CN110867097A - Autonomous decision-making method for collision avoidance of highway confluence area - Google Patents
Autonomous decision-making method for collision avoidance of highway confluence area Download PDFInfo
- Publication number
- CN110867097A CN110867097A CN201911115216.1A CN201911115216A CN110867097A CN 110867097 A CN110867097 A CN 110867097A CN 201911115216 A CN201911115216 A CN 201911115216A CN 110867097 A CN110867097 A CN 110867097A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- vehicles
- automatic driving
- cost
- adjustment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an autonomous decision-making method for collision avoidance in a highway confluence area, which comprises the following specific steps: initially arranging the conflict risk avoiding sequence of the automatic driving vehicles by using the time demand intensity of the vehicles and the priority levels of the types of the vehicles; when the time demand intensity and the vehicle type priority level are the same, a vehicle driving intention interaction model is established based on a cooperative game theory, and the collision risk avoiding sequence of the automatically driven vehicles is finally arranged; establishing a vehicle driving intention quantification model based on probability subtraction, and realizing intention quantification on the automatic driving vehicle needing driving behavior adjustment; and realizing the automatic decision of automatically driving the vehicle for collision and risk avoidance on the basis of the collision and risk avoidance sequencing and the vehicle driving intention quantification result. The invention has the beneficial effects that: the method actually provides decision-making suggestions for the collision avoidance process of the automatically driven vehicles and provides technical service support for further development of the networked automatically driven vehicles.
Description
Technical Field
The invention relates to the technical field of networked automatic driving vehicles, in particular to an autonomous decision-making method for collision avoidance in a highway confluence area.
Background
The current main development direction of the intelligent traffic system is the automatic driving intelligent vehicle-road cooperation technology, the development center of gravity of the intelligent traffic system is transited to the process of group intelligence and environment intelligence interaction from a single intelligence stage, advanced wireless communication and internet technologies provide guarantee for interconnection and intercommunication among automatic driving vehicles, and the information sharing degree among the automatic driving vehicles is greatly improved. The advantages and support of the technology cannot be fully utilized in the latest automatic risk avoiding technology of the automatic driving vehicle to realize mutual negotiation decision making of the automatic driving vehicle in the risk avoiding process, and the influence of factors such as vehicle types, time demand intensity, different vehicle running preference and the like on the automatic driving vehicle in the automatic risk avoiding process cannot be considered in the existing automatic risk avoiding technology, so that the requirements of the automatic driving vehicle on mutual cooperation and automatic decision making risk avoiding cannot be met due to the fact that one side is considered, the practicability is poor.
Disclosure of Invention
The invention aims to provide an autonomous decision-making method for collision and danger avoidance in a highway confluence area, which fully considers the time demand intensity and the vehicle type characteristic difference of an automatic driving vehicle in the actual running process, realizes the autonomous decision-making for collision and danger avoidance of the vehicle based on the time demand intensity priority and the vehicle type priority, combines the practical conditions, has good practicability and can meet the requirement of the automatic driving vehicle on collision and autonomous decision and danger avoidance.
In order to achieve the above object, the present invention provides the following solutions:
step 1: comparing the danger avoiding and releasing priority levels of the two vehicles based on the time demand intensity of the vehicles, if the time demand intensity of the two automatic driving vehicles is the same, turning to the step 2, if the time demand intensity of the two automatic driving vehicles is different, determining the danger avoiding and releasing sequence of the two vehicles, and then turning to the step 4.
Step 2: comparing the danger avoiding and releasing priority levels of the two vehicles based on the vehicle types, if the vehicle types of the two automatic driving vehicles are consistent, turning to the step 3, if the vehicle types are different, determining the sequence of danger avoiding and releasing of the two vehicles according to the vehicle type priority levels, and then turning to the step 4.
And step 3: and (5) carrying out driving intention interaction on the two automatic driving vehicles, determining a risk avoidance and release scheme of the two automatic driving vehicles according to the driving intention interaction result of the vehicles, and then turning to the step 5.
And 4, step 4: and (5) determining whether the two vehicles need to be adjusted according to the danger avoiding and releasing sequence of the two automatic driving vehicles, and turning to the step 5 after determining whether each vehicle needs to be adjusted.
And 5: and (6) determining the adjusting mode of the vehicle by the automatic driving vehicle needing behavior adjustment, and turning to step 6.
Step 6: and adjusting the running behavior of the automatic driving vehicle.
In the step 1, the danger avoiding and releasing priority levels of the two vehicles are compared based on the time demand intensity of the vehicles, wherein the time demand intensity of the ith automatic driving vehicle is represented as tau, and
(i-A, B, a for autonomous vehicle a, B for autonomous vehicle B, l for the length of autonomous vehicle i from the potential conflict point, v for the current situational speed of autonomous vehicle i). The time demand intensity priority comparison is performed for two potential conflicting autonomous vehicles according to τ.
The step 2 of comparing the risk avoidance and release priority levels of the two vehicles based on the vehicle types is carried out on the basis that the time demand intensity of the two vehicles is the same in the step 1. The vehicle types are divided primarily from their transport functions and job tasks, and vehicle type prioritization is performed for two potentially conflicting autonomous vehicles.
And in the step 3, the driving intention interaction of the two automatic driving vehicles is carried out on the basis that the time requirement strength is the same in the step 1 and the priority levels of the vehicle types are the same in the step 2, and the quantitative process of the intention interaction of the two automatic driving vehicles is mainly based on the cooperative game as a theoretical basis. The basic goal of cooperative gaming is to maximize the benefits of a team, or maximize one party's benefits without the other party's benefits being threatened or even lost. According to the 'benefit game' characteristic of the automatic driving vehicle in the process of solving the potential conflict decision, the cooperation game theory is introduced into the interaction process of the driving intention of the automatic driving vehicle, and the method has certain rationality and strong practicality.
The autonomous vehicle driving intention interaction process is mainly divided into the following steps.
Step 3-1: and inputting payment cost of each alliance.
Step 3-2: and quantizing the adjustment intention of the automatic driving vehicle by using a random function, and inputting the adjustment intention of the automatic driving vehicle and the payment cost of each alliance into the calculation of the total virtual cost function.
Step 3-3: and calculating the total virtual cost of each alliance, and comparing the total virtual cost of each alliance.
Step 3-4: and outputting the minimum value of the total virtual cost of the alliance and determining the alliance adjustment scheme corresponding to the minimum value of the total virtual cost.
Step 3-5: and judging whether the adjustment scheme corresponding to the minimum value of the total virtual cost needs to be adjusted by two vehicles at the same time, if not, turning to the step 3-6, and if so, turning to the step 3-7.
Step 3-6: and 3, determining that the conflict resolution sequence is arranged in front of the vehicles which do not need to be adjusted, determining that the conflict resolution sequence is arranged in back of the vehicles which need to be adjusted, and then, turning to the step 3-9 after the conflict resolution sequence is determined.
Step 3-7: and calculating the contribution value of each coalition member in the coalition adjustment scheme corresponding to the minimum value of the total virtual cost.
Step 3-8: comparing the contribution values of all the coalition members in the adjustment scheme, determining that the conflict resolution sequence of the automatic driving vehicles corresponding to the smaller contribution values is arranged in front, determining that the conflict resolution sequence of the automatic driving vehicles corresponding to the larger contribution values is arranged in back, and switching to the step 3-9 after the conflict resolution sequence is determined.
Step 3-9: and (4) switching to a two-vehicle conflict resolution logic step 4.
Wherein the payment cost x of each coalition member in the step 3-1i(i-A, B, a stands for autonomous vehicle a and B stands for autonomous vehicle B) according toThe positional relationship between two autonomous vehicles and the speed of travel, taking into account the length l of the autonomous vehicle from the potential conflict pointiThe farther away the autonomous vehicle is, the safer it is, xiWith liIs increased and decreased; speed v of traveliThe larger the autonomous vehicle will be closer to the conflict point in a short time, xiWith viIs increased by increasing the action weight k of the two parameters1,k2Determining the origin equation of the payment cost of the coalition members as
The step 3-2 of quantifying the driving intention of the automatic driving vehicle means that a random function is used for realizing a quantifying process of the driving intention of the automatic driving vehicle, and the parameters a and B are used for representing the adjustment intentions of the two automatic driving vehicles, so that the payment coefficients a and B of the automatic driving vehicle A and the automatic driving vehicle B are determined, if the automatic driving vehicle wants to perform behavior adjustment, the payment coefficient value is 1, and if the automatic driving vehicle does not want to perform behavior adjustment, the payment coefficient value is greater than 1.
The process of calculating the total virtual cost of each alliance in the step 3-3 is that 4 optional adjustment behaviors of the two automatic driving vehicles are determined, j is determined as a serial number corresponding to each alliance, and when j is set to be 1, A, B two vehicles are selected to be adjusted; when j is 2, the vehicle A selects adjustment, and the vehicle B does not perform adjustment; when j is 3, the vehicle B selects adjustment, and the vehicle A does not perform adjustment; when j is 4, A, B neither vehicle selects adjustment, and at this time, both vehicles will have collision risk, so the virtual payment cost will be infinite, and this scheme (j is 4) will be directly excluded in the actual operation process.
Then, according to the parameter quantification and calibration in the step 3-1, the step 3-2 and the step 3-3, the calculation formula for determining the total payment cost of each alliance is
Said step 3-4 outputting federation virtualizationThe federate adjustment scheme process corresponding to the minimum virtual cost total is determined, comparison of value size is carried out according to calculation results of payment cost total of all federates, and a calculation formula for determining the minimum payment cost total is cmin(xA,xB)＝min(cj) According to c, therebymin(xA,xB)＝min(cj) The value of j in (1) determines the corresponding federation adjustment scheme.
The process of calculating the contribution value of each coalition member in the coalition adjustment scheme corresponding to the minimum virtual total cost in the steps 3-7 is that the total cost to be paid by the vehicles A and B in the scheme under the non-cooperative game condition is determined firstly, and the formula is
And then calculating A, B payment cost deltac saved by two vehicles under the cooperative game condition, wherein the calculation formula is
Finally, the contribution value of each member in the coalition adjustment scheme corresponding to the minimum value of the total virtual cost is calculated, and the comparison algorithm is
And 4, determining whether the two automatic driving vehicles need to be adjusted according to the danger avoiding and releasing sequence of the two automatic driving vehicles, wherein the automatic driving vehicles with the prior danger avoiding and releasing sequence are determined to keep the original driving state unchanged according to the time demand intensity in the step 1 and the sequencing result determined by the vehicle type priority in the step 2, and the automatic driving vehicles with the later danger avoiding and releasing sequence perform the automatic adjustment of danger avoiding and releasing according to the automatic driving vehicles with the prior danger avoiding and releasing sequence.
And 5, determining the adjusting mode of the vehicle by the automatic driving vehicle needing behavior adjustment in the step 5, namely establishing an automatic driving vehicle intention probability updating model by using a probability subtraction method.
When the automatic driving vehicle after the risk avoidance and release sequence faces the adjustment of the selectable behaviors, the probability that the automatic driving vehicle selects the real-time adjustable behaviors is changed in real time by taking the virtual equivalence of the quantized values of the intentions of the automatic driving vehicle as an initial state, and the quantitative characterization process of the intentions of the automatic driving vehicle for decision-making and adjustment behaviors is realized. Assuming that the alternative adjustment behaviors are speed regulation (VC) and lane regulation (HC), respectively, and the probabilities of initial occurrence are both equal and sum to 1, equation P is satisfiedVC＝PHC,PVC+PHC1. When the automatic driving vehicle is in the condition of potential conflict environment, the probability of one regulation behavior randomly appearing in the two regulation modes is reduced to the original one
In order to satisfy the initial condition that the sum of the probability values is 1, the probability of another adjustment mode naturally changes in an expanding manner.
The probability reduction process is
P 'if the probability of satisfaction is 1'VC＝1-P'HC. Or with probability the reduction process is
If the probability of 1 is satisfied, P is "HC＝1-P”VC。
When the automatic driving vehicle adjusts the intention probability relation to satisfy P'VC＞P'HCOr P'VC＞P”HCAnd if not, adjusting the speed of the corresponding vehicle, otherwise, adjusting the lane.
The invention has the beneficial effects that: the time demand intensity and the vehicle type characteristic difference of the automatic driving vehicle in the actual running process are fully considered, the vehicle conflict autonomous risk avoiding decision based on the time demand intensity priority and the vehicle type priority is realized, the practical condition is combined, the practicability is good, and the requirement of the automatic driving vehicle for conflict autonomous decision risk avoiding can be met.
Drawings
Fig. 1 is a flowchart illustrating an embodiment of an autonomous decision method for collision risk avoidance according to the present invention;
FIG. 2 is a flow chart of an interaction conflict risk avoidance decision-making process of driving intention of an automatic driving vehicle based on a cooperative game theory, provided by an embodiment of the invention;
FIG. 3 is a schematic diagram illustrating analysis and variation of parameters in a simulation process according to an embodiment of the present invention;
fig. 4 is a comparison graph of the theoretical cost saving rate of the cooperative game in the simulation process of the embodiment of the present invention.
Detailed Description
The collision risk avoidance autonomous decision method for an autonomous driving vehicle according to the present invention will be described in detail with reference to the accompanying drawings and specific embodiments. The embodiment is only used as an illustration of a situation in the technology of the present invention, and the scope of the present invention patent is not limited to the embodiment.
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Fig. 1 shows a flowchart of an autonomous decision-making method for collision avoidance of an autonomous driving vehicle according to an embodiment of the present invention. As shown in fig. 1, the autonomous decision-making method for collision avoidance of an autonomous driving vehicle according to the embodiment of the present invention includes the following steps:
firstly, the running state and the running environment of the automatic driving vehicles are known, the running state, the transportation task, the vehicle type and the like of each automatic driving vehicle can be acquired by other vehicles, parameters including real-time distance, flight speed, distance from a potential conflict point and the like between each automatic driving vehicle can be acquired, and high-quality information interaction between the two automatic driving vehicles can be realized.
Step 1: and sequentially arranging the risk avoidance and release priority levels of the two vehicles based on the time demand intensity of the vehicles.
In the step, the two automatic driving vehicles are subjected to conflict risk avoiding sequence arrangement according to the time demand intensity, and the basis is that the shortest time interval of the whole transmission and reaction process is considered. The comparison of the autonomous vehicle with the actual intensity of demand is further described herein with reference to 0.6s, based on a related study of the values of existing autonomous vehicle parameters.
When in use
Defining that the time demand intensity of two automatic driving vehicles is the same; when in use
When is, i.e. tauA＞τBSpecifying that the autonomous vehicle time demand intensity of number a is greater than the autonomous vehicle time demand intensity of number B, thereby determining that the autonomous vehicle of number a is ranked prior to the autonomous vehicle of number B;
when is, i.e. tauA＜τBIn the meantime, it is explained that the autonomous vehicle time demand intensity of number a is smaller than the autonomous vehicle time demand intensity of number B, so that the autonomous vehicle of number B is determined to be sorted prior to the autonomous vehicle of number a.
The time demand intensity comparison result of the two automatic driving vehicles has two results that the time demand intensities of the two automatic driving vehicles are the same and different.
And if the time demand intensities of the automatic driving vehicles are different, determining the conflict risk avoiding arrangement sequence of the automatic driving vehicles according to the time demand intensity relationship, then entering the step 4, keeping the original driving state of the automatic driving vehicles with the priority of the conflict risk avoiding decision sequence unchanged, and adjusting the driving behaviors of the automatic driving vehicles with the priority of the conflict risk avoiding decision sequence.
And if the time demand intensity of the two automatic driving vehicles is the same, entering the step 2 to carry out the collision risk avoiding sequence arrangement of the automatic driving vehicles based on the vehicle types.
Step 2: the two vehicle risk avoidance and disengagement priority levels are sequentially arranged based on the vehicle types.
In the step, the danger avoiding and releasing priority levels of the two vehicles are sequentially arranged based on the vehicle types, and the vehicle type priority levels of the two potentially conflicting automatic driving vehicles are determined. According to the embodiment, the priority level sequence of each vehicle type is determined to be rescue vehicle > long-distance bus > general social vehicle according to the common vehicle types and carrying tasks of the long-distance bus, the rescue vehicle, the common social vehicle and the like.
The comparison of the priority levels of the two types of autonomous vehicles will result in two types, one with the same priority level and one with a different priority level.
And if the priority levels of the two vehicle types are different, determining the conflict risk avoiding arrangement sequence of the vehicles according to the limited levels of the vehicle types, and turning to the step 4, so that the automatic driving vehicle with the priority level of the conflict risk avoiding decision sequence keeps the original driving state unchanged, and the automatic driving vehicle with the later conflict risk avoiding decision sequence adjusts the driving behavior.
And if the priority levels of the two vehicle types are the same, the step 3 is carried out to mutually aim the driving of the two vehicles.
And step 3: the vehicle driving intentions are interactive.
In the step, the implementation of the interaction process of the vehicle driving intentions is mainly based on a cooperative game theory, the quantized result of the cost paid by the two vehicle driving intentions is input into the total function of the alliance payment costs, the minimum value of the payment costs of all the alliances is calculated, the corresponding adjustment alliance is determined according to the minimum value of the payment costs, and the adjustment scheme of the vehicle corresponding to the alliance is determined.
Fig. 2 shows a vehicle driving intention interaction collision avoidance decision flow chart based on a cooperative game theory in the autonomous collision avoidance decision method for the autonomous driving vehicle according to the embodiment of the invention. As shown in fig. 2, the vehicle driving intention interaction conflict risk avoidance decision provided by the embodiment of the present invention includes the following steps:
step 3-1: and inputting the payment cost of each coalition member.
In the step, the payment cost of each alliance member is input, wherein the payment cost source equation is
Step 3-2: and quantifying the vehicle driving intention.
In the step, the vehicle driving intention is quantized by using a random function, payment coefficients of an automatic driving vehicle A and an automatic driving vehicle B are determined, if the vehicle wants to perform behavior adjustment in the driving process, the secondary payment coefficient is determined to be 1, and if the vehicle does not want to perform behavior adjustment, the secondary payment coefficient is determined to be a number larger than 1.
Step 3-3: and calculating the total virtual cost of each alliance.
In the step, the total virtual cost of each alliance is calculated, and according to the payment cost of the alliance members in the step 3-1 and the quantification result of the vehicle driving intention in the step 3-2, the total virtual cost of each alliance is determined to be calculated according to the formula
Step 3-4: and determining a coalition adjustment scheme corresponding to the minimum value of the total virtual cost.
The step of comparing the total amount of cost payment to determine the minimum value of the total amount of output virtual cost, wherein the calculation formula is cmin(xA,xB)＝min(cj). And further determining a federation adjustment scheme corresponding to the payment cost on the basis of the determined minimum value of the federation virtual cost.
Step 3-5: and determining whether the minimum value of the total virtual cost corresponds to the adjustment scheme of the alliance and whether the adjustment of the two vehicles is needed.
In this step, a coalition adjustment scheme corresponding to the minimum value of the total amount of the virtual payment cost is determined, wherein the adjustment scheme mainly comprises two types of results of adjusting two vehicles simultaneously and only one vehicle.
And if the corresponding alliance adjustment scheme is that only one vehicle is adjusted, the step 3-6 is carried out. And if the corresponding alliance adjustment scheme is that both vehicles need to be adjusted, the step 3-7 is carried out.
Step 3-6: and determining that the conflict risk avoiding sequence of the automatic driving vehicle which does not need to be adjusted is prior, and determining that the conflict risk avoiding sequence of the automatic driving vehicle which needs to be adjusted is later.
In the step, the collision risk avoiding sequence of the two vehicles is determined, and the collision risk avoiding sequence is mainly determined according to the scheme that whether the two vehicles are adjusted or not is determined according to the alliance adjustment scheme in the step 3-5. Wherein, the vehicle collision risk avoiding sequence which does not need to be adjusted is in front, and after the vehicle collision risk avoiding sequence which needs to be adjusted is in back, the step 3-9 is carried out after the collision risk avoiding sequence is determined.
And 3-7, calculating the contribution value of the coalition members in the adjustment scheme corresponding to the minimum value of the total virtual cost.
In the step, the contribution value of each coalition member in the adjustment scheme is calculated, the total cost to be paid by the vehicle A and the vehicle B in the scheme corresponding to the minimum payment cost under the non-cooperative game condition is calculated, and the calculation formula is
And then calculating A, B payment cost deltac saved by two vehicles under the cooperative game condition, wherein the calculation formula is
And finally, calculating the contribution value of each coalition member in the cooperative game process, wherein the calculation formula is
Step 3-8: and determining the collision risk avoidance arrangement sequence of the automatic driving vehicles according to the contribution values of all the alliance members.
In the step, the conflict risk avoiding arrangement sequence of the automatic driving vehicles is determined, the contribution values of all the alliance members are compared, and the calculation formula is
And determining the priority of the collision and risk avoidance sequence of the automatic driving vehicles corresponding to the squealers according to the comparison result, and after the collision and risk avoidance sequence of the automatic driving vehicles corresponding to the automatic driving vehicles with larger values is backed up, determining the collision and risk avoidance sequence and then turning to the step 3-9.
Step 3-9: and (5) switching to a two-vehicle conflict resolution logic step 5.
The step is to transfer the determined automatic driving vehicle collision avoidance arrangement sequence to the step for 5 weeks, and then to carry out the next step.
And 4, step 4: it is determined whether each vehicle requires adjustment.
And determining whether the two vehicles need to be adjusted finally according to the progress results of the steps, and then, turning to the step 5.
And 5: the automatic driving vehicle needing behavior adjustment determines the vehicle adjustment mode according to the driving intention.
In this step, the probability that the speed regulation (VC) and the lane regulation (HC) are both equal and 1 is added according to the knowledge that the formula P is satisfiedVC＝PHC,PVC+PHC1. Will occur during the course of making vehicle intent determination-based vehicle driving behavior adjustments
P'VC＝1-P'HC. Or appear
P”HC＝1-P”VC. Therefore when the autonomous vehicle adjusts the intention probabilistic relationship to satisfy P'VC＞P'HCOr P'VC＞P”HCAnd if not, adjusting the speed of the corresponding vehicle, otherwise, adjusting the lane.
Step 6: and adjusting the running behavior of the automatic driving vehicle.
The step is carried out, namely the automatic driving vehicle carries out running behavior adjustment according to the running intention of the vehicle, so that potential conflict points are avoided smoothly, and the safe running of the vehicle is ensured.
The vehicle collision risk avoidance decision provided by the embodiment of the invention only utilizes several possible decision combinations of two automatic driving vehicles.
The embodiment of the invention uses the vehicle conflict risk avoidance decision in the simulation experimentThe initial conflict state is begin. The simulation experiment is set to have the same time requirement intensity and vehicle type of two automatic driving vehicles, and v is set respectivelyA60Km/h、vB60Km/h，vA60Km/h、vB40Km/h, and lA15m、lB15m，lA15m、lB20m, etc. The basic scene is that near a junction of ramps of the expressway, certain potential conflicts exist between the automatic driving vehicle A of the main lane and the automatic driving vehicle B which is about to enter the main lane in the ramps.
The embodiment of the invention provides several possible decision modes for vehicle collision risk avoidance decision in a simulation experiment. Namely, after a series of conflict resolution cooperative games are carried out for avoiding potential conflicts, conflict avoidance autonomous decisions are respectively made for the automatically driven vehicles B about to enter the main road and the automatically driven vehicles A of the main road in the ramp.
There may be a case where lane change adjustment is performed by a to give out an entry space for B, and B travels according to the original traveling state and gradually merges into the main lane. There may be a case where a performs acceleration adjustment to give way for B to merge into a space, and B proceeds according to the original driving state and gradually merges into the main road. And B may perform deceleration adjustment to gradually merge into the main road after reserving space for the main road. There may be various adjustment modes such as A performing lane change adjustment, B performing deceleration adjustment, and making room for B to merge into the main lane gradually
Fig. 3 shows a variation trend of the payment cost of the vehicle collision autonomous hedge decision in the simulation experiment according to the embodiment of the present invention, which is generated along with the parameter variation, and also shows a high correlation between the driving adjustment intention of the autonomous driving vehicle and the payment cost, when the driving speed and the distance between the vehicles are within a certain range, the better the cooperative game effect of the two vehicles is, the lower the payment cost of the system is.
Fig. 4 is a comparative analysis diagram of the cost savings rate of the cooperative game theory in the simulation experiment of the embodiment of the present invention, which shows that in each case of the simulation experiment, the application of the cooperative game theory actually reduces the payment cost of the system and well realizes the collision resolution avoidance decision.
Claims (10)
1. An autonomous decision-making method for collision avoidance in a highway confluence area is characterized by comprising the following steps:
step 1: comparing the danger avoiding and releasing sequence of the two vehicles based on the time demand intensity of the vehicles, if the time demand intensity of the two automatic driving vehicles is the same, turning to the step 2, if the time demand intensity of the two automatic driving vehicles is different, determining the danger avoiding and releasing sequence of the two vehicles, and then turning to the step 4;
step 2: comparing the danger avoiding and releasing priority levels of the two vehicles based on the vehicle types, if the vehicle types of the two automatic driving vehicles are consistent, turning to a step 3, if the vehicle types are different, determining the sequence of danger avoiding and releasing of the two vehicles according to the vehicle type priority levels, and then turning to a step 4;
and step 3: the two automatic driving vehicles carry out driving intention interaction, a danger avoiding and releasing scheme of the two automatic driving vehicles is determined according to a vehicle driving intention interaction result, and then the step 5 is carried out;
and 4, step 4: determining whether the two vehicles need to be adjusted according to the danger avoiding and releasing sequence of the two automatic driving vehicles, and turning to the step 5 after determining whether each vehicle needs to be adjusted;
and 5: determining the adjusting mode of the vehicle by the automatic driving vehicle needing behavior adjustment, and turning to step 6;
step 6: and adjusting the running behavior of the automatic driving vehicle.
2. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 1, characterized in that: comparing the risk avoidance and release priority levels of the two vehicles based on the time demand intensity of the vehicles, representing the time demand intensity of the ith automatic driving vehicle as tau, and
where i-A, B, a stands for autonomous vehicle a, B stands for autonomous vehicle B, l stands for length of autonomous vehicle i from potential conflict point, v stands for current shape of autonomous vehicle iPotential velocity; the time demand intensity priority comparison is performed for two potential conflicting autonomous vehicles according to τ.
3. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 1, characterized in that: comparing the risk avoidance and release priority levels of the two vehicles based on the vehicle types, and developing the vehicle types on the basis that the time demand intensity of the two vehicles is the same in step 1, wherein the vehicle types are mainly divided from the transportation function and the operation task of the vehicle types, and the vehicle type priority levels of the two potentially conflicting automatic driving vehicles are determined.
4. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 1, characterized in that: the interaction method for the driving intentions of the two automatic driving vehicles is developed on the basis that the time requirement intensity in the step 1 is the same and the vehicle type priority level in the step 2 is the same, and comprises the following steps of:
step 3-1: inputting payment cost of each alliance;
step 3-2: quantifying the adjustment intention of the automatic driving vehicle by using a random function, and inputting the adjustment intention of the automatic driving vehicle and the payment cost of each alliance into the calculation of a total virtual cost function;
step 3-3: calculating the total virtual cost of each alliance, and comparing the total virtual cost of each alliance;
step 3-4: outputting the minimum value of the virtual total cost of the alliance and determining an alliance adjusting scheme corresponding to the minimum value of the virtual total cost;
step 3-5: judging whether the adjustment scheme corresponding to the minimum value of the total virtual cost needs to be adjusted by two vehicles at the same time, if not, turning to the step 3-6, and if so, turning to the step 3-7;
step 3-6: determining that the conflict resolution sequence is arranged in front of the vehicles which do not need to be adjusted, determining that the conflict resolution sequence is arranged in back of the vehicles which need to be adjusted, and switching to the step 3-9 after the conflict resolution sequence is determined;
step 3-7: calculating contribution values of all the coalition members in the coalition adjustment scheme corresponding to the minimum value of the total virtual cost;
step 3-8: comparing the contribution values of all the coalition members in the adjustment scheme, determining that the conflict resolution sequence of the automatic driving vehicles corresponding to the smaller contribution value is arranged in front, determining that the conflict resolution sequence of the automatic driving vehicles corresponding to the larger contribution value is arranged in back, and switching to the step 3-9 after the conflict resolution sequence is determined;
step 3-9: and (4) switching to a two-vehicle conflict resolution logic step 4.
5. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 4, characterized in that: the method for inputting the payment cost of each alliance in the step 3-1 is specifically that the payment cost x of each alliance memberiWherein i is A, B, a represents the automatic driving vehicle a, B represents the automatic driving vehicle B, and the length l of the automatic driving vehicle from the potential conflict point is considered according to the position relation and the driving speed between the two automatic driving vehiclesiThe farther away the autonomous vehicle is, the safer it is, xiWith liIs increased and decreased; speed v of traveliThe larger the autonomous vehicle will be closer to the conflict point in a short time, xiWith viIs increased by increasing the action weight k of the two parameters1,k2Determining the origin equation of the payment cost of the coalition members as
6. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 4, characterized in that: in the step 3-2, the method for quantifying the driving intention of the automatic driving vehicle specifically comprises the step of utilizing a random function to realize the quantifying process of the driving intention of the automatic driving vehicle, firstly utilizing parameters a and B to represent the adjustment intention of the two automatic driving vehicles, thereby determining that a and B are the payment coefficients of the automatic driving vehicle A and the automatic driving vehicle B, if the automatic driving vehicle wants to perform behavior adjustment, the value of the payment coefficient is 1, and if the automatic driving vehicle does not want to perform behavior adjustment, the value of the payment coefficient is more than 1.
7. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 4, characterized in that: step 3-3, a method for calculating the total virtual cost of each alliance is specifically that 4 crossed combinations of selectable adjustment behaviors of two automatic driving vehicles are determined, j is determined as a corresponding serial number of each alliance, and when j is set to be 1, A, B two vehicles are selected to be adjusted; when j is 2, the vehicle A selects adjustment, and the vehicle B does not perform adjustment; when j is 3, the vehicle B selects adjustment, and the vehicle A does not perform adjustment; when j is 4, A, B neither vehicle selects adjustment, and at this time, both vehicles will have collision risk, so the virtual payment cost will be infinite, and this scheme (j is 4) will be directly excluded in the actual operation process.
8. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 4, characterized in that: outputting the minimum value of the virtual total cost of the alliances and determining the alliance adjustment scheme corresponding to the minimum value of the virtual total cost in the step 3-4, wherein the calculation formula of the total amount of the alliance payment cost is
Comparing the values according to the calculated value of the total payment cost of each alliance, and determining the calculation formula of the minimum total payment cost as cmin(xA,xB)＝min(cj) And further determining the alliance adjustment scheme corresponding to the minimum payment cost total amount.
9. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 4, characterized in that: and 3-7, calculating the contribution value of each coalition member in the coalition adjustment scheme corresponding to the minimum value of the total virtual cost, specifically, determining the total cost to be paid by the vehicles A and B in the scheme under the non-cooperative game condition by the formula
And then calculating A, B payment cost deltac saved by two vehicles under the cooperative game condition, wherein the calculation formula is
Finally, the contribution value of each member in the coalition adjustment scheme corresponding to the minimum value of the total virtual cost is calculated, and the comparison algorithm is
10. The highway confluence area collision risk avoidance autonomous decision-making method according to claim 1, characterized in that: a method for determining the regulation mode of the vehicle by the automatically driven vehicle needing behavior regulation specifically includes utilizing probability subtraction method to establish an intention probability updating model of the automatically driven vehicle, supposing that the optional regulation behaviors are speed regulation (VC) and lane regulation (HC), the initial probabilities are equal and are added to be 1, and satisfying formula PVC＝PHC,PVC+PHC1. When the automatic driving vehicle is in the condition of potential conflict environment, the probability of one regulation behavior randomly appearing in the two regulation modes is reduced to the original one
In order to meet the initial condition that the sum of the probability values is 1, the probability of the other adjusting mode naturally expands and changes;
wherein the probability reduction process is
P 'if the probability of satisfaction is 1'VC＝1-P'HC(ii) a Or with probability the reduction process is
If the probability of 1 is satisfied, P is "HC＝1-P”VC；
When the automatic driving vehicle adjusts the intention probability relation to satisfy P'VC＞P'HCOr P'VC＞P”HCAnd if not, adjusting the speed of the corresponding vehicle, otherwise, adjusting the lane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911115216.1A CN110867097A (en) | 2019-11-14 | 2019-11-14 | Autonomous decision-making method for collision avoidance of highway confluence area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911115216.1A CN110867097A (en) | 2019-11-14 | 2019-11-14 | Autonomous decision-making method for collision avoidance of highway confluence area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110867097A true CN110867097A (en) | 2020-03-06 |
Family
ID=69654031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911115216.1A Pending CN110867097A (en) | 2019-11-14 | 2019-11-14 | Autonomous decision-making method for collision avoidance of highway confluence area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110867097A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583640A (en) * | 2020-04-30 | 2020-08-25 | 重庆大学 | Ramp-up cooperative merging control method based on vehicle-road cooperation |
| CN111627205A (en) * | 2020-04-28 | 2020-09-04 | 南京理工大学 | Automatic driving vehicle and non-motor vehicle right of way distribution method based on collision risk |
| US11644835B2 (en) * | 2020-07-29 | 2023-05-09 | Toyota Research Institute, Inc. | Game-theoretic planning for risk-aware interactive agents |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101573994A (en) * | 2006-10-23 | 2009-11-04 | 泰克迪亚科技公司 | A roadside network unit using local peer groups as network groups |
| US20130265175A1 (en) * | 2012-04-04 | 2013-10-10 | Mando Corporation | Parking control apparatus and method for providing an alarm thereof |
| CN103700251A (en) * | 2013-11-27 | 2014-04-02 | 东南大学 | Variable speed limiting and ramp control coordination and optimization control method on expressway |
| CN110009940A (en) * | 2019-05-13 | 2019-07-12 | 南京航空航天大学 | A kind of General Aviation mixed running Solving Flight Conflicts method and system |
-
2019
- 2019-11-14 CN CN201911115216.1A patent/CN110867097A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101573994A (en) * | 2006-10-23 | 2009-11-04 | 泰克迪亚科技公司 | A roadside network unit using local peer groups as network groups |
| US20130265175A1 (en) * | 2012-04-04 | 2013-10-10 | Mando Corporation | Parking control apparatus and method for providing an alarm thereof |
| CN103700251A (en) * | 2013-11-27 | 2014-04-02 | 东南大学 | Variable speed limiting and ramp control coordination and optimization control method on expressway |
| CN110009940A (en) * | 2019-05-13 | 2019-07-12 | 南京航空航天大学 | A kind of General Aviation mixed running Solving Flight Conflicts method and system |
Non-Patent Citations (4)
| Title |
|---|
| MIN YANG ET AL.: ""Exploring the impact or residential relocation on modal shift in commute trips Evidence from a quasi-longitudinal analysis"", 《TRANSPORT POLICY》 * |
| 宋威龙: ""城区动态环境下智能车辆行为决策研究"", 《博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 江欣国 等: ""基于元胞自动机的高速公路临时瓶颈交通流仿真"", 《西南交通大学学报》 * |
| 盘意伟: "" 快速路入口匝道合流区的瓶颈形成机理与特性研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627205A (en) * | 2020-04-28 | 2020-09-04 | 南京理工大学 | Automatic driving vehicle and non-motor vehicle right of way distribution method based on collision risk |
| CN111627205B (en) * | 2020-04-28 | 2022-06-07 | 南京理工大学 | Method for assigning right of passage of automatic driving vehicle and non-motor vehicle |
| CN111583640A (en) * | 2020-04-30 | 2020-08-25 | 重庆大学 | Ramp-up cooperative merging control method based on vehicle-road cooperation |
| CN111583640B (en) * | 2020-04-30 | 2022-04-22 | 重庆大学 | Ramp-up cooperative merging control method based on vehicle-road cooperation |
| US11644835B2 (en) * | 2020-07-29 | 2023-05-09 | Toyota Research Institute, Inc. | Game-theoretic planning for risk-aware interactive agents |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110750877A (en) | Method for predicting car following behavior under Apollo platform | |
| CN110867097A (en) | Autonomous decision-making method for collision avoidance of highway confluence area | |
| CN111222630B (en) | Autonomous driving rule learning method based on deep reinforcement learning | |
| CN108877256B (en) | Wireless communication-based method for controlling scattered cooperative self-adaptive cruise near intersection | |
| CN108595823A (en) | A kind of computational methods of Autonomous Vehicles lane-change strategy that combining driving style and theory of games | |
| Hult et al. | An miqp-based heuristic for optimal coordination of vehicles at intersections | |
| CN103761883B (en) | A kind of self-learning method of traffic signalization and system | |
| CN113276884B (en) | Intelligent vehicle interactive decision passing method and system with variable game mode | |
| CN114265398A (en) | Trajectory planning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| Hult et al. | Optimal coordination of automated vehicles at intersections with turns | |
| CN112233413A (en) | Multilane space-time trajectory optimization method for intelligent networked vehicle | |
| CN117252318A (en) | Intelligent networking automobile group machine collaborative carpooling scheduling method and system | |
| Fabiani et al. | A mixed-logical-dynamical model for automated driving on highways | |
| Peng et al. | Bayesian persuasive driving | |
| CN111899509A (en) | Intelligent networking automobile state vector calculation method based on vehicle-road information coupling | |
| Li et al. | Research on car-following control and energy management strategy of hybrid electric vehicles in connected scene | |
| CN110853335B (en) | Cooperative fleet conflict risk avoidance autonomous decision-making method for common bottleneck sections of expressway | |
| CN109064760B (en) | Data-driven intelligent robust vehicle speed real-time planning method and system | |
| Guo et al. | Self-defensive coordinated maneuvering of an intelligent vehicle platoon in mixed traffic | |
| Keskin et al. | Altruistic control of connected automated vehicles in mixed-autonomy multi-lane highway traffic | |
| CN117671978A (en) | Vehicle formation and signal lamp cooperative control method and system based on multi-agent reinforcement learning | |
| CN117075473A (en) | Multi-vehicle collaborative decision-making method in man-machine mixed driving environment | |
| Wen et al. | TrafficMCTS: A Closed-Loop Traffic Flow Generation Framework with Group-Based Monte Carlo Tree Search | |
| Hoel et al. | An evolutionary approach to general-purpose automated speed and lane change behavior | |
| Ghaemi et al. | Driver's behavior modeling using fuzzy logic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |
|
| RJ01 | Rejection of invention patent application after publication |