05-11 | 2020-08-25 | 中国人民解放军陆军研究院装甲兵研究所 | Test question bank system based on environmental data |
CN111879319A (en) * | 2020-06-29 | 2020-11-03 | 中国科学院合肥物质科学研究院 | Indoor testing method and system for ground unmanned platform and computer equipment |
CN112525542A (en) * | 2020-10-26 | 2021-03-19 | 泉州装备制造研究所 | Intelligent vehicle performance test system and method thereof |
CN112785838A (en) * | 2019-11-11 | 2021-05-11 | 千寻位置网络有限公司 | Test yard supervision system and method thereof |
CN113418718A (en) * | 2021-05-24 | 2021-09-21 | 东风柳州汽车有限公司 | Test task monitoring system and method based on test vehicle |
CN113686595A (en) * | 2021-09-26 | 2021-11-23 | 国汽智控(北京)科技有限公司 | Vehicle durability test method and device, cloud control platform and system |
CN116663939A (en) * | 2023-07-31 | 2023-08-29 | 北京理工大学 | Unmanned vehicle path planning scene and task complexity evaluation method and system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100017124A1 (en) * | 2008-07-17 | 2010-01-21 | Memsic, Inc. | Location and path-map generation data acquisition and analysis systems |
CN103207090A (en) * | 2013-04-09 | 2013-07-17 | 北京理工大学 | Driverless vehicle environment simulation test system and test method |
CN103234763A (en) * | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
CN103335853A (en) * | 2013-07-18 | 2013-10-02 | 中国科学院自动化研究所 | Unmanned driving vehicle cognitive competence testing system and method |
CN104020674A (en) * | 2014-04-21 | 2014-09-03 | 华南农业大学 | Matlab simulation visualized platform of vehicle Bug obstacle avoidance algorithm |
CN104260722A (en) * | 2014-09-23 | 2015-01-07 | 北京理工大学 | Automatic parking system |
CN105354356A (en) * | 2015-09-29 | 2016-02-24 | 中国人民解放军63892部队 | Radar intelligence simulation based air intelligence fusion performance evaluation system and method |
-
2016
- 2016-10-24 CN CN201610939638.0A patent/CN106644503B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100017124A1 (en) * | 2008-07-17 | 2010-01-21 | Memsic, Inc. | Location and path-map generation data acquisition and analysis systems |
CN103207090A (en) * | 2013-04-09 | 2013-07-17 | 北京理工大学 | Driverless vehicle environment simulation test system and test method |
CN103234763A (en) * | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
CN103335853A (en) * | 2013-07-18 | 2013-10-02 | 中国科学院自动化研究所 | Unmanned driving vehicle cognitive competence testing system and method |
CN104020674A (en) * | 2014-04-21 | 2014-09-03 | 华南农业大学 | Matlab simulation visualized platform of vehicle Bug obstacle avoidance algorithm |
CN104260722A (en) * | 2014-09-23 | 2015-01-07 | 北京理工大学 | Automatic parking system |
CN105354356A (en) * | 2015-09-29 | 2016-02-24 | 中国人民解放军63892部队 | Radar intelligence simulation based air intelligence fusion performance evaluation system and method |
Cited By (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108983633A (en) * | 2017-06-02 | 2018-12-11 | 北京图森未来科技有限公司 | Simulation system, the method and apparatus of more objects in a kind of virtual environment |
CN109211575A (en) * | 2017-07-05 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | Pilotless automobile and its field test method, apparatus and readable medium |
CN107678306A (en) * | 2017-10-09 | 2018-02-09 | 驭势(上海)汽车科技有限公司 | Dynamic scene information is recorded and emulation back method, device, equipment and medium |
CN107729878A (en) * | 2017-11-14 | 2018-02-23 | 智车优行科技(北京)有限公司 | Obstacle detection method and device, equipment, vehicle, program and storage medium |
CN109839925A (en) * | 2017-11-24 | 2019-06-04 | 东莞产权交易中心 | A kind of dynamic route of vehicle and speed general control strategy |
CN108088686A (en) * | 2017-12-21 | 2018-05-29 | 驭势科技(浙江)有限公司 | Test emulation method and apparatus, computer storage media and electronic equipment |
CN108088686B (en) * | 2017-12-21 | 2020-11-20 | 驭势科技(浙江)有限公司 | Test simulation method and device, computer storage medium and electronic equipment |
CN108829087A (en) * | 2018-07-19 | 2018-11-16 | 山东省科学院自动化研究所 | A kind of intelligent test system and test method of autonomous driving vehicle |
CN108829087B (en) * | 2018-07-19 | 2019-09-10 | 山东省科学院自动化研究所 | A kind of intelligent test system of autonomous driving vehicle |
WO2020014951A1 (en) * | 2018-07-20 | 2020-01-23 | 深圳市道通智能航空技术有限公司 | Method and apparatus for building local obstacle map, and unmanned aerial vehicle |
CN109141924A (en) * | 2018-09-12 | 2019-01-04 | 五方智能车科技有限公司 | A kind of examination and test method of intelligent vehicle basic performance |
CN109141929A (en) * | 2018-10-19 | 2019-01-04 | 重庆西部汽车试验场管理有限公司 | Intelligent network joins automobile emulation test system and method |
CN109764881A (en) * | 2018-12-07 | 2019-05-17 | 北京掌行通信息技术有限公司 | Pilotless automobile test method, device, electronic equipment and medium |
CN109764881B (en) * | 2018-12-07 | 2021-05-07 | 北京掌行通信息技术有限公司 | Unmanned vehicle testing method and device, electronic equipment and medium |
CN111443702A (en) * | 2018-12-29 | 2020-07-24 | 沈阳新松机器人自动化股份有限公司 | Method for verifying robot path consistency |
TWI684085B (en) * | 2019-04-24 | 2020-02-01 | 揚昇育樂事業股份有限公司 | Self-driving travel path central controlling device of self-driving car |
CN110456767A (en) * | 2019-08-02 | 2019-11-15 | 上海哲奥实业有限公司 | A kind of vehicle operating system framework based on ecological chain and industrial chain |
CN110633905B (en) * | 2019-09-06 | 2023-05-02 | 武汉理工大学 | Intelligent Che Yun platform reliability calculation method and system |
CN110633905A (en) * | 2019-09-06 | 2019-12-31 | 武汉理工大学 | Reliability calculation method for cloud platform of intelligent vehicle |
CN110595798B (en) * | 2019-09-19 | 2022-04-05 | 北京百度网讯科技有限公司 | Test method and device |
CN110595798A (en) * | 2019-09-19 | 2019-12-20 | 北京百度网讯科技有限公司 | Test method and device |
CN110673590A (en) * | 2019-10-21 | 2020-01-10 | 安徽江淮汽车集团股份有限公司 | Method, device and equipment for judging reliability of automatic driving system and storage medium |
CN112785838A (en) * | 2019-11-11 | 2021-05-11 | 千寻位置网络有限公司 | Test yard supervision system and method thereof |
CN111007834B (en) * | 2019-12-13 | 2021-05-18 | 北京经纬恒润科技股份有限公司 | Laboratory test system and method for ADAS path planning function |
CN111007834A (en) * | 2019-12-13 | 2020-04-14 | 北京经纬恒润科技有限公司 | Laboratory test system and method for ADAS path planning function |
CN111581102A (en) * | 2020-05-11 | 2020-08-25 | 中国人民解放军陆军研究院装甲兵研究所 | Test question bank system based on environmental data |
CN111879319A (en) * | 2020-06-29 | 2020-11-03 | 中国科学院合肥物质科学研究院 | Indoor testing method and system for ground unmanned platform and computer equipment |
CN111879319B (en) * | 2020-06-29 | 2023-10-20 | 中国科学院合肥物质科学研究院 | Indoor test method and system for ground unmanned platform and computer equipment |
CN112525542A (en) * | 2020-10-26 | 2021-03-19 | 泉州装备制造研究所 | Intelligent vehicle performance test system and method thereof |
CN112525542B (en) * | 2020-10-26 | 2022-09-27 | 泉州装备制造研究所 | Intelligent vehicle performance test system and method thereof |
CN113418718A (en) * | 2021-05-24 | 2021-09-21 | 东风柳州汽车有限公司 | Test task monitoring system and method based on test vehicle |
CN113418718B (en) * | 2021-05-24 | 2022-07-01 | 东风柳州汽车有限公司 | Test task monitoring system and method based on test vehicle |
CN113686595A (en) * | 2021-09-26 | 2021-11-23 | 国汽智控(北京)科技有限公司 | Vehicle durability test method and device, cloud control platform and system |
CN116663939A (en) * | 2023-07-31 | 2023-08-29 | 北京理工大学 | Unmanned vehicle path planning scene and task complexity evaluation method and system |
CN116663939B (en) * | 2023-07-31 | 2023-10-17 | 北京理工大学 | Unmanned vehicle path planning scene and task complexity evaluation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN106644503B (en) | 2019-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106644503A (en) | Intelligent vehicle planning capacity testing platform | |
US10346888B2 (en) | Systems and methods to obtain passenger feedback in response to autonomous vehicle driving events | |
US11900738B2 (en) | Systems and methods to obtain feedback in response to autonomous vehicle failure events | |
CN109466543A (en) | Plan autokinetic movement | |
WO2022221979A1 (en) | Automated driving scenario generation method, apparatus, and system | |
Yoo et al. | Stackelberg game based model of highway driving | |
CN107697070A (en) | Driving behavior Forecasting Methodology and device, unmanned vehicle | |
US20130052614A1 (en) | Driver Performance Metric | |
CN110531740A (en) | A kind of intelligent vehicle intelligence degree quantization assessment method | |
CN109084992A (en) | Method based on engine bench test unmanned vehicle intelligence | |
Sun et al. | Acclimatizing the operational design domain for autonomous driving systems | |
US20220198107A1 (en) | Simulations for evaluating driving behaviors of autonomous vehicles | |
Tango et al. | Field tests and machine learning approaches for refining algorithms and correlations of driver’s model parameters | |
CN112508164B (en) | End-to-end automatic driving model pre-training method based on asynchronous supervised learning | |
CN109782751A (en) | Method and apparatus for autonomous system performance and benchmark test | |
US11654938B1 (en) | Methods and apparatus for disengaging an autonomous mode based on lateral error of an autonomous vehicle | |
CN109284889B (en) | Unmanned vehicle reaction agility evaluation method and device | |
Taş | Integrating combinatorial reasoning and continuous methods for optimal motion planning of autonomous vehicles | |
Faraji et al. | Autonomous Merging onto the Highway Using LSTM Neural Network | |
US20240144748A1 (en) | Systems and Methods to Obtain Feedback in Response to Autonomous Vehicle Failure Events | |
Schester | Multi-Agent Reinforcement Learning Autonomous Driving Highway On-Ramp Merge | |
Menendez et al. | Detecting and Predicting Smart Car Collisions in Hybrid Environments from Sensor Data | |
Escuín et al. | A Long-Distance Smart Driving Service Based on Floating Car Data and Open Data | |
CN107958616A (en) | System is tested in driver training based on confrontation neutral net | |
US11348455B2 (en) | Intersection traffic control method, apparatus and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |