CN113254336A - Method and system for simulation test of traffic regulation compliance of automatic driving automobile - Google Patents
Method and system for simulation test of traffic regulation compliance of automatic driving automobile Download PDFInfo
- Publication number
- CN113254336A CN113254336A CN202110564766.2A CN202110564766A CN113254336A CN 113254336 A CN113254336 A CN 113254336A CN 202110564766 A CN202110564766 A CN 202110564766A CN 113254336 A CN113254336 A CN 113254336A
- Authority
- CN
- China
- Prior art keywords
- proposition
- rule
- cross
- traffic
- rules
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3604—Software analysis for verifying properties of programs
- G06F11/3616—Software analysis for verifying properties of programs using software metrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3664—Environments for testing or debugging software
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a method and a system for simulating and testing the conformity of traffic laws and regulations of an automatic driving automobile. The preset classification principle is adopted when the intersection rule atom proposition is extracted, so that the intersection rule atom proposition logic is clear, omission is avoided, the reusability is high, and the judgment efficiency of the whole system can be improved. And can cover most intersection rules including simple scenarios as well as complex scenarios. Judging the truth of the traffic rule atom proposition according to the acquired parameter information of the traffic participants; and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participants obey the cross rules or not by using the authenticity of the formal cross rules. Because the generated formal intersection rules contain the intersection rule atomic propositions with clear logic, the behavior of the automatic driving vehicle or the output result of the planning decision part can be better evaluated whether to comply with the intersection rules or not through the more reasonable formal intersection rules.
Description
Technical Field
The application relates to the technical field of intelligent traffic, in particular to a method and a system for simulation test of traffic regulation compliance of an automatic driving automobile.
Background
With the development of society, intelligent automobiles are gradually entering the daily lives of people. Automatic driving plays an important role in intelligent automobiles, and automatic driving vehicles need to pass various tests, and currently, the tests mainly focus on closed or open road tests at the whole vehicle level or compliance and performance tests at the component level. The design and test of a decision planning module in the automatic driving vehicle mainly focuses on driving safety and partial simple traffic regulation legitimacy, such as no collision with an obstacle, following of a traffic light and a road sign, no overspeed and the like, and far does not cover enough traffic regulations. In the prior art, a rule for human drivers is converted into a corresponding formalized rule through a certain specific logic language, so that decision planning algorithm design developers or machines can know the rule without ambiguity. However, the technology only makes formal translation on the natural language traffic rules, the formal traffic rules are mainly used for guiding the design and development of an automatic driving system (such as a decision planning module), and tests and verifications on whether the output results of the behavior of the whole automatic driving vehicle or the decision planning part meet the traffic rules are less. In addition, during design of the formal intersection rules, corresponding atom propositions are generally extracted from the natural language intersection rules one by one without a uniform system, so that the extracted atom propositions are mixed and disorderly, strong similarity exists among propositions, the reusability is not high, and formal verification is difficult to perform.
Disclosure of Invention
In order to overcome the problems of incomplete formation of formal traffic regulations and no subsequent evaluation in the related technology at least to a certain extent, the application provides a simulation test method and a system for compliance of traffic regulations of an automatic driving automobile.
The scheme of the application is as follows:
according to a first aspect of the embodiments of the present application, there is provided a method for simulation test of compliance of traffic regulations of an autonomous vehicle, including:
acquiring parameter information of traffic participants;
acquiring a formalized cross standard; the formal cross rules comprise cross rule atom propositions extracted according to a preset classification principle;
judging the truth of the traffic rule atom proposition according to the parameter information of the traffic participant;
and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participant obeys the cross rules or not by using the authenticity of the formal cross rules.
Preferably, in an implementation manner of the present application, before the obtaining the formalized intersection, the method further includes:
extracting the intersection rule atom proposition according to a preset classification principle;
combining the cross rule atom proposition with a preset conjunction word to obtain a cross rule high-grade proposition;
and combining the cross rule atom proposition, the cross rule high-level proposition and the conjunction words, or combining the cross rule high-level proposition and the conjunction words to obtain the formalized cross rule.
Preferably, in an implementation manner of the present application, the extracting according to a preset classification rule to obtain the intersection atomic proposition includes:
taking a road as a reference, adding static infrastructure on the road, dynamic information of temporary conditions, and dynamic traffic participant behavior and environmental information on the road layer by layer, and classifying the traffic rule atom proposition into: road type proposition, infrastructure type proposition, temporary condition type proposition, behavior type proposition and environment type proposition;
and extracting various classified intersection rule atom propositions.
Preferably, in an implementation manner of the present application, the extracting according to a preset classification rule to obtain the intersection atomic proposition further includes:
describing that the traffic participant is located on a preset road under a preset environment by taking basic components of the traffic rule as a reference, finding a preset signal, and when a preset action is performed, meeting a preset constraint condition, classifying the atomic proposition of the traffic rule into: setting questions of environment class, position class, signal class, action class and constraint condition class;
and extracting various classified intersection rule atom propositions.
Preferably, in an implementable manner of the present application, the determining the authenticity of the formalized cross-standard according to the authenticity of the cross-standard atomic proposition includes:
judging the truth of the cross-standard high-grade proposition according to the truth of the cross-standard atomic proposition;
and judging the authenticity of the formal cross rules according to the authenticity of the cross rule atom proposition and the authenticity of the cross rule high-grade proposition.
Preferably, in an implementable manner of the present application, the determining the authenticity of the traffic rule atomic proposition according to the parameter information of the traffic participant includes: judging the truth of the traffic rule atom proposition at each time point according to the parameter information of the traffic participant at each time point;
the judging the truth of the formal cross rules according to the truth of the cross rule atom proposition comprises the following steps: and judging the authenticity of the formalized cross gauges at each time point according to the authenticity of the cross gauge atom proposition at each time point.
Preferably, in an implementation manner of the present application, the method further includes:
classifying the grade of the traffic rule high-grade proposition;
and combining the cross rule atom proposition, the preset conjunction words and the low-level cross rule high-level proposition to obtain the high-level cross rule high-level proposition.
Preferably, in an implementable manner of the present application, the parameter information of the traffic participant includes at least: participant inherent attribute information, time information, environment information, location information, speed information, attitude information, lighting information, sound information, and status information.
Preferably, in an implementable manner of the present application, the predetermined conjunctions include: a logic operator and a time sequence operator;
the logical operator conjuncts include at least: negation, conjunctive, disjunctive, derivational, and equivalents;
the temporal operator conjunction word comprises at least: the next moment, until, always, finally, always occurs within this time period and will occur within this time period.
According to a second aspect of the embodiments of the present application, there is provided a traffic rule formalization and evaluation system, including:
the acquisition module is used for acquiring parameter information of the traffic participants;
the generating module is used for acquiring the formalized intersection rule; the formal cross rules comprise cross rule atom propositions extracted according to a preset classification principle;
the judging module is used for judging the truth of the traffic rule atom proposition according to the parameter information of the traffic participant; and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participant obeys the cross rules or not by using the authenticity of the formal cross rules.
The technical scheme provided by the application can comprise the following beneficial effects: according to the method for simulating and testing the conformity of the traffic laws and regulations of the automatically-driven automobile, the obtained formalized traffic laws comprise atomic propositions of the traffic laws extracted according to the preset classification principle. The preset classification principle is adopted when the intersection rule atom proposition is extracted, so that the intersection rule atom proposition logic is clear, omission is avoided, the reusability is high, and the judgment efficiency of the whole system can be improved. And can cover most intersection rules including simple scenarios as well as complex scenarios. Judging the truth of the traffic rule atom proposition according to the acquired parameter information of the traffic participants; and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participants obey the cross rules or not by using the authenticity of the formal cross rules. Because the generated formal intersection rules contain the intersection rule atomic propositions with clear logic, the behavior of the automatic driving vehicle or the output result of the planning decision part can be better evaluated whether to comply with the intersection rules or not through the more reasonable formal intersection rules.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic flow chart of a method for simulation testing compliance with traffic regulations for an auto-driven vehicle according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating the process of obtaining a formal traffic rule in a method for simulation testing compliance with an auto-driving vehicle traffic rule according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a simulation test system for compliance with traffic regulations for an auto-driven vehicle according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a simulation test device for compliance with the autonomy traffic regulations, according to an embodiment of the present application.
Reference numerals: an acquisition module-21; an acquisition module-22; a judgment module-23; a processor-31; a memory-32.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
An automated driving vehicle traffic regulation compliance simulation test method, referring to fig. 1, includes:
s11: acquiring parameter information of traffic participants;
the parameter information of the traffic participant at least comprises inherent attribute information, time information, environment information, position information, speed information, attitude information, light information, sound information, state information and the like of the traffic participant.
The intrinsic attribute information of the traffic participant includes, but is not limited to, category information of the traffic participant, including, but not limited to, motor vehicles, non-motor vehicles, pedestrians, automobiles, special vehicles, three-wheel vehicles, two-wheel vehicles, and the like. The size information includes the length, width, etc. of the traffic participant. The environmental information includes but is not limited to natural environmental information, which includes information of rain, snow, fog, visibility, illumination intensity, and the like of the environment where the traffic participant is located; the map environment information comprises high-precision map information of the area where the traffic participant is located, and the high-precision map information comprises, but is not limited to, road surface material information, lane line information, traffic sign information, traffic light information and the like. The position information includes, but is not limited to, three-dimensional position coordinate information or longitude and latitude information of the traffic participant in a world coordinate system and a road coordinate system. The speed information includes, but is not limited to, information of a linear speed, a linear acceleration, an angular speed, an angular acceleration, and the like of the traffic participant, and the speed may be a value in a world coordinate system or a value in a vehicle coordinate system. Attitude information includes, but is not limited to, pitch angle, yaw angle, roll angle, or quaternion of the traffic participants. The light information includes, but is not limited to, the traffic participants' dipped headlights, high beams, turn signals, brake lights, hazard lights, fog lights, position lights, etc. The sound information includes, but is not limited to, a whistling sound, a special vehicle sound, and the like. The status information includes, but is not limited to, fault information of the traffic participants, and the like.
S12: acquiring a formalized cross standard; the formalized cross rules comprise cross rule atom propositions extracted according to a preset classification principle;
the method for acquiring the formal intersection rules refers to fig. 2, and specifically comprises the following steps:
s121: extracting according to a preset classification principle to obtain an intersection atomic proposition;
the cross rule atom proposition is obtained by extracting a cross rule set according to the following classification principle:
optional classification principle 1:
taking a road as a reference, adding static infrastructure on the road, dynamic information (such as traffic lights) of temporary conditions, and dynamic traffic participant behavior and environmental information on the road layer by layer, and classifying traffic rule atomic propositions into: road type proposition, infrastructure type proposition, temporary condition type proposition, behavior type proposition and environment type proposition;
extracting various classified cross rule atom propositions.
The classification principle is from bottom to top, logic is clear, various propositions are not crossed with each other, and the multiplex rate is high, thereby promoting the evaluation efficiency of the whole system.
The atomic propositions classified according to classification rule 1 are illustrated:
road class atom propositions include, but are not limited to:
the onRamp/onAccLane/onDecLane/onEmergencyLane/onHighwayMain respectively represents that the target vehicle is on the ramp/the acceleration lane/the deceleration lane/the emergency lane/the highway main road
The onHighway/onUrbanroad/onRuralroad respectively represents that the target vehicle is on the expressway/urban road/rural road
The onRoadSideRight/onRoadSideLeft respectively indicate that the target vehicle is in the rightmost/leftmost lane of the road
Infrastructure class atom propositions include, but are not limited to:
infNostop/infSpeedlimit respectively indicates the existence of the front stop sign/speed limit sign
Temporary condition class atom propositions include, but are not limited to:
the temtLightRed/temtLightGreen/temtLightyellow respectively indicates that the traffic lights on the driving path of the target vehicle are red/green/yellow
Behavioral class atom propositions include, but are not limited to:
stKeeplane shows that the lane where the target vehicle is located is consistent with the last state point
The stOnLine represents the state of the line pressing at the target vehicle, including all the lane lines and the stop lines
The stCrosingLeft/stCrosingRight respectively indicates that the target vehicle is pressing the line and is in the left lane/the right lane after being out of the line pressing state
stReverse indicates that the target vehicle is backing
stStop indicates that the target vehicle is parked
stRetogride indicates that the target vehicle is driving in the wrong direction
stCollision indicates that the target vehicle collides
stSignalLeft/stSignalRight/stSignalEmergenience/stSignalPositionLamps/stSignalTailLamps/stSignalLowBeam/stSignalHeadLampls/stSignalLowBeam for distinguishing and indicating target vehicle left turn light/right turn light/stSignalHighBeam/stSignalHighLowFlicker, switching between left turn light, right turn light, high light and high and low light is in on state
stProperDist indicates that the target vehicle and other obstacles meet the distance constraint
stPROPERRIGHTGOfWay indicates that the target vehicle has right of way
stPropperseed indicates that the target vehicle meets the requirement of road speed limit
stProperseedhorizontal indicates that the target vehicle satisfies the lateral speed constraint
stProperlone indicates that the target vehicle is traveling on the correct lane
stProperaAccVertical/stProperaAccHorifocal indicating that target vehicle lateral/longitudinal acceleration satisfies acceleration constraints
stBreakDown indicates that the target vehicle has failed
stHorn indicates that the target vehicle is using a horn
StObjBehin/stObjAhead/stObjLeft/stObjRight indicates that other targets are behind/front/left/right of the target vehicle
StObjSameLane/StObjLeftLane/StObjRightLane indicates that other target and target vehicles are in the same lane/in the left/right lane of the target vehicle
actUTurn shows the turning of the target vehicle
actTurnleft/actTurnRight indicating left/right turn of the target vehicle
Environmental class atom propositions include, but are not limited to
envRain/envSnow/envFog indicates that the current environment is rain/snow/fog
envVisilityLevelzero/envVisilityLevelone/envVisilibivelTwo/envVisilityLevelThree indicates a visibility of 0/1/2/3 levels
envLowIlluminance represents that the current illumination is low
envTrafficJam indicates that the current traffic jam state is
Optional classification principle 2:
describing that the traffic participant is located on a preset road under a preset environment by taking basic components of the traffic rule as a reference, finding a preset signal, and when a preset action is performed, meeting a preset constraint condition, classifying the atomic proposition of the traffic rule into: setting questions of environment class, position class, signal class, action class and constraint condition class;
extracting various classified cross rule atom propositions.
The classification principle has clear logic, various propositions are not crossed with each other, and the reuse rate is high, so that the evaluation efficiency of the whole system is improved.
The atomic propositions classified according to classification principle 2 are illustrated:
environmental class atom propositions include, but are not limited to
envRain/envSnow/envFog indicates that the current environment is rain/snow/fog
Position class atom propositions include, but are not limited to
The onRamp/onAccLane/onDecLane/onEmergencyLane/onHighwayMain respectively represents that the target vehicle is on the ramp/the acceleration lane/the deceleration lane/the emergency lane/the highway main road
Signal class atom propositions include, but are not limited to
the temtLightRed/temtLightGreen/temtLightyellow respectively indicates that the traffic lights on the driving path of the target vehicle are red/green/yellow
infNostop/infSpeedlimit respectively indicates the existence of the front stop sign/speed limit sign
Action class atom propositions include, but are not limited to
The stCrosingLeft/stCrosingRight respectively indicates that the target vehicle is pressing the line and is in the left lane/the right lane after being out of the line pressing state
stReverse indicates that the target vehicle is backing
stStop indicates that the target vehicle is parked
Constraint class atom propositions include, but are not limited to
stProperDist indicates that the target vehicle and other obstacles meet the distance constraint
stProperseedhorizontal indicates that the target vehicle satisfies the lateral speed constraint
stProperlone indicates that the target vehicle is traveling on the correct lane
stProperaAccVertical/stProperaAccHorifocal indicating that target vehicle lateral/longitudinal acceleration satisfies acceleration constraints
S122: combining the cross rule atom proposition with a preset connection word to obtain a cross rule high-grade proposition;
the cross rule proposition comprises a cross rule atom proposition and a cross rule high-grade proposition, and the cross rule high-grade proposition consists of a cross rule atom proposition and a connection word. The combination of the cross rule atom propositions is utilized to generate the cross rule high-grade proposition, a new atom proposition description is used for avoiding meeting new target actions or scenes, the number of the cross rule atom propositions is reduced, and the reusability of the proposition is increased.
Conjunctions include: a logic operator and a time sequence operator;
the logical operator conjuncts include at least: negation, conjunctive, disjunctive, derivational, and equivalents;
the temporal operator conjunction word comprises at least: the next moment, until, always, finally, always occurs within this time period and will occur within this time period.
Reference is made to the following table:
summary table of logical operators
Time sequence operator summary table
Preferably, the high-level proposition of the traffic rule is classified in a grade way;
and combining the cross rule atom propositions, the preset conjunction words and the low-level cross rule high-level propositions to obtain the high-level cross rule high-level propositions.
The atomic proposition can also be called a 0-level proposition, a high-level proposition consisting of only the 0-level proposition and the conjunction words is a 1-level proposition, a high-level proposition consisting of the 1-level proposition, the 0-level proposition and the conjunction words is a 2-level proposition, and the higher-level atomic proposition composition method is analogized in the same way. For the alternative classification principle 1, high-level propositions are exemplified as follows:
road class level 1 propositions include, but are not limited to
onRoadSide indicates that the target vehicle is on the roadside, onRoadRightSide
onRoad represents the target vehicle on the road, onHighway onUrb and road
Behavior class level 1 propositions include, but are not limited to
stSurpass indicates that the target vehicle exceeds the other vehicles, stObjAhead ^ X (stObjBehind)
actCrossLeft indicates that the target vehicle is next to move to the left lane,
actcrosssright indicates that the target vehicle has next a change to right lane maneuver,
behavior class level 2 propositions include, but are not limited to
ACTOVTake indicates that the target vehicle has a subsequent overtaking action, either ACTCROSSLeft ^ F (stKEEPLane ^ F (ACTCROSSRight))) or ACTCROSSRight ^ F (stKEEPLane ^ F (ACTCROSSLeft)))
S123: combining the cross rule atom proposition, the cross rule high-grade proposition and the connection words, or combining the cross rule high-grade proposition and the connection words to obtain the formalized cross rule.
The formalized cross rule consists of a cross rule proposition and a conjunction word. For example, a formalized intersection of "when it is confirmed that the vehicle does not satisfy the safety distance with the rear of the adjacent lane, lane change is not required" is:
(stCrossingLeft∧stObjLeftLane∧stObjBehind)∨(stCrossingRight∧stObjRightLane∧stObjBehind)→stProperDist
the indication is that when the target vehicle is in a left lane change state, if the other vehicle is in a left lane of the target vehicle and behind the target vehicle, the target vehicle needs to satisfy a safe distance with the other vehicle, or when the target vehicle is in a right lane change state, if the other vehicle is in a right lane of the target vehicle and behind the target vehicle, the target vehicle needs to satisfy the safe distance with the other vehicle.
For example, the formalized intersection rule that a vehicle runs on a highway and cannot go backwards or backwards and pass through a central division zone to turn around is as follows:
the target vehicle can not be in a reversing state, a reverse running state and a turning around state when the target vehicle is on the highway.
For example, a formalized intersection rule that "turn left, change lane left, prepare to overtake, should turn on the left turn signal light T seconds ahead" is:
(actTurnLeft∨actCrossLeft∨actOvertake)→G(-T,0)(stSignalLeft)
when the target vehicle turns left, changes lane left or overtakes, the on state of the left turn light is always established within the first T seconds.
For example, the formalized convention for "at high speed, the autonomous vehicle should be a safe distance from the lead vehicle" is:
onHighway∧stObjAhead∧stObjSameLane→stProperDist
when the target vehicle is at a high speed, if the target vehicle is located in front of the target vehicle and in the same lane with the target vehicle, the target vehicle needs to keep a safe distance with the target vehicle.
For example, a formal intersection rule that the line pressing time is not longer than T seconds in the vehicle lane changing process is as follows:
and indicating that the state of no line pressing exists in the first T seconds when the target vehicle is in the left lane changing state or the right lane changing state.
For example, a formalized traffic rule that "overtaking from the left side of the overtaken vehicle only" is:
indicating that when the target vehicle overtakes, the target vehicle is to the right of the target vehicle when it becomes in front of the target vehicle behind the target vehicle.
For example, the formalized intersection rule that the speed is not less than 60km/h when driving from an acceleration lane to a highway road is as follows:
onHighway∧onAccLane∧X(stCrossingLeft)→stProperSpeed
it is shown that when the target vehicle is on the expressway and in the acceleration lane, the constraint of the speed not less than 60km/h is to be satisfied when the target vehicle is to change lanes from the left of the acceleration lane.
For example, a formalized convention for "before a collision with a target, an effective safety measure is to be performed" is:
stCollision→G(-T,0)(stProperAccVertical∧stProperAccHorizontal)
the method shows that the longitudinal deceleration constraint and the transverse acceleration constraint are required to be met within T seconds before the target vehicle turns over and collides.
S13: judging the truth of the traffic rule atomic proposition according to the parameter information of the traffic participant;
and judging the truth of the traffic rule atom proposition according to the parameter information of the traffic participant. For example, the judgment result of propositions such as stCrosingLeft/stCrosingRight is obtained through the position relation between the target vehicle boundary and the lane line; obtaining a judgment result of propositions such as stObjBehind/stObjAhead and the like through the position relation between the target vehicle and other vehicles; judging the judgment result of propositions such as the st ObjLeftLane/the st ObjRightLane and the like according to the size relation of the ID of the target vehicle and the ID of the lane where the other vehicle is positioned; and judging the judgment result of the proposition such as stPropertDist and the like according to the size relationship between the distance between the target vehicle and the other vehicle and the safety distance.
Specifically, the truth of each time point traffic rule atomic proposition is judged according to the parameter information of each time point traffic participant, and the truth of each proposition can be judged at each time point.
stCrossingLeft：False，Ture，Ture…
stCrossingRight：False，False，False…
stObjLeftLane：False，False，False…
stObjRightLane：False，False，False…
stObjBehind：Ture，Ture，False…
stObjAhead：False，False，Ture…
stProperDist：False，False，False…
stKeepLane：Ture，False，Ture…
stOnLine：Ture，Ture，Ture…
…
S14: and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participants obey the cross rules or not by using the authenticity of the formal cross rules.
The method specifically comprises the following steps:
judging the truth of the high-grade proposition of the cross rule according to the truth of the atomic proposition of the cross rule;
and judging the truth of the formal cross rule according to the truth of the cross rule atomic proposition and the truth of the cross rule high-grade proposition.
Similarly, the truth of the high-grade proposition of each time point cross rule is judged according to the truth of the atom proposition of each time point cross rule. And judging the authenticity of the formalized cross rule at each time point according to the authenticity of the atomic proposition of the cross rule at each time point and the authenticity of the high-grade proposition of the cross rule.
The truth judgment of the high-level proposition of the cross rule is illustrated according to the truth of the atomic proposition of the cross rule:
true and false actCrossLeft results from the true and false of the StOnLine, stCrossLeft proposition, for example:
actCrossLeft can be obtained: ture.
The true and false of stSurpass is derived from the true and false of the proposition of stObjAhead, stObjBehind, for example: stObjAhead ^ x (stobjbehind): false ^ X (Ture), which can obtain stSurpass: ture.
The truth of actOvertake is obtained from the truth of the propositions actCrossLeft, stKeepLane, stSurpass and actCrosssright, for example: actCrossLeft ^ F (stKeepanlane ^ F (stSurplass ^ F (stKeepanlane ^ F (actCrossRight))): more particularly, the present invention relates to a method for obtaining actoverture by using more than two parts of Ture ^ F (Ture)): ture.
The truth of the formal cross rules is judged according to the truth of the cross rule atomic proposition and the truth of the cross rule high-grade proposition by way of example:
for the cross gauge (stCrossingLeft. Lame. StObjLeftLane. StObjBehind) (stCrossingRight. StObjRightLane. StObjBehind) → stProperDist)
(Ture ^ Ture) → Fals, it can be concluded that the proposition is False, i.e. the formalized traffic rule value is False, i.e. the vehicle does not comply with the traffic rule when changing lanes.
For cross rule
In the method for simulation testing of compliance of the traffic laws of the automatically driven automobile in the embodiment, the obtained formalized traffic laws comprise atomic propositions of the traffic laws extracted according to the preset classification principle. The preset classification principle is adopted when the intersection rule atom proposition is extracted, so that the intersection rule atom proposition logic is clear, omission is avoided, the reusability is high, and the judgment efficiency of the whole system can be improved. And can cover most intersection rules including simple scenarios as well as complex scenarios. Judging the truth of the traffic rule atom proposition according to the acquired parameter information of the traffic participants; and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participants obey the cross rules or not by using the authenticity of the formal cross rules. Because the generated formal intersection rules contain the intersection rule atomic propositions with clear logic, the behavior of the automatic driving vehicle or the output result of the planning decision part can be better evaluated whether to comply with the intersection rules or not through the more reasonable formal intersection rules.
An automated driving vehicle traffic regulation compliance simulation test system, referring to fig. 3, comprising:
the acquisition module 21 is used for acquiring parameter information of the traffic participants;
an obtaining module 22, configured to obtain a formalized intersection rule; the formalized cross rules comprise cross rule atom propositions extracted according to a preset classification principle;
the judging module 23 is used for judging the truth of the traffic rule atom proposition according to the parameter information of the traffic participant; and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participants obey the cross rules or not by using the authenticity of the formal cross rules.
In the simulation test system for compliance of the automatic driving automobile traffic laws in the embodiment, the formal traffic laws generated by the generation module comprise atomic propositions of the traffic laws extracted according to the preset classification principle. The preset classification principle is adopted when the intersection rule atom proposition is extracted, so that the intersection rule atom proposition logic is clear, omission is avoided, the reusability is high, and the judgment efficiency of the whole system can be improved. And can cover most intersection rules including simple scenarios as well as complex scenarios. Judging the truth of the traffic rule atom proposition through a judging module according to the parameter information of the traffic participant acquired by the acquiring module; and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participants obey the cross rules or not by using the authenticity of the formal cross rules. Because the generated formal intersection rules contain the intersection rule atomic propositions with clear logic, the behavior of the automatic driving vehicle or the output result of the planning decision part can be better evaluated whether to comply with the intersection rules or not through the more reasonable formal intersection rules.
The automated driving vehicle traffic regulation compliance simulation test system in some embodiments, further comprising:
the extraction module is used for extracting the intersection rule atom proposition according to a preset classification principle;
the synthesis module is used for combining the cross rule atom proposition and the preset connection words to obtain a cross rule high-grade proposition; combining the cross rule atom proposition, the cross rule high-grade proposition and the connection words, or combining the cross rule high-grade proposition and the connection words to obtain the formalized cross rule.
The automated driving vehicle traffic regulation compliance simulation test system in some embodiments, further comprising:
the judging module is used for judging the authenticity of the cross-standard advanced proposition according to the authenticity of the cross-standard atomic proposition; and judging the authenticity of the formal cross rules according to the authenticity of the cross rule atom proposition and the authenticity of the cross rule high-grade proposition.
An autopilot traffic regulation compliance simulation test apparatus, referring to fig. 4, comprising:
a processor 31 and a memory 32;
the processor 31 and the memory 32 are connected by a communication bus:
the processor 31 is used for calling and executing the program stored in the memory 32;
a memory 32 for storing a program for executing at least the automated driving automobile traffic regulation compliance simulation test method in any of the above embodiments.
An embodiment of the present invention further provides a storage medium, where the storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the simulation test method for compliance with the traffic regulations of the autonomous driving vehicle in the above embodiment are implemented.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A simulation test method for compliance of traffic regulations of an automatically driven automobile is characterized by comprising the following steps:
acquiring parameter information of traffic participants;
acquiring a formalized cross standard; the formal cross rules comprise cross rule atom propositions extracted according to a preset classification principle;
judging the truth of the traffic rule atom proposition according to the parameter information of the traffic participant;
and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participant obeys the cross rules or not by using the authenticity of the formal cross rules.
2. The method of claim 1, wherein prior to obtaining the formalized intersection, the method further comprises:
extracting the intersection rule atom proposition according to a preset classification principle;
combining the cross rule atom proposition with a preset conjunction word to obtain a cross rule high-grade proposition;
and combining the cross rule atom proposition, the cross rule high-level proposition and the conjunction words, or combining the cross rule high-level proposition and the conjunction words to obtain the formalized cross rule.
3. The method of claim 2, wherein the extracting the intersection atomic proposition according to the preset classification rule comprises:
taking a road as a reference, adding static infrastructure on the road, dynamic information of temporary conditions, and dynamic traffic participant behavior and environmental information on the road layer by layer, and classifying the traffic rule atom proposition into: road type proposition, infrastructure type proposition, temporary condition type proposition, behavior type proposition and environment type proposition;
and extracting various classified intersection rule atom propositions.
4. The method of claim 2, wherein the extracting the intersection atomic proposition according to the preset classification rule comprises:
describing that the traffic participant is located on a preset road under a preset environment by taking basic components of the traffic rule as a reference, finding a preset signal, and when a preset action is performed, meeting a preset constraint condition, classifying the atomic proposition of the traffic rule into: setting questions of environment class, position class, signal class, action class and constraint condition class;
and extracting various classified intersection rule atom propositions.
5. The method of claim 2, wherein said determining the authenticity of the formalized cross-rules based on the authenticity of the cross-rule atomic proposition comprises:
judging the truth of the cross-standard high-grade proposition according to the truth of the cross-standard atomic proposition;
and judging the authenticity of the formal cross rules according to the authenticity of the cross rule atom proposition and the authenticity of the cross rule high-grade proposition.
6. The method of claim 1, wherein the determining the authenticity of the traffic rule atomic proposition according to the parameter information of the traffic participant comprises: judging the truth of the traffic rule atom proposition at each time point according to the parameter information of the traffic participant at each time point;
the method for judging the authenticity of the formal cross rules according to the authenticity of the cross rule atom proposition specifically comprises the following steps: and judging the authenticity of the formalized cross gauges at each time point according to the authenticity of the cross gauge atom proposition at each time point.
7. The method of claim 2, further comprising:
classifying the grade of the traffic rule high-grade proposition;
and combining the cross rule atom proposition, the preset conjunction words and the low-level cross rule high-level proposition to obtain the high-level cross rule high-level proposition.
8. The method of claim 1, wherein the parameter information of the transportation participant at least comprises: participant inherent attribute information, time information, environment information, location information, speed information, attitude information, lighting information, sound information, and status information.
9. The method of claim 2, wherein the preset conjuncts comprise: a logic operator and a time sequence operator;
the logical operator conjuncts include at least: negation, conjunctive, disjunctive, derivational, and equivalents;
the temporal operator conjunction word comprises at least: the next moment, until, always, finally, always occurs within this time period and will occur within this time period.
10. An automated driving vehicle traffic regulation compliance simulation test system, comprising:
the acquisition module is used for acquiring parameter information of the traffic participants;
the generating module is used for acquiring the formalized intersection rule; the formal cross rules comprise cross rule atom propositions extracted according to a preset classification principle;
the judging module is used for judging the truth of the traffic rule atom proposition according to the parameter information of the traffic participant; and judging the authenticity of the formal cross rules according to the authenticity of the atomic proposition of the cross rules, and representing whether the traffic participant obeys the cross rules or not by using the authenticity of the formal cross rules.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110564766.2A CN113254336B (en) | 2021-05-24 | 2021-05-24 | Method and system for simulation test of traffic regulation compliance of automatic driving automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110564766.2A CN113254336B (en) | 2021-05-24 | 2021-05-24 | Method and system for simulation test of traffic regulation compliance of automatic driving automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113254336A true CN113254336A (en) | 2021-08-13 |
| CN113254336B CN113254336B (en) | 2022-11-08 |
Family
ID=77183905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110564766.2A Active CN113254336B (en) | 2021-05-24 | 2021-05-24 | Method and system for simulation test of traffic regulation compliance of automatic driving automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113254336B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114077797A (en) * | 2021-11-29 | 2022-02-22 | 公安部道路交通安全研究中心 | Automatic driving test scene design method and device based on road traffic regulations |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108958066A (en) * | 2017-05-19 | 2018-12-07 | 百度在线网络技术（北京）有限公司 | Emulation test method and device |
| CN108986473A (en) * | 2017-05-31 | 2018-12-11 | 蔚来汽车有限公司 | Vehicle mounted traffic unlawful practice identification and processing system and method |
| CN109849816A (en) * | 2019-02-01 | 2019-06-07 | 公安部交通管理科学研究所 | A kind of autonomous driving vehicle driving ability evaluating method, apparatus and system |
| CN109872392A (en) * | 2019-02-19 | 2019-06-11 | 北京百度网讯科技有限公司 | Man-machine interaction method and device based on high-precision map |
| CN110263381A (en) * | 2019-05-27 | 2019-09-20 | 南京航空航天大学 | A kind of automatic driving vehicle test emulation scene generating method |
| US20190317496A1 (en) * | 2018-04-11 | 2019-10-17 | GM Global Technology Operations LLC | Method and apparatus for automatical rule learning for autonomous driving |
| CN110597711A (en) * | 2019-08-26 | 2019-12-20 | 湖南大学 | Automatic driving test case generation method based on scene and task |
| CN110597086A (en) * | 2019-08-19 | 2019-12-20 | 深圳元戎启行科技有限公司 | Simulation scene generation method and unmanned system test method |
| CN110673636A (en) * | 2019-09-30 | 2020-01-10 | 上海商汤临港智能科技有限公司 | Unmanned simulation test system and method, and storage medium |
| US20200050719A1 (en) * | 2018-08-09 | 2020-02-13 | Sick Ag | Determining One or More Characteristic Values and Simulating Traffic for an Autonomously Trafficable Environment |
| CN110795818A (en) * | 2019-09-12 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Method and device for determining virtual test scene, electronic equipment and storage medium |
| CN110874738A (en) * | 2018-09-02 | 2020-03-10 | 许先学 | Method and device for collecting and processing traffic violation information of intelligent traffic control and intelligent traffic control |
| WO2020060478A1 (en) * | 2018-09-18 | 2020-03-26 | Sixan Pte Ltd | System and method for training virtual traffic agents |
| US20200125472A1 (en) * | 2018-10-17 | 2020-04-23 | Toyota Research Institute, Inc. | Systems and methods for automatic test generation |
| US10636295B1 (en) * | 2019-01-30 | 2020-04-28 | StradVision, Inc. | Method and device for creating traffic scenario with domain adaptation on virtual driving environment for testing, validating, and training autonomous vehicle |
| CN111409648A (en) * | 2019-01-08 | 2020-07-14 | 上海汽车集团股份有限公司 | Driving behavior analysis method and device |
| CN111651712A (en) * | 2020-05-27 | 2020-09-11 | 北京航空航天大学 | Method and system for evaluating complexity of test scene of intelligent automobile |
| CN111785025A (en) * | 2020-07-22 | 2020-10-16 | 北京航空航天大学 | Novel flexible bus dispatching method based on automatic driving module bus |
| CN112819968A (en) * | 2021-01-22 | 2021-05-18 | 北京智能车联产业创新中心有限公司 | Test method and device for automatic driving vehicle based on mixed reality |
-
2021
- 2021-05-24 CN CN202110564766.2A patent/CN113254336B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108958066A (en) * | 2017-05-19 | 2018-12-07 | 百度在线网络技术（北京）有限公司 | Emulation test method and device |
| CN108986473A (en) * | 2017-05-31 | 2018-12-11 | 蔚来汽车有限公司 | Vehicle mounted traffic unlawful practice identification and processing system and method |
| US20190317496A1 (en) * | 2018-04-11 | 2019-10-17 | GM Global Technology Operations LLC | Method and apparatus for automatical rule learning for autonomous driving |
| US20200050719A1 (en) * | 2018-08-09 | 2020-02-13 | Sick Ag | Determining One or More Characteristic Values and Simulating Traffic for an Autonomously Trafficable Environment |
| CN110874738A (en) * | 2018-09-02 | 2020-03-10 | 许先学 | Method and device for collecting and processing traffic violation information of intelligent traffic control and intelligent traffic control |
| WO2020060478A1 (en) * | 2018-09-18 | 2020-03-26 | Sixan Pte Ltd | System and method for training virtual traffic agents |
| US20200125472A1 (en) * | 2018-10-17 | 2020-04-23 | Toyota Research Institute, Inc. | Systems and methods for automatic test generation |
| CN111409648A (en) * | 2019-01-08 | 2020-07-14 | 上海汽车集团股份有限公司 | Driving behavior analysis method and device |
| US10636295B1 (en) * | 2019-01-30 | 2020-04-28 | StradVision, Inc. | Method and device for creating traffic scenario with domain adaptation on virtual driving environment for testing, validating, and training autonomous vehicle |
| CN109849816A (en) * | 2019-02-01 | 2019-06-07 | 公安部交通管理科学研究所 | A kind of autonomous driving vehicle driving ability evaluating method, apparatus and system |
| CN109872392A (en) * | 2019-02-19 | 2019-06-11 | 北京百度网讯科技有限公司 | Man-machine interaction method and device based on high-precision map |
| CN110263381A (en) * | 2019-05-27 | 2019-09-20 | 南京航空航天大学 | A kind of automatic driving vehicle test emulation scene generating method |
| CN110597086A (en) * | 2019-08-19 | 2019-12-20 | 深圳元戎启行科技有限公司 | Simulation scene generation method and unmanned system test method |
| CN110597711A (en) * | 2019-08-26 | 2019-12-20 | 湖南大学 | Automatic driving test case generation method based on scene and task |
| CN110795818A (en) * | 2019-09-12 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Method and device for determining virtual test scene, electronic equipment and storage medium |
| CN110673636A (en) * | 2019-09-30 | 2020-01-10 | 上海商汤临港智能科技有限公司 | Unmanned simulation test system and method, and storage medium |
| CN111651712A (en) * | 2020-05-27 | 2020-09-11 | 北京航空航天大学 | Method and system for evaluating complexity of test scene of intelligent automobile |
| CN111785025A (en) * | 2020-07-22 | 2020-10-16 | 北京航空航天大学 | Novel flexible bus dispatching method based on automatic driving module bus |
| CN112819968A (en) * | 2021-01-22 | 2021-05-18 | 北京智能车联产业创新中心有限公司 | Test method and device for automatic driving vehicle based on mixed reality |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114077797A (en) * | 2021-11-29 | 2022-02-22 | 公安部道路交通安全研究中心 | Automatic driving test scene design method and device based on road traffic regulations |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113254336B (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110597711B (en) | Automatic driving test case generation method based on scene and task | |
| CN110675656B (en) | Intelligent vehicle lane change early warning method based on instantaneous risk identification | |
| US20220187834A1 (en) | Generating trajectories for autonomous vehicles | |
| US20190143992A1 (en) | Self-driving learning apparatus and method using driving experience information | |
| US20080027607A1 (en) | Assistance System for Motor Vehicles | |
| US20220169214A1 (en) | Emergency braking for autonomous vehicles | |
| CN113212454B (en) | Method and device for adjusting running state of vehicle, computer equipment and storage medium | |
| CN111583711A (en) | Behavior control method and behavior control device | |
| CN109910880B (en) | Vehicle behavior planning method and device, storage medium and terminal equipment | |
| CN113320545A (en) | Intersection behavior prediction decision method based on line-control intelligent vehicle | |
| Huang et al. | Study on the test scenarios of level 2 automated vehicles | |
| CN113254336B (en) | Method and system for simulation test of traffic regulation compliance of automatic driving automobile | |
| Xie et al. | Study on the controlled field test scenarios of automated vehicles | |
| CN111476491A (en) | Vehicle motion simulation analysis method in urban traffic scene | |
| CN115731695A (en) | Scene security level determination method, device, equipment and storage medium | |
| CN112896166A (en) | Vehicle lane changing method and device and electronic equipment | |
| CN116842688A (en) | Online compliance verification system oriented to automatic driving decision algorithm | |
| CN115985096A (en) | Evaluation system and method under road traffic scene of navigation driving assistance system | |
| WO2023133758A1 (en) | Test method and apparatus | |
| CN115855531A (en) | Test scene construction method, device and medium for automatic driving automobile | |
| CN115092186A (en) | Vehicle automatic driving method and device, electronic equipment and storage medium | |
| CN115431961A (en) | Vehicle control method and device, vehicle and storage medium | |
| WO2020202818A1 (en) | Vehicle control device, vehicle control method, and program | |
| CN114003582A (en) | Traffic accident foreground derivation method for automatic driving vehicle and storage medium | |
| Kale et al. | Simulation based design and development of test track for adas functions validation and verification with respect to indian scenario |
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 |