WO2021103841A1 - 控制车辆 - Google Patents

控制车辆 Download PDF

Info

Publication number
WO2021103841A1
WO2021103841A1 PCT/CN2020/121620 CN2020121620W WO2021103841A1 WO 2021103841 A1 WO2021103841 A1 WO 2021103841A1 CN 2020121620 W CN2020121620 W CN 2020121620W WO 2021103841 A1 WO2021103841 A1 WO 2021103841A1
Authority
WO
WIPO (PCT)
Prior art keywords
matrix
control information
target
vehicle
target vehicle
Prior art date
Application number
PCT/CN2020/121620
Other languages
English (en)
French (fr)
Inventor
丁曙光
郭潇阳
任冬淳
付圣
钱德恒
Original Assignee
北京三快在线科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Priority to EP20893631.0A priority Critical patent/EP3919337B1/en
Priority to JP2021555012A priority patent/JP2023504945A/ja
Publication of WO2021103841A1 publication Critical patent/WO2021103841A1/zh
Priority to US17/677,671 priority patent/US20220176977A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0097—Predicting future conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B60W60/00272—Planning or execution of driving tasks using trajectory prediction for other traffic participants relying on extrapolation of current movement
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B60W60/00276—Planning or execution of driving tasks using trajectory prediction for other traffic participants for two or more other traffic participants
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0002—Automatic control, details of type of controller or control system architecture
    • B60W2050/0004—In digital systems, e.g. discrete-time systems involving sampling
    • B60W2050/0005—Processor details or data handling, e.g. memory registers or chip architecture
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation

Definitions

  • This application relates to the field of artificial intelligence technology, in particular to a control vehicle.
  • vehicle control technology can be used to drive vehicles.
  • the embodiment of the present application provides a control vehicle.
  • the technical solution is as follows:
  • a method for controlling a vehicle includes:
  • the target driving control information of the target vehicle is acquired, and the target driving control information is used to control the target vehicle.
  • the splitting the target matrix to obtain multiple sub-matrices includes:
  • the matrix in each sub-matrix is determined according to a non-parametric estimation method element.
  • the method further includes:
  • performing iterative calculation based on the matrix element to obtain the updated matrix element includes:
  • the acquiring the target driving control information of the target vehicle based on the matrix elements in each sub-matrix and the driving control information of surrounding vehicles of the target vehicle includes:
  • the target travel control information is acquired from the one or more reference travel control information.
  • the acquiring the target driving control information from the one or more reference driving control information based on the driving control information of the surrounding vehicles of the target vehicle includes:
  • the reference travel control information with the largest sum of the return values corresponding to each moment is used as the target travel control information.
  • a device for controlling a vehicle includes:
  • the first acquisition module is used to acquire vehicle information of the target vehicle and environmental information of the reference environment where the target vehicle is located;
  • the second acquisition module is configured to acquire a target matrix based on the vehicle information and the environmental information, and the elements in the target matrix are the probability values of the target vehicle moving to the next state after performing an action in the current state;
  • a splitting module for splitting the target matrix to obtain multiple sub-matrices
  • the control module is used to obtain the target driving control information of the target vehicle based on the matrix elements in each sub-matrix and the driving control information of the surrounding vehicles of the target vehicle.
  • the target driving control information is used to control the target vehicle .
  • the splitting module is configured to, based on the current state and the next state of the target vehicle in the target matrix, and sampling points and standard normal distribution functions obtained by sampling the next state, according to The non-parametric estimation method determines the matrix elements in each sub-matrix.
  • the device further includes: a calculation module, configured to perform an iterative calculation based on the matrix element for any matrix element to obtain an updated matrix element.
  • a calculation module configured to perform an iterative calculation based on the matrix element for any matrix element to obtain an updated matrix element.
  • the calculation module is configured to determine, for any matrix element, the corresponding value of the matrix element at different moments; in response to the different values of the matrix element at different moments, according to the matrix element at different times The values corresponding to the moments are calculated iteratively to obtain updated matrix elements, and the updated matrix elements correspond to the same values at different moments.
  • control module is configured to determine the probability value of one or more next states of the target vehicle based on the matrix elements in each sub-matrix; according to the correspondence between the probability value of the next state and the driving control information Relationship, one or more reference travel control information is acquired; based on the travel control information of surrounding vehicles of the target vehicle, the target travel control information is acquired from the one or more reference travel control information.
  • control module is configured to determine, based on the driving control information of the surrounding vehicles of the target vehicle, the reward value corresponding to each of the reference driving control information at one or more future moments;
  • the reference travel control information with the largest sum of the reward values corresponding to each moment is used as the target travel control information.
  • an electronic device in one aspect, includes a memory and a processor; the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement any one of this application.
  • One possible implementation provides a method of controlling the vehicle.
  • a non-transitory computer-readable storage medium is provided, and at least one instruction is stored in the non-transitory computer-readable storage medium, and the instruction is loaded and executed by a processor to implement any one of the present application Possible implementations provide the method of controlling the vehicle.
  • a computer program or computer program product includes: computer instructions, which when executed by a computer, cause the computer to implement any of the exemplary embodiments of the present application.
  • the method of controlling a vehicle provided by the embodiment.
  • Multiple sub-matrices are obtained by splitting the target matrix obtained based on vehicle information and environmental information, and the target driving control information for controlling the target vehicle is obtained based on the sub-matrices. It not only avoids the disaster of dimensionality, but also reduces the complexity of calculation, and reduces the amount of calculation required to obtain target driving control information, making the method of controlling vehicles suitable for more complex reference environments.
  • the target driving control information obtained in this embodiment also considers the driving control information of surrounding vehicles that may interact with the target vehicle, thus ensuring the safety of the target vehicle in a multi-vehicle interactive scene, making the method of controlling the vehicle applicable to A scene of multi-vehicle interaction.
  • Figure 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application.
  • Figure 2 is a flowchart of a method for controlling a vehicle provided by an embodiment of the present application
  • FIG. 3 is a structural diagram of a method for controlling a vehicle provided by an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a device for controlling a vehicle provided by an embodiment of the present application.
  • Fig. 5 is a schematic structural diagram of a terminal provided by an embodiment of the present application.
  • the related art provides a method for controlling a vehicle: obtaining a matrix corresponding to the controlled vehicle, each element in the matrix is used to indicate the probability of the controlled vehicle transitioning from the current state to the next state, and the dimension of the matrix is equal to the received state. Control the number of states that the vehicle may be in. After that, the value of each element in the matrix is determined, and the strategy is obtained based on the determined value of each element, so as to control the controlled vehicle according to the strategy.
  • the number of states that the controlled vehicle may be in is large, and the dimension of the matrix is also large, which leads to a large amount of calculations and complex calculations required to determine the value of each element in the matrix.
  • the high degree of control affects the efficiency of controlling the vehicle.
  • the embodiment of the present application provides a method for controlling a vehicle, and the method can be applied in the implementation environment as shown in FIG. 1.
  • at least one terminal 11 and a detector 12 are included.
  • the terminal 11 can communicate with the detector 12 to obtain the vehicle information of the detection target vehicle detected by the detector 12 and the environment of the reference environment where the target vehicle is located. information.
  • the terminal 11 includes, but is not limited to: any electronic product that can interact with the user through one or more methods such as keyboard, touchpad, touch screen, remote control, voice interaction or handwriting equipment, such as PC (Personal Computer, personal computer), mobile phone, smart phone, PDA (Personal Digital Assistant), wearable device, Pocket PC (Pocket PC), tablet computer, smart car machine, smart TV, smart speaker, etc.
  • PC Personal Computer
  • PDA Personal Digital Assistant
  • wearable device wearable device
  • Pocket PC Personal PC
  • tablet computer smart car machine
  • smart TV smart speaker
  • smart speaker etc.
  • terminal 11 and detector 12 are only examples, and other related or future terminals or detectors that are applicable to the embodiments of this application should also be included in the scope of protection of the embodiments of this application. Within, included here by reference.
  • an embodiment of the present application provides a method for controlling a vehicle, and the method can be applied to the terminal shown in FIG. 1. As shown in Figure 2, the method includes:
  • Step 201 Obtain vehicle information of the target vehicle and environmental information of the reference environment where the target vehicle is located.
  • the target vehicle is the vehicle to be controlled.
  • the vehicle information of the target vehicle includes vehicle state information and vehicle action information.
  • the vehicle status information includes but is not limited to the target vehicle's position (latitude and longitude), orientation (south-east, north-west), speed, acceleration, throttle, braking, and steering wheel angle.
  • the vehicle action information includes the amount of change in the aforementioned vehicle status information.
  • the reference environment where the target vehicle is located is a road, a residential area, etc.
  • the environmental information of the reference environment where the target vehicle is located includes a map of the reference environment, a drivable path, a dynamic obstacle, a static obstacle, and so on.
  • the traversable path is multiple lanes of the road
  • the dynamic obstacle is other vehicles on the road
  • the static obstacle is the isolation guardrail in the middle of the road.
  • one or more current states of the target vehicle can be determined. Still taking the reference environment as a road as an example, the lane where the target vehicle is located can be determined according to the position and orientation, and the speed and direction of the target vehicle can be determined according to the speed, acceleration, throttle amount, braking amount, and steering wheel angle. After that, one or more current states of the target vehicle can be obtained by combining the lane, driving speed and driving direction. For example, the current state of the target vehicle is driving along the first lane at a constant speed, and so on.
  • the current movement of the target vehicle can be determined through the above-mentioned vehicle movement information.
  • the change in the travel speed of the target vehicle is determined based on the change in speed, acceleration, throttle, and braking, and the change in the travel direction of the target vehicle is determined based on the change in the steering wheel angle. Therefore, the current movement of the target vehicle can be obtained according to the change in the travel speed and the change in the travel direction. For example, acceleration and deceleration actions to the left.
  • the above-mentioned information can be detected by a detector located on the target vehicle.
  • this embodiment does not limit the manner of obtaining the above information. No matter what method is used to obtain the above information, after obtaining the above information, the target matrix can be obtained based on the above information. See step 202 for details.
  • Step 202 Obtain a target matrix based on the vehicle information and environmental information.
  • step 201 it can be known that one or more current states that the target vehicle may be in and the current actions of the target vehicle can be obtained based on the vehicle information and environmental information. Assuming that the next state of the target vehicle is only related to the current state and current action, if the current action is executed in the current state, there is a certain probability that it will transition from the current state to the next state. For example, if the current state is going straight along the first lane, and the current action is accelerating to the left, the next state may be entering the second lane to the left of the first lane, or still going straight along the first lane.
  • the target matrix can be obtained according to the above one or more current states, and one or more next states to which one or more current states and current actions may transition to.
  • the elements in the target matrix are the probability values of the target vehicle moving to the next state after performing an action in the current state.
  • the dimension of the target matrix is equal to the number of current states.
  • the value of that element can be obtained by calculation.
  • the target matrix is split first, see step 203 for details.
  • Step 203 Split the target matrix to obtain multiple sub-matrices.
  • the target matrix is split into multiple sub-matrices that are multiplied, and the matrix element in each sub-matrix is still the probability value of the target vehicle moving to the next state after the target vehicle performs an action in a current state.
  • the dimension of each sub-matrix is smaller than the dimension of the target matrix, for example, each sub-matrix is a two-dimensional matrix.
  • this embodiment does not limit the dimensions of the sub-matrices.
  • the sub-matrices are three-dimensional matrices, four-dimensional matrices, etc. whose dimensions are higher than the two-dimensional matrix.
  • the target matrix is split to obtain multiple sub-matrices, including: based on the current state and the next state of the target vehicle in the target matrix, and sampling points and standards obtained by sampling the next state
  • the normal distribution function determines the matrix elements in each sub-matrix according to the non-parametric estimation method.
  • x t + 1 for the next state x t is the current state
  • x t, a t) represents x t performing a t transferred to x t + 1 of probability values (also referred to as conditional probability), p (x t + 1
  • the method provided in this embodiment further includes: for any matrix element, iterative calculation is performed based on the matrix element to obtain the updated Of matrix elements.
  • each matrix element in the matrix is the probability value of transition from the target vehicle to the next state after the target vehicle performs an action in the current state.
  • the next state corresponding to different moments is different, for example, the current state is a constant speed state, the state at the next moment is an acceleration state, and then the state at the next moment becomes a constant speed state again, resulting in different moments
  • the elements of the matrix fluctuate. Therefore, the matrix elements can be updated iteratively at different times, so that the matrix elements finally converge to a stable value, so that the target driving control information of the target vehicle can be obtained based on the stable value in the subsequent process. See step 204 for details.
  • iterative calculation is performed based on the matrix element to obtain the updated matrix element, including: for any matrix element, determining the corresponding value of the matrix element at different moments.
  • iterative calculations are performed according to the values corresponding to the matrix elements at different times to obtain updated matrix elements, and the updated matrix elements correspond to the same values at different times.
  • the situation where a matrix element corresponds to different values at different times is the situation in which the matrix elements at different times fluctuate in the above description.
  • iterative calculation is performed based on the different values of the matrix element at different times. After the iterative calculation process converges, a stable updated matrix element can be obtained.
  • a matrix element corresponding to the same value at different times that is, the matrix element at a different time does not fluctuate
  • a matrix element has a different value less than the number threshold among the corresponding values at different times (that is, different The fluctuation degree of the matrix element at time is small)
  • the target driving control information of the target vehicle can be directly obtained based on the matrix element.
  • this embodiment does not limit the value of the number threshold.
  • Step 204 Obtain the target driving control information of the target vehicle based on the matrix elements in each sub-matrix and the driving control information of the surrounding vehicles of the target vehicle, and control the target vehicle according to the target driving control information.
  • the driving control information refers to the actions that the vehicle can perform.
  • driving control information includes but is not limited to driving at a constant speed along the current road, accelerating driving along the current road, driving at a reduced speed along the current road, changing lanes to the left and driving at a constant speed, and changing lanes to the left Speed up and so on.
  • driving control information includes but is not limited to driving at a constant speed along the current road, accelerating driving along the current road, driving at a reduced speed along the current road, changing lanes to the left and driving at a constant speed, and changing lanes to the left Speed up and so on.
  • obtaining the target driving control information of the target vehicle based on the matrix elements in each sub-matrix and the driving control information of the surrounding vehicles of the target vehicle includes the following steps 2041 to 2043:
  • Step 2041 Determine the probability value of one or more next states of the target vehicle based on the matrix elements in each sub-matrix.
  • the probability of the next state of the target vehicle can be determined according to the following formula (3):
  • p (x t + 1) denotes the probability value next state
  • x t represents the current state
  • a t represents the current operation
  • z t represents the current observed value
  • Equation (3) can be decomposed into equation (4), so that by the following matrix elements p
  • the surrounding vehicles are represented by the superscript v, and the probability of the next state of any surrounding vehicle can be expressed as the following decomposition form (5):
  • the joint next state probability of all surrounding vehicles is equal to the probabilistic product of the next state of each surrounding vehicle, so the joint next state probability of all surrounding vehicles is expressed as the following formula (6):
  • the target vehicle is represented by the superscript q.
  • the probability value of the next state of the target vehicle needs to be considered comprehensively for the target vehicle itself and all surrounding vehicles.
  • the next state probability of the target vehicle can be expressed as the following formula ( 8):
  • the driving control information used for the target vehicle at the current moment can be determined by the vehicle state and vehicle action in step 201.
  • the reference driving control information can be further obtained based on the probability value, see step 2042.
  • Step 2042 According to the corresponding relationship between the probability value of the next state and the driving control information, obtain one or more reference driving control information.
  • a data set storing the corresponding relationship between the probability value of the next state and the driving control information can be obtained.
  • manually set driving control information for multiple sample vehicles and store the probability value of the next state obtained by the sample vehicle executing the driving control information corresponding to the driving control information, so as to obtain the probability value of the next state and driving Correspondence of control information.
  • one or more driving control information can be determined according to the corresponding relationship in the data set, and the driving control information with the largest number among the one or more driving control information is used as the next driving control information.
  • the state's probability value refers to the driving control information. It can be seen that one or more reference driving control information can be obtained according to the probability value of one or more next states of the target vehicle.
  • this embodiment continues to select from one or more reference driving control information to obtain a target driving control information for controlling the target vehicle, see step 2043.
  • Step 2043 Based on the travel control information of the surrounding vehicles of the target vehicle, obtain target travel control information from one or more reference travel control information.
  • obtaining the target driving control information from one or more reference driving control information based on the driving control information of the surrounding vehicles of the target vehicle includes: determining each reference driving control based on the driving control information of the surrounding vehicles of the target vehicle The return value corresponding to each moment of the information at one or more moments in the future. The reference travel control information with the largest sum of the reward values corresponding to each moment is used as the target travel control information.
  • each reference driving control information includes multiple state-to-action mappings, so that when the target vehicle is in different states, the actions that need to be performed in each state can be determined based on the multiple state-to-action mappings. .
  • the constant speed state and the acceleration action are mapped, so that when the target vehicle is in the constant speed state, the action that the target vehicle needs to perform is to accelerate and overtake.
  • the reward value is used to indicate the pros and cons of the actions performed by the target vehicle, and the pros and cons of the actions performed by the target vehicle need to be determined in conjunction with the driving control information of the surrounding vehicles. Therefore, the reward value corresponding to the action performed at each moment can be determined based on the driving control information of the surrounding vehicles.
  • the target vehicle performing the action collides with surrounding vehicles based on the driving control information of the surrounding vehicles. If it is determined that a collision occurs, it means that the action effect is poor, and the reward value corresponding to the action at that moment is a negative value (penalty value). Correspondingly, if it is determined that no collision will occur, the reward value corresponding to the action at that moment is a positive value (reward value).
  • the reward value of the action can also be determined according to the driving mode set for the target vehicle. For example, in the efficient mode, the reward value of the acceleration and overtaking action is higher than the reward value of the deceleration and follow action; in the normal mode, the reward value of the deceleration and overtaking action is equal; in the safe mode, the reward value of the acceleration and overtaking action is lower than The return value of the deceleration following action.
  • the target vehicle determines the reward value corresponding to the action performed at each time according to the mapping between the state and the action included in the reference driving control information
  • the reward corresponding to each time can be reported
  • the numerical values are summed and calculated, and the reference driving control information with the largest sum of the return values corresponding to each moment is used as the target driving control information.
  • ⁇ * represents the target driving control information
  • t represents the time
  • t ⁇ H H can be set according to experience
  • ⁇ represents the discount factor
  • the value of the discount factor is a non-negative number not greater than 1, which is used to indicate future returns
  • R is the return value.
  • the target driving control information can be used to control the target vehicle.
  • the actions that the target vehicle needs to perform are determined from the multiple maps included in the target driving control information, so as to control the target vehicle according to the target driving control information.
  • this embodiment splits the target matrix obtained based on vehicle information and environmental information to obtain multiple sub-matrices, and obtains target driving control information for controlling the target vehicle based on the sub-matrices. It not only avoids the disaster of dimensionality, but also reduces the complexity of calculation, and reduces the amount of calculation required to obtain target driving control information, so that the method of controlling a vehicle is suitable for a more complicated reference environment.
  • the target driving control information acquired in this embodiment also considers the driving control information of surrounding vehicles that may interact with the target vehicle, thus ensuring the safety of the target vehicle in a multi-vehicle interactive scene, making the method of controlling vehicles suitable for multiple vehicles. The scene of car interaction.
  • this embodiment also uses the above-mentioned non-parametric estimation method to determine the matrix elements in each sub-matrix, which has higher computational efficiency and better robustness.
  • an embodiment of the present application provides a device for controlling a vehicle.
  • the device includes:
  • the first acquisition module 401 is configured to acquire vehicle information of the target vehicle and environmental information of the reference environment where the target vehicle is located;
  • the second acquisition module 402 is configured to acquire a target matrix based on vehicle information and environmental information, and the elements in the target matrix are the probability values of the target vehicle moving to the next state after performing an action in the current state;
  • the splitting module 403 is used to split the target matrix to obtain multiple sub-matrices
  • the control module 404 is configured to obtain the target driving control information of the target vehicle based on the matrix elements in each sub-matrix and the driving control information of the surrounding vehicles of the target vehicle, and the target driving control information is used to control the target vehicle.
  • the splitting module 403 is used to determine each state based on the current state and the next state of the target vehicle in the target matrix, as well as the sampling points obtained by sampling the next state and the standard normal distribution function, according to a non-parametric estimation method.
  • the device further includes: a calculation module for performing an iterative calculation based on the matrix element for any matrix element to obtain an updated matrix element.
  • the calculation module is used to determine the corresponding value of the matrix element at different times for any matrix element; in response to the different values of the matrix elements at different times, iterative calculations are performed according to the values corresponding to the matrix elements at different times , Get the updated matrix element, and the updated matrix element corresponds to the same value at different moments.
  • control module 404 is configured to determine the probability value of one or more next states of the target vehicle based on the matrix elements in each sub-matrix; according to the corresponding relationship between the probability value of the next state and the driving control information, obtain One or more reference travel control information; based on the travel control information of the surrounding vehicles of the target vehicle, the target travel control information is obtained from the one or more reference travel control information.
  • control module 404 is configured to determine, based on the driving control information of the surrounding vehicles of the target vehicle, the reward value corresponding to each of the reference driving control information at one or more times in the future; The reference travel control information with the largest sum of return values is used as the target travel control information.
  • this embodiment splits the target matrix obtained based on vehicle information and environmental information to obtain multiple sub-matrices, and obtains target driving control information for controlling the target vehicle based on the sub-matrices. It not only avoids the disaster of dimensionality, but also reduces the complexity of calculation, and reduces the amount of calculation required to obtain target driving control information, so that the method of controlling a vehicle is suitable for a more complicated reference environment.
  • the target driving control information acquired in this embodiment also considers the driving control information of surrounding vehicles that may interact with the target vehicle, thus ensuring the safety of the target vehicle in a multi-vehicle interactive scene, making the method of controlling vehicles suitable for multiple vehicles. The scene of car interaction.
  • this embodiment also uses the above-mentioned non-parametric estimation method to determine the matrix elements in each sub-matrix, which has higher computational efficiency and better robustness.
  • the terminal 500 is a portable mobile terminal, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, Motion Picture Expert Compression Standard Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer) IV, the dynamic image expert compresses the standard audio level 4) Player, laptop or desktop computer.
  • the terminal 500 may also be called user equipment, portable terminal, laptop terminal, desktop terminal and other names.
  • the terminal 500 includes a processor 501 and a memory 502.
  • the processor 501 includes one or more processing cores, such as a 4-core processor, a 5-core processor, and so on.
  • the processor 501 adopts at least one hardware form among DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array, Programmable Logic Array).
  • the processor 501 includes a main processor and a coprocessor.
  • the main processor is a processor used to process data in an awake state, and is also called a CPU (Central Processing Unit, central processing unit);
  • the processor is a low-power processor used to process data in the standby state.
  • the processor 501 is integrated with a GPU (Graphics Processing Unit, image processor), and the GPU is used for rendering and drawing content that needs to be displayed on the display screen.
  • the processor 501 further includes an AI (Artificial Intelligence) processor, and the AI processor is used to process computing operations related to machine learning.
  • AI Artificial Intelligence
  • the memory 502 includes one or more computer-readable storage media, and the computer-readable storage media is non-transitory, or non-transitory.
  • the memory 502 also includes a high-speed random access memory and a non-volatile memory, such as one or more magnetic disk storage devices and flash memory storage devices.
  • the non-transitory computer-readable storage medium in the memory 502 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 501 to implement the control vehicle provided by the method embodiment of the present application. Methods.
  • the terminal 500 may optionally further include: a peripheral device interface 503 and at least one peripheral device.
  • the processor 501, the memory 502, and the peripheral device interface 503 are connected by a bus or signal line.
  • Each peripheral device is connected to the peripheral device interface 503 through a bus, a signal line or a circuit board.
  • the peripheral device includes: at least one of a radio frequency circuit 504, a touch screen 505, a camera 506, an audio circuit 507, a positioning component 508, and a power supply 509.
  • the peripheral device interface 503 can be used to connect at least one peripheral device related to I/O (Input/Output) to the processor 501 and the memory 502.
  • the processor 501, the memory 502, and the peripheral device interface 503 are integrated on the same chip or circuit board; in some other embodiments, any one of the processor 501, the memory 502, and the peripheral device interface 503 or The two can be implemented on a separate chip or circuit board, which is not limited in this embodiment.
  • the radio frequency circuit 504 is used for receiving and transmitting RF (Radio Frequency, radio frequency) signals, also called electromagnetic signals.
  • the radio frequency circuit 504 communicates with a communication network and other communication devices through electromagnetic signals.
  • the radio frequency circuit 504 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals.
  • the radio frequency circuit 504 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and so on.
  • the radio frequency circuit 504 communicates with other terminals through at least one wireless communication protocol.
  • the wireless communication protocol includes, but is not limited to: metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (Wireless Fidelity, wireless fidelity) networks.
  • the radio frequency circuit 504 further includes a circuit related to NFC (Near Field Communication), which is not limited in the embodiment of the present application.
  • the display screen 505 is used to display a UI (User Interface, user interface).
  • the UI includes graphics, text, icons, videos, and any combination of them.
  • the display screen 505 also has the ability to collect touch signals on or above the surface of the display screen 505.
  • the touch signal is input to the processor 501 as a control signal for processing.
  • the display screen 505 is also used to provide virtual buttons and/or virtual keyboards, also called soft buttons and/or soft keyboards.
  • one display screen 505 is provided on the front panel of the terminal 500; in other embodiments, there are at least two display screens 505, which are respectively provided on different surfaces of the terminal 500 or in a folding design;
  • the display screen 505 is a flexible display screen, which is arranged on the curved surface or the folding surface of the terminal 500.
  • the display screen 505 can also be configured as a non-rectangular irregular pattern, that is, a special-shaped screen.
  • the display screen 505 is made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).
  • the camera assembly 506 is used to capture images or videos.
  • the camera assembly 506 includes a front camera and a rear camera.
  • the front camera is set on the front panel of the terminal, and the rear camera is set on the back of the terminal.
  • the camera assembly 506 also includes a flash.
  • the flash is a single-color temperature flash or a dual-color temperature flash. Dual color temperature flash refers to a combination of warm light flash and cold light flash used for light compensation under different color temperatures.
  • the audio circuit 507 includes a microphone and a speaker.
  • the microphone is used to collect sound waves from the user and the environment, convert the sound waves into electrical signals and input them to the processor 501 for processing, or input to the radio frequency circuit 504 to implement voice communication.
  • the microphone is an array microphone or an omnidirectional acquisition microphone.
  • the speaker is used to convert the electrical signal from the processor 501 or the radio frequency circuit 504 into sound waves.
  • the speakers are traditional thin-film speakers, or piezoelectric ceramic speakers.
  • the speaker When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into sound waves that are audible to humans, but also convert electrical signals into sound waves that are inaudible to humans for purposes such as distance measurement.
  • the audio circuit 507 also includes a headphone jack.
  • the positioning component 508 is used to locate the current geographic location of the terminal 500 to implement navigation or LBS (Location Based Service, location-based service).
  • the positioning component 508 is a positioning component based on the GPS (Global Positioning System, Global Positioning System) of the United States, the Beidou system of China, the Grenas system of Russia, or the Galileo system of the European Union.
  • the power supply 509 is used to supply power to various components in the terminal 500.
  • the power source 509 is an alternating current, a direct current, a disposable battery, or a rechargeable battery.
  • the rechargeable battery can support wired charging or wireless charging.
  • the rechargeable battery can also be used to support fast charging technology.
  • the terminal 500 further includes one or more sensors 510.
  • the one or more sensors 510 include, but are not limited to: an acceleration sensor 511, a gyroscope sensor 512, a pressure sensor 513, a fingerprint sensor 514, an optical sensor 515, and a proximity sensor 516.
  • the acceleration sensor 510 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 500.
  • the acceleration sensor 511 can be used to detect the components of gravitational acceleration on three coordinate axes.
  • the processor 501 can control the touch screen 505 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 511.
  • the acceleration sensor 511 can also be used for game or user motion data collection.
  • the gyroscope sensor 512 can detect the body direction and the rotation angle of the terminal 500, and the gyroscope sensor 512 can cooperate with the acceleration sensor 511 to collect the user's 3D actions on the terminal 500. Based on the data collected by the gyroscope sensor 512, the processor 501 can implement the following functions: motion sensing (such as changing the UI according to a user's tilt operation), image stabilization during shooting, game control, and inertial navigation.
  • the pressure sensor 513 is disposed on the side frame of the terminal 500 and/or the lower layer of the touch screen 505.
  • the processor 501 performs left and right hand recognition or quick operation according to the holding signal collected by the pressure sensor 513.
  • the processor 501 controls the operability controls on the UI interface according to the user's pressure operation on the touch display screen 505.
  • the operability control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.
  • the fingerprint sensor 514 is used to collect the user's fingerprint.
  • the processor 501 can identify the user's identity based on the fingerprint collected by the fingerprint sensor 514, or the fingerprint sensor 514 can identify the user's identity based on the collected fingerprint. When it is recognized that the user's identity is a trusted identity, the processor 501 authorizes the user to perform related sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings.
  • the fingerprint sensor 514 is provided on the front, back or side of the terminal 500. When a physical button or a manufacturer logo is provided on the terminal 500, the fingerprint sensor 514 can be integrated with the physical button or the manufacturer logo.
  • the optical sensor 515 is used to collect the ambient light intensity.
  • the processor 501 can control the display brightness of the touch screen 505 according to the ambient light intensity collected by the optical sensor 515. Exemplarily, when the ambient light intensity is high, the display brightness of the touch screen 505 is increased; when the ambient light intensity is low, the display brightness of the touch screen 505 is decreased.
  • the processor 501 can also dynamically adjust the shooting parameters of the camera assembly 506 according to the ambient light intensity collected by the optical sensor 515.
  • the proximity sensor 516 also called a distance sensor, is usually arranged on the front panel of the terminal 500.
  • the proximity sensor 516 is used to collect the distance between the user and the front of the terminal 500.
  • the processor 501 controls the touch screen 505 to switch from the on-screen state to the off-screen state; when the proximity sensor 516 detects When the distance between the user and the front of the terminal 500 gradually increases, the processor 501 controls the touch display screen 505 to switch from the rest screen state to the bright screen state.
  • FIG. 5 does not constitute a limitation on the terminal 500, and can include more or fewer components than shown in the figure, or combine some components, or adopt different component arrangements.
  • an embodiment of the present application provides an electronic device, which includes a memory and a processor; at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor, so as to realize any possibility of the present application. Implement the method of controlling the vehicle provided by the way.
  • the embodiments of the present application provide a non-transitory computer-readable storage medium, and at least one instruction is stored in the non-transitory computer-readable storage medium.
  • the instruction is loaded and executed by a processor to implement any of the instructions in the present application.
  • One possible implementation provides a method of controlling the vehicle.
  • the embodiments of the present application provide a computer program or computer program product.
  • the computer program or computer program product includes: computer instructions.
  • the computer instructions When the computer instructions are executed by a computer, the computer realizes the control provided by any exemplary embodiment of the present application. Vehicle approach.
  • the non-transitory computer-readable storage medium mentioned above is a read-only memory, a magnetic disk or an optical disk, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Optimization (AREA)
  • Software Systems (AREA)
  • Mathematical Analysis (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

一种控制车辆的方法，包括：获取目标车辆的车辆信息以及目标车辆所在的参考环境的环境信息。基于车辆信息及环境信息，获取目标矩阵。对目标矩阵进行拆分，得到多个子矩阵。基于每个子矩阵中的矩阵元素以及目标车辆的周围车辆的行驶控制信息，获取目标车辆的目标行驶控制信息。

Description

控制车辆
本申请要求于2019年11月27日提交的申请号为201911185658.3、申请名称为“控制车辆的方法、装置、电子设备及可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能技术领域，特别涉及一种控制车辆。
背景技术
随着人工智能技术的发展，越来越多的人工智能技术被应用于人们的生活中，车辆控制技术便是其中的一种。在交通场景中，车辆控制技术可用于对车辆进行驾驶。
发明内容
本申请实施例提供了一种控制车辆。所述技术方案如下：
一方面，提供了一种控制车辆的方法，所述方法包括：
获取目标车辆的车辆信息以及所述目标车辆所在的参考环境的环境信息；
基于所述车辆信息及所述环境信息，获取目标矩阵，所述目标矩阵中的元素为所述目标车辆在当前状态下执行动作后转移到下一个状态的概率值；
对所述目标矩阵进行拆分，得到多个子矩阵；
基于每个子矩阵中的矩阵元素以及所述目标车辆的周围车辆的行驶控制信息，获取所述目标车辆的目标行驶控制信息，所述目标行驶控制信息用于控制所述目标车辆。
可选地，所述对所述目标矩阵进行拆分，得到多个子矩阵，包括：
基于所述目标矩阵中所述目标车辆的当前状态及下一个状态，以及对所述下一个状态采样得到的采样点和标准正态分布函数，根据非参数估计的方式确定每个子矩阵中的矩阵元素。
可选地，所述根据非参数估计的方式确定每个子矩阵中的矩阵元素之后，所述方法还包括：
对于任一矩阵元素，基于所述矩阵元素进行迭代计算，得到更新后的矩阵元素。
可选地，所述对于任一矩阵元素，基于所述矩阵元素进行迭代计算，得到更新后的矩阵元素，包括：
对于任一矩阵元素，确定所述矩阵元素在不同时刻对应的数值；
响应于所述矩阵元素在不同时刻对应的数值不同，根据所述矩阵元素在不同时刻对应的数值进行迭代计算，得到更新后的矩阵元素，所述更新后的矩阵元素在不同时刻对应有相同的数值。
可选地，所述基于每个子矩阵中的矩阵元素以及所述目标车辆的周围车辆的行驶控制信息，获取所述目标车辆的目标行驶控制信息，包括：
基于每个子矩阵中的矩阵元素，确定所述目标车辆的一个或多个下一个状态的概率值；
根据下一个状态的概率值与行驶控制信息的对应关系，获取一个或多个参考行驶控制信息；
基于所述目标车辆的周围车辆的行驶控制信息，从所述一个或多个参考行驶控制信息中获取所述目标行驶控制信息。
可选地，所述基于所述目标车辆的周围车辆的行驶控制信息，从所述一个或多个参考行驶控制信息中获取所述目标行驶控制信息，包括：
基于所述目标车辆的周围车辆的行驶控制信息，确定每个参考行驶控制信息在未来一个或多个时刻中的每个时刻对应的回报数值；
将每个时刻对应的回报数值之和最大的参考行驶控制信息作为所述目标行驶控制信息。
一方面，提供了一种控制车辆的装置，所述装置包括：
第一获取模块，用于获取目标车辆的车辆信息以及所述目标车辆所在的参考环境的环境信息；
第二获取模块，用于基于所述车辆信息及所述环境信息，获取目标矩阵，所述目标矩阵中的元素为所述目标车辆在当前状态下执行动作后转移到下一个状态的概率值；
拆分模块，用于对所述目标矩阵进行拆分，得到多个子矩阵；
控制模块，用于基于每个子矩阵中的矩阵元素以及所述目标车辆的周围车辆的行驶控制信息，获取所述目标车辆的目标行驶控制信息，所述目标行驶控 制信息用于控制所述目标车辆。
可选地，所述拆分模块，用于基于所述目标矩阵中所述目标车辆的当前状态及下一个状态，以及对所述下一个状态采样得到的采样点和标准正态分布函数，根据非参数估计的方式确定每个子矩阵中的矩阵元素。
可选地，所述装置还包括：计算模块，用于对于任一矩阵元素，基于所述矩阵元素进行迭代计算，得到更新后的矩阵元素。
可选地，所述计算模块，用于对于任一矩阵元素，确定所述矩阵元素在不同时刻对应的数值；响应于所述矩阵元素在不同时刻对应的数值不同，根据所述矩阵元素在不同时刻对应的数值进行迭代计算，得到更新后的矩阵元素，所述更新后的矩阵元素在不同时刻对应有相同的数值。
可选地，所述控制模块，用于基于每个子矩阵中的矩阵元素，确定所述目标车辆的一个或多个下一个状态的概率值；根据下一个状态的概率值与行驶控制信息的对应关系，获取一个或多个参考行驶控制信息；基于所述目标车辆的周围车辆的行驶控制信息，从所述一个或多个参考行驶控制信息中获取所述目标行驶控制信息。
可选地，所述控制模块，用于基于所述目标车辆的周围车辆的行驶控制信息，确定每个参考行驶控制信息在未来一个或多个时刻中的每个时刻对应的回报数值；将每个时刻对应的回报数值之和最大的参考行驶控制信息作为所述目标行驶控制信息。
一方面，提供了一种电子设备，所述设备包括存储器及处理器；所述存储器中存储有至少一条指令，所述至少一条指令由所述处理器加载并执行，以实现本申请的任一种可能的实现方式所提供的控制车辆的方法。
一方面，提供了一种非临时性计算机可读存储介质，所述非临时性计算机可读存储介质中存储有至少一条指令，所述指令由处理器加载并执行以实现本申请的任一种可能的实现方式所提供的控制车辆的方法。
另一方面，提供了一种计算机程序或计算机程序产品，所述计算机程序或计算机程序产品包括：计算机指令，所述计算机指令被计算机执行时，使得所述计算机实现本申请的任一种示例性实施例所提供的控制车辆的方法。
本申请实施例所提供的技术方案带来的有益效果至少包括：
通过对基于车辆信息及环境信息得到的目标矩阵进行拆分得到多个子矩阵，基于子矩阵来获取用于控制目标车辆的目标行驶控制信息。不仅避免了维 数灾难，还减小了计算复杂程度，降低了获取目标行驶控制信息所需的计算量，使得该控制车辆的方法适用于较为复杂的参考环境。本实施例所获取的目标行驶控制信息还考虑了可能与目标车辆交互的周围车辆的行驶控制信息，因而保证了目标车辆在多车交互场景下的安全性，使得该控制车辆的方法可适用于多车交互的场景。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还能够根据这些附图获得其他的附图。
图1是本申请实施例提供的实施环境示意图；
图2是本申请实施例提供的控制车辆的方法的流程图；
图3是本申请实施例提供的控制车辆的方法的架构图；
图4是本申请实施例提供的控制车辆的装置的结构示意图；
图5是本申请实施例提供的终端的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
在交通场景中，如何对车辆进行控制，是保证驾驶安全性的关键。相关技术提供一种控制车辆的方法：获取受控车辆对应的矩阵，该矩阵中的每个元素用于指示受控车辆从当前状态转移到下一个状态的概率，且该矩阵的维数等于受控车辆有可能处于的状态的数量。之后，确定矩阵中每个元素的数值，基于所确定的每个元素的数值来获取策略，从而根据该策略控制受控车辆。
然而，在复杂交通场景中，受控车辆有可能处于的状态的数量较大，则矩阵的维数也较大，从而导致确定矩阵中每个元素的数值所需的计算量较大、计算复杂度高，影响了控制车辆的效率。
本申请实施例提供了一种控制车辆的方法，该方法可应用于如图1所示的实施环境中。图1中，包括至少一个终端11和探测器12，终端11可与探测器12进行通信连接，以获取探测器12所探测到的探测目标车辆的车辆信息，以及目标车辆所在的参考环境的环境信息。
其中，终端11包括但不限于：任何一种可与用户通过键盘、触摸板、触摸屏、遥控器、语音交互或手写设备等一种或多种方式进行人机交互的电子产品，例如PC(Personal Computer，个人计算机)、手机、智能手机、PDA(Personal Digital Assistant，个人数字助手)、可穿戴设备、掌上电脑PPC(Pocket PC)、平板电脑、智能车机、智能电视、智能音箱等。
本领域技术人员应能理解上述终端11和探测器12仅为举例，其他相关的或今后可能出现的终端或探测器如可适用于本申请实施例，也应包含在本申请实施例的保护范围以内，在此以引用方式包含于此。
基于上述图1所示的实施环境，参见图2，本申请实施例提供了一种控制车辆的方法，该方法可应用于图1所示的终端中。如图2所示，该方法包括：
步骤201，获取目标车辆的车辆信息以及目标车辆所在的参考环境的环境信息。
其中，目标车辆为待控制的车辆。目标车辆的车辆信息包括车辆状态信息以及车辆动作信息。车辆状态信息包括但不限于目标车辆的位置(经纬度)、朝向(东南西北)、速度、加速度、油门量、刹车量以及方向盘转角，车辆动作信息包括上述车辆状态信息的变化量。
示例性地，目标车辆所在的参考环境是马路、居民区等地点，目标车辆所在的参考环境的环境信息包括参考环境的地图、可行驶路径、动态障碍物及静态障碍物等等。例如，当参考环境为马路时，可行驶路径为马路的多个车道，动态障碍物为马路上的其他车辆，静态障碍物为马路中间的隔离护栏。
通过上述车辆状态信息及环境信息，能够确定目标车辆的一个或多个当前状态。仍以参考环境为马路为例，根据位置及朝向便可确定目标车辆所位于的车道，根据速度、加速度、油门量、刹车量以及方向盘转角，能够确定目标车辆的行驶速度及行驶方向。之后，结合车道、行驶速度及行驶方向便可得到目标车辆的一个或多个当前状态。例如，目标车辆的当前状态为沿第一车道匀速行驶等等。
通过上述车辆动作信息能够确定目标车辆的当前动作。例如，根据速度、加速度、油门量以及刹车量的变化量确定目标车辆的行驶速度变化，根据方向盘转角的变化量确定目标车辆的行驶方向变化。因此，根据行驶速度变化以及行驶方向变化能够得到目标车辆的当前动作。例如，向左加速、减速动作。
示例性地，上述信息能够通过位于目标车辆上的探测器进行探测得到。当 然，本实施例不对获取上述信息的方式加以限定，无论采用何种方法获取上述信息，在实现获取之后，便可基于上述信息获取目标矩阵，详见步骤202。
步骤202，基于车辆信息及环境信息，获取目标矩阵。
根据步骤201中的说明可知，基于车辆信息及环境信息能够得到目标车辆所可能处于的一个或多个当前状态，以及目标车辆的当前动作。假设目标车辆的下一个状态仅与当前状态及当前动作有关，则在当前状态下执行当前动作，便有一定的概率由当前状态转移为下一个状态。例如，当前状态为沿第一车道直行，当前动作为向左加速，则下一个状态可能是进入了第一车道左侧的第二车道，也可能是仍沿第一车道直行等其他状态。
因此，可根据上述一个或多个当前状态，以及由一个或多个当前状态及当前动作所可能转移到的一个或多个下一个状态获取目标矩阵。其中，目标矩阵中的元素为目标车辆在当前状态下执行动作后，转移到下一个状态的概率值。目标矩阵的维数等于当前状态的数量。
对于目标矩阵中的任一元素，可通过计算获取该元素的值。需要说明的是，当目标车辆所在的参考环境较为复杂时，例如马路上车道数量较多、目标车辆周围车辆较多时，目标车辆所可能处于的当前状态的数量也较多，导致目标矩阵的维数较大。因此，若后续基于目标矩阵进行计算，则会使得计算复杂度较高、计算量较大。基于上述考虑，本实施例在进行计算之前，先对目标矩阵进行拆分，详见步骤203。
步骤203，对目标矩阵进行拆分，得到多个子矩阵。
在实施中，将目标矩阵拆分成多个连乘的子矩阵，每个子矩阵中的矩阵元素仍为目标车辆在一个当前状态下执行动作后，转移到下一个状态的概率值。每个子矩阵的维度均小于目标矩阵的维度，例如每个子矩阵均为二维矩阵。当然，本实施例不对子矩阵的维度加以限定，示例性地，子矩阵为维度高于二维矩阵的三维矩阵、四维矩阵等等。
在一种可选的实施方式中，对目标矩阵进行拆分，得到多个子矩阵，包括：基于目标矩阵中目标车辆的当前状态及下一个状态，以及对下一个状态采样得到的采样点和标准正态分布函数，根据非参数估计的方式确定每个子矩阵中的矩阵元素。
例如，对于任一矩阵元素，按照如下的公式(1)来进行确定：
Figure PCTCN2020121620-appb-000001
其中，x t+1为下一个状态，x t为当前状态，a t为当前动作，p(x t+1|x t,a t)表示x t在执行a t转移到x t+1的概率值(也被称为条件概率)，p(x t+1|x t,a t)即为矩阵元素；
Figure PCTCN2020121620-appb-000002
为对下一个状态进行采样得到的第i个采样点，i≤n，在每次采样中，都使目标车辆在x t执行a t，实际得到的状态即为采样点。
在公式(1)中，
Figure PCTCN2020121620-appb-000003
为标准正态分布函数，该标准正态分布函数为非参数估计所使用的核函数，h为核宽度。需要说明的是，核宽度h为超参数，可根据实际需要或经验进行设置。
Figure PCTCN2020121620-appb-000004
可表示为如下的公式(2)：
Figure PCTCN2020121620-appb-000005
通过上述非参数估计的方式来确定每个子矩阵中的矩阵元素，运算效率较高、稳健性较好。可选地，参见图3，根据非参数估计的方式确定每个子矩阵中的矩阵元素之后，本实施例所提供的方法还包括：对于任一矩阵元素，基于矩阵元素进行迭代计算，得到更新后的矩阵元素。
其中，矩阵中的每个矩阵元素均为从目标车辆在当前状态下执行动作后，转移到下一个状态的概率值。在该转移过程中，不同时刻所对应的下一个状态有所不同，例如当前状态为匀速状态、下一时刻的状态为加速状态，再下一时刻的状态重新变为匀速状态，从而导致不同时刻的矩阵元素有所波动。因此，可在不同时刻迭代更新矩阵元素，使得矩阵元素最终收敛至一个稳定的数值，以便于后续过程中基于该稳定的数值获取目标车辆的目标行驶控制信息，详见步骤204。
也就是说，对于任一矩阵元素，基于矩阵元素进行迭代计算，得到更新后的矩阵元素，包括：对于任一矩阵元素，确定矩阵元素在不同时刻对应的数值。响应于矩阵元素在不同时刻对应的数值不同，根据矩阵元素在不同时刻对应的数值进行迭代计算，得到更新后的矩阵元素，更新后的矩阵元素在不同时刻对应有相同的数值。
其中，一个矩阵元素在不同时刻对应的数值不同的情况即为上述说明中不同时刻的矩阵元素有所波动的情况。在此种情况下，再基于该矩阵元素在不同时刻对应的各个不同数值进行迭代计算，该迭代计算过程收敛后便能够得到稳定的更新后的矩阵元素。相应地，响应于一个矩阵元素在不同时刻对应的数值相同(也就是不同时刻的矩阵元素未波动)，或者一个矩阵元素在不同时刻对 应的数值中仅有小于数量阈值个数值不同(也就是不同时刻的矩阵元素波动程度较小)，则无需执行上述迭代计算过程，步骤204中直接基于矩阵元素获取目标车辆的目标行驶控制信息即可。其中，本实施例不对该数量阈值的取值进行限定。
步骤204，基于每个子矩阵中的矩阵元素以及目标车辆的周围车辆的行驶控制信息，获取目标车辆的目标行驶控制信息，根据目标行驶控制信息控制目标车辆。
其中，行驶控制信息是指车辆能够执行的动作，例如行驶控制信息包括但不限于沿当前道路匀速行驶、沿当前道路加速行驶、沿当前道路减速行驶、向左变道匀速行驶、向左变道加速行驶等等。考虑到参考环境中目标车辆周围可能具有一个或多个其他车辆，因而需要综合周围车辆的行驶控制信息，来确定目标车辆的目标行驶控制信息，以保证根据目标行驶控制信息所控制的目标车辆能与周围车辆安全交互。
在一种可选的实施方式中，基于每个子矩阵中的矩阵元素以及目标车辆的周围车辆的行驶控制信息，获取目标车辆的目标行驶控制信息，包括如下的步骤2041～2043：
步骤2041，基于每个子矩阵中的矩阵元素，确定目标车辆的一个或多个下一个状态的概率值。
在实施中，可根据如下的公式(3)确定目标车辆的下一个状态的概率：
Figure PCTCN2020121620-appb-000006
其中，p(x t+1)表示下一个状态的概率值，x t表示当前状态，a t表示当前动作，z t表示当前观测值。
上述公式(3)可分解为如下的公式(4)，从而通过矩阵元素p(x t+1|x t,a t)进行表示：
Figure PCTCN2020121620-appb-000007
另外，通过上标v表示周围车辆，任一周围车辆下一个状态的概率可表示为如下的分解形式(5)：
Figure PCTCN2020121620-appb-000008
根据独立性假设，周围所有车辆的联合下一个状态概率等于每个周围车辆的下一个状态的概率乘积，因而以周围所有车辆的联合下一个状态概率表示为如下的公式(6)：
Figure PCTCN2020121620-appb-000009
之后，引入周围车辆的行驶控制信息
Figure PCTCN2020121620-appb-000010
假定周围车辆按照道路行驶规则进行行驶便可确定出
Figure PCTCN2020121620-appb-000011
从而将上述公式(5)表示为如下分解形式的公式(7)：
Figure PCTCN2020121620-appb-000012
仍根据独立性假设，将目标车辆通过上标q进行表示，目标车辆下一个状态的概率值需要将目标车辆自身及周围所有车辆综合考虑，目标车辆的下一个状态概率可表示为如下的公式(8)：
Figure PCTCN2020121620-appb-000013
其中，
Figure PCTCN2020121620-appb-000014
为目标车辆当前时刻采用的行驶控制信息，可通过步骤201中的车辆状态及车辆动作确定。
在根据上述公式确定每个下一个状态的概率值之后，便可进一步基于概率值获取参考行驶控制信息，参见步骤2042。
步骤2042，根据下一个状态的概率值与行驶控制信息的对应关系，获取一个或多个参考行驶控制信息。
在实施中，可获取存储有下一个状态的概率值与行驶控制信息的对应关系的数据集。在该数据集中，人工为多个样本车辆设置行驶控制信息，将样本车辆执行该行驶控制信息所得到的下一个状态的概率值与行驶控制信息对应存储，从而得到下一个状态的概率值与行驶控制信息的对应关系。
对于步骤2041中所确定的下一个状态的概率值，可根据数据集中的对应关系确定一个或多个行驶控制信息，将一个或多个行驶控制信息中数量最多的一个行驶控制信息作为该下一个状态的概率值的参考行驶控制信息。能够看出，根据目标车辆的一个或多个下一个状态的概率值，便可得到一个或多个参考行驶控制信息。
之后，本实施例继续从一个或多个参考行驶控制信息中进行选择，得到一个用于控制目标车辆的目标行驶控制信息，参见步骤2043。
步骤2043，基于目标车辆的周围车辆的行驶控制信息，从一个或多个参考行驶控制信息中获取目标行驶控制信息。
其中，对于每个周围车辆，均可假设该周围车辆按照参考的道路行驶规则进行行驶，从而基于参考的道路行驶规则获取该周围车辆的行驶控制信息。在获取周围车辆的行驶控制信息之后，便可结合目标车辆的周围车辆的行驶控制信息，来确定目标行驶控制信息。可选地，基于目标车辆的周围车辆的行驶控制信息，从一个或多个参考行驶控制信息中获取目标行驶控制信息，包括：基于目标车辆的周围车辆的行驶控制信息，确定每个参考行驶控制信息在未来一个或多个时刻中的每个时刻对应的回报数值。将每个时刻对应的回报数值之和最大的参考行驶控制信息作为目标行驶控制信息。
需要说明的是，每个参考行驶控制信息均包括多个状态到动作的映射，从而可在目标车辆处于不同状态时，根据多个状态到动作的映射确定出每个状态时所需执行的动作。例如将匀速状态与加速动作映射，从而在目标车辆处于匀速状态时，指示目标车辆所需执行的动作为加速超车。另外，回报数值用于指示目标车辆所执行动作的优劣，而目标车辆所执行动作的优劣需要结合周围车辆的行驶控制信息来进行确定。因此，可基于周围车辆的行驶控制信息来确定每个时刻所执行动作对应的回报数值。
在实施中，对于每个时刻目标车辆所执行的动作，可基于周围车辆的行驶控制信息来确定执行该动作的目标车辆是否与周围车辆碰撞。若确定发生碰撞，则说明该动作效果较差，该时刻的动作对应的回报数值为负值(惩罚值)。相应地，若确定不会发生碰撞，该时刻的动作对应的回报数值为正值(奖励值)。
另外，还可根据针对目标车辆设置的驾驶模式来确定动作的回报数值。例如，在高效模式下，加速超车动作的回报数值高于减速跟随动作的回报数值；在正常模式下，减速跟随与加速超车的回报数值相等；在安全模式下，加速超车动作的回报数值低于减速跟随动作的回报数值。
对于任一参考行驶控制信息，在目标车辆根据该参考行驶控制信息所包括的状态与动作之间的映射，确定每个时刻所执行的动作对应的回报数值之后，便可对各个时刻对应的回报数值进行求和计算，将每个时刻对应的回报数值之和最大的参考行驶控制信息作为目标行驶控制信息。该过程可表示为如下的公式(9)：
Figure PCTCN2020121620-appb-000015
其中，π *表示目标行驶控制信息，t表示时间，t≤H，H可根据经验进行设置；γ表示折扣因子，折扣因子的取值为不大于1的非负数，用于指示未来 时刻的回报数值对于当前时刻的回报数值的重要程度；R为回报数值。
在得到目标行驶控制信息之后，该目标行驶控制信息可用于对目标车辆进行控制。在实施中，根据目标车辆在每个时刻所处于的状态，从该目标行驶控制信息所包括的多个映射中确定出目标车辆所需执行的动作，从而实现根据目标行驶控制信息控制目标车辆。
综上所述，本实施例对基于车辆信息及环境信息得到的目标矩阵进行拆分得到多个子矩阵，基于子矩阵来获取用于控制目标车辆的目标行驶控制信息。不仅避免了维数灾难，还减小了计算复杂程度，降低了获取目标行驶控制信息所需的计算量，使得该控制车辆的方法适用于较为复杂的参考环境。本实施例所获取的目标行驶控制信息还考虑了可能与目标车辆交互的周围车辆的行驶控制信息，因而保证了目标车辆在多车交互场景下的安全性，使得该控制车辆的方法适用于多车交互的场景。
进一步地，本实施例还通过上述非参数估计的方式来确定每个子矩阵中的矩阵元素，运算效率较高、稳健性较好。
基于相同构思，本申请实施例提供了一种控制车辆的装置，参见图4，该装置包括：
第一获取模块401，用于获取目标车辆的车辆信息以及目标车辆所在的参考环境的环境信息；
第二获取模块402，用于基于车辆信息及环境信息，获取目标矩阵，目标矩阵中的元素为目标车辆在当前状态下执行动作后转移到下一个状态的概率值；
拆分模块403，用于对目标矩阵进行拆分，得到多个子矩阵；
控制模块404，用于基于每个子矩阵中的矩阵元素以及目标车辆的周围车辆的行驶控制信息，获取目标车辆的目标行驶控制信息，目标行驶控制信息用于控制目标车辆。
可选地，拆分模块403，用于基于目标矩阵中目标车辆的当前状态及下一个状态，以及对下一个状态采样得到的采样点和标准正态分布函数，根据非参数估计的方式确定每个子矩阵中的矩阵元素。
可选地，装置还包括：计算模块，用于对于任一矩阵元素，基于矩阵元素进行迭代计算，得到更新后的矩阵元素。
可选地，该计算模块，用于对于任一矩阵元素，确定矩阵元素在不同时刻对应的数值；响应于矩阵元素在不同时刻对应的数值不同，根据矩阵元素在不同时刻对应的数值进行迭代计算，得到更新后的矩阵元素，更新后的矩阵元素在不同时刻对应有相同的数值。
可选地，控制模块404，用于基于每个子矩阵中的矩阵元素，确定目标车辆的一个或多个下一个状态的概率值；根据下一个状态的概率值与行驶控制信息的对应关系，获取一个或多个参考行驶控制信息；基于目标车辆的周围车辆的行驶控制信息，从一个或多个参考行驶控制信息中获取目标行驶控制信息。
可选地，控制模块404，用于基于目标车辆的周围车辆的行驶控制信息，确定每个参考行驶控制信息在未来一个或多个时刻中的每个时刻对应的回报数值；将每个时刻对应的回报数值之和最大的参考行驶控制信息作为目标行驶控制信息。
综上所述，本实施例对基于车辆信息及环境信息得到的目标矩阵进行拆分得到多个子矩阵，基于子矩阵来获取用于控制目标车辆的目标行驶控制信息。不仅避免了维数灾难，还减小了计算复杂程度，降低了获取目标行驶控制信息所需的计算量，使得该控制车辆的方法适用于较为复杂的参考环境。本实施例所获取的目标行驶控制信息还考虑了可能与目标车辆交互的周围车辆的行驶控制信息，因而保证了目标车辆在多车交互场景下的安全性，使得该控制车辆的方法适用于多车交互的场景。
进一步地，本实施例还通过上述非参数估计的方式来确定每个子矩阵中的矩阵元素，运算效率较高、稳健性较好。
需要说明的是，上述实施例提供的装置在实现其功能时，仅以上述各功能模块的划分进行举例说明，实际应用中，根据需要而将上述功能分配由不同的功能模块完成，即将设备的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的装置与方法实施例属于同一构思，其实现过程详见方法实施例，这里不再赘述。
参见图5，其示出了本申请实施例提供的一种终端500的结构示意图。示例性地，该终端500是便携式移动终端，比如：智能手机、平板电脑、MP3播放器(Moving Picture Experts Group Audio Layer III，动态影像专家压缩标准音频层面3)、MP4(Moving Picture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4)播放器、笔记本电脑或台式电脑。终端500还可能被 称为用户设备、便携式终端、膝上型终端、台式终端等其他名称。
通常，终端500包括有：处理器501和存储器502。
示例性地，处理器501包括一个或多个处理核心，比如4核心处理器、5核心处理器等。处理器501采用DSP(Digital Signal Processing，数字信号处理)、FPGA(Field－Programmable Gate Array，现场可编程门阵列)、PLA(Programmable Logic Array，可编程逻辑阵列)中的至少一种硬件形式来实现。示例性地，处理器501包括主处理器和协处理器，主处理器是用于对在唤醒状态下的数据进行处理的处理器，也称CPU(Central Processing Unit，中央处理器)；协处理器是用于对在待机状态下的数据进行处理的低功耗处理器。在一些实施例中，处理器501在集成有GPU(Graphics Processing Unit，图像处理器)，GPU用于负责显示屏所需要显示的内容的渲染和绘制。一些实施例中，处理器501还包括AI(Artificial Intelligence，人工智能)处理器，该AI处理器用于处理有关机器学习的计算操作。
示例性地，存储器502包括一个或多个计算机可读存储介质，该计算机可读存储介质是非暂态的，或者说非临时性的。存储器502还包括高速随机存取存储器，以及非易失性存储器，比如一个或多个磁盘存储设备、闪存存储设备。在一些实施例中，存储器502中的非暂态的计算机可读存储介质用于存储至少一个指令，该至少一个指令用于被处理器501所执行以实现本申请中方法实施例提供的控制车辆的方法。
在一些实施例中，终端500还可选包括有：外围设备接口503和至少一个外围设备。处理器501、存储器502和外围设备接口503之间通过总线或信号线相连。各个外围设备通过总线、信号线或电路板与外围设备接口503相连。示例性地，外围设备包括：射频电路504、触摸显示屏505、摄像头506、音频电路507、定位组件508和电源509中的至少一种。
外围设备接口503可被用于将I/O(Input/Output，输入/输出)相关的至少一个外围设备连接到处理器501和存储器502。在一些实施例中，处理器501、存储器502和外围设备接口503被集成在同一芯片或电路板上；在一些其他实施例中，处理器501、存储器502和外围设备接口503中的任意一个或两个能够在单独的芯片或电路板上实现，本实施例对此不加以限定。
射频电路504用于接收和发射RF(Radio Frequency，射频)信号，也称电磁信号。射频电路504通过电磁信号与通信网络以及其他通信设备进行通信。 射频电路504将电信号转换为电磁信号进行发送，或者，将接收到的电磁信号转换为电信号。可选地，射频电路504包括：天线系统、RF收发器、一个或多个放大器、调谐器、振荡器、数字信号处理器、编解码芯片组、用户身份模块卡等等。射频电路504通过至少一种无线通信协议来与其它终端进行通信。该无线通信协议包括但不限于：城域网、各代移动通信网络(2G、3G、4G及5G)、无线局域网和/或WiFi(Wireless Fidelity，无线保真)网络。在一些实施例中，射频电路504还包括NFC(Near Field Communication，近距离无线通信)有关的电路，本申请实施例对此不加以限定。
显示屏505用于显示UI(User Interface，用户界面)。该UI包括图形、文本、图标、视频及其它们的任意组合。当显示屏505是触摸显示屏时，显示屏505还具有采集在显示屏505的表面或表面上方的触摸信号的能力。该触摸信号作为控制信号输入至处理器501进行处理。此时，显示屏505还用于提供虚拟按钮和/或虚拟键盘，也称软按钮和/或软键盘。在一些实施例中，显示屏505为一个，设置终端500的前面板；在另一些实施例中，显示屏505为至少两个，分别设置在终端500的不同表面或呈折叠设计；在再一些实施例中，显示屏505是柔性显示屏，设置在终端500的弯曲表面上或折叠面上。甚至，显示屏505还能够设置成非矩形的不规则图形，也即异形屏。示例性地，显示屏505采用LCD(Liquid Crystal Display，液晶显示屏)、OLED(Organic Light-Emitting Diode,有机发光二极管)等材质制备。
摄像头组件506用于采集图像或视频。可选地，摄像头组件506包括前置摄像头和后置摄像头。通常，前置摄像头设置在终端的前面板，后置摄像头设置在终端的背面。在一些实施例中，后置摄像头为至少两个，分别为主摄像头、景深摄像头、广角摄像头、长焦摄像头中的任意一种，以实现主摄像头和景深摄像头融合实现背景虚化功能、主摄像头和广角摄像头融合实现全景拍摄以及VR(Virtual Reality，虚拟现实)拍摄功能或者其它融合拍摄功能。在一些实施例中，摄像头组件506还包括闪光灯。闪光灯是单色温闪光灯，或者是双色温闪光灯。双色温闪光灯是指暖光闪光灯和冷光闪光灯的组合，用于不同色温下的光线补偿。
音频电路507包括麦克风和扬声器。麦克风用于采集用户及环境的声波，将声波转换为电信号输入至处理器501进行处理，或者输入至射频电路504以实现语音通信。出于立体声采集或降噪的目的，麦克风为多个，分别设置在终 端500的不同部位。或者，麦克风是阵列麦克风或全向采集型麦克风。扬声器则用于将来自处理器501或射频电路504的电信号转换为声波。扬声器是传统的薄膜扬声器，或者是压电陶瓷扬声器。当扬声器是压电陶瓷扬声器时，不仅能够将电信号转换为人类可听见的声波，也能够将电信号转换为人类听不见的声波以进行测距等用途。在一些实施例中，音频电路507还包括耳机插孔。
定位组件508用于定位终端500的当前地理位置，以实现导航或LBS(Location Based Service，基于位置的服务)。定位组件508是基于美国的GPS(Global Positioning System，全球定位系统)、中国的北斗系统、俄罗斯的格雷纳斯系统或欧盟的伽利略系统的定位组件。
电源509用于为终端500中的各个组件进行供电。电源509是交流电、直流电、一次性电池或可充电电池。当电源509包括可充电电池时，该可充电电池能够支持有线充电或无线充电。该可充电电池还能够用于支持快充技术。
在一些实施例中，终端500还包括有一个或多个传感器510。该一个或多个传感器510包括但不限于：加速度传感器511、陀螺仪传感器512、压力传感器513、指纹传感器514、光学传感器515以及接近传感器516。
加速度传感器510能够检测以终端500建立的坐标系的三个坐标轴上的加速度大小。比如，加速度传感器511能够用于检测重力加速度在三个坐标轴上的分量。处理器501能够根据加速度传感器511采集的重力加速度信号，控制触摸显示屏505以横向视图或纵向视图进行用户界面的显示。加速度传感器511还能够用于游戏或者用户的运动数据的采集。
陀螺仪传感器512能够检测终端500的机体方向及转动角度，陀螺仪传感器512能够与加速度传感器511协同采集用户对终端500的3D动作。处理器501根据陀螺仪传感器512采集的数据，能够实现如下功能：动作感应(比如根据用户的倾斜操作来改变UI)、拍摄时的图像稳定、游戏控制以及惯性导航。
示例性地，压力传感器513设置在终端500的侧边框和/或触摸显示屏505的下层。当压力传感器513设置在终端500的侧边框时，能够检测用户对终端500的握持信号，由处理器501根据压力传感器513采集的握持信号进行左右手识别或快捷操作。当压力传感器513设置在触摸显示屏505的下层时，由处理器501根据用户对触摸显示屏505的压力操作，实现对UI界面上的可操作性控件进行控制。可操作性控件包括按钮控件、滚动条控件、图标控件、菜单控件中的至少一种。
指纹传感器514用于采集用户的指纹，由处理器501根据指纹传感器514采集到的指纹识别用户的身份，或者，由指纹传感器514根据采集到的指纹识别用户的身份。在识别出用户的身份为可信身份时，由处理器501授权该用户执行相关的敏感操作，该敏感操作包括解锁屏幕、查看加密信息、下载软件、支付及更改设置等。示例性地，指纹传感器514被设置终端500的正面、背面或侧面。当终端500上设置有物理按键或厂商Logo时，指纹传感器514能够与物理按键或厂商Logo集成在一起。
光学传感器515用于采集环境光强度。在一个实施例中，处理器501能够根据光学传感器515采集的环境光强度，控制触摸显示屏505的显示亮度。示例性地，当环境光强度较高时，调高触摸显示屏505的显示亮度；当环境光强度较低时，调低触摸显示屏505的显示亮度。在另一个实施例中，处理器501还能够根据光学传感器515采集的环境光强度，动态调整摄像头组件506的拍摄参数。
接近传感器516，也称距离传感器，通常设置在终端500的前面板。接近传感器516用于采集用户与终端500的正面之间的距离。在一个实施例中，当接近传感器516检测到用户与终端500的正面之间的距离逐渐变小时，由处理器501控制触摸显示屏505从亮屏状态切换为息屏状态；当接近传感器516检测到用户与终端500的正面之间的距离逐渐变大时，由处理器501控制触摸显示屏505从息屏状态切换为亮屏状态。
本领域技术人员能够理解，图5中示出的结构不构成对终端500的限定，能够包括比图示更多或更少的组件，或者组合某些组件，或者采用不同的组件布置。
基于相同构思，本申请实施例提供了一种电子设备，设备包括存储器及处理器；存储器中存储有至少一条指令，至少一条指令由处理器加载并执行，以实现本申请的任一种可能的实现方式所提供的控制车辆的方法。
基于相同构思，本申请实施例提供了一种非临时性计算机可读存储介质，非临时性计算机可读存储介质中存储有至少一条指令，指令由处理器加载并执行以实现本申请的任一种可能的实现方式所提供的控制车辆的方法。
本申请实施例提供了一种计算机程序或计算机程序产品，计算机程序或计算机程序产品包括：计算机指令，计算机指令被计算机执行时，使得计算机实现本申请的任一种示例性实施例所提供的控制车辆的方法。
上述所有可选技术方案，能够采用任意结合形成本申请的可选实施例，在此不再一一赘述。
本领域普通技术人员能够理解实现上述实施例的全部或部分步骤能够通过硬件来完成，也能够通过程序来指令相关的硬件完成，所述的程序能够存储于一种非临时性计算机可读存储介质中，上述提到的非临时性计算机可读存储介质是只读存储器，磁盘或光盘等。
以上所述仅为本申请的实施例，不用以进行限制，凡在本申请实施例的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请实施例的保护范围之内。

Claims (14)

  1. 一种控制车辆的方法，其中，所述方法包括：
    获取目标车辆的车辆信息以及所述目标车辆所在的参考环境的环境信息；
    基于所述车辆信息及所述环境信息，获取目标矩阵，所述目标矩阵中的元素为所述目标车辆在当前状态下执行动作后转移到下一个状态的概率值；
    对所述目标矩阵进行拆分，得到多个子矩阵；
    基于每个子矩阵中的矩阵元素以及所述目标车辆的周围车辆的行驶控制信息，获取所述目标车辆的目标行驶控制信息，所述目标行驶控制信息用于控制所述目标车辆。
  2. 根据权利要求1所述的方法，其中，所述基于所述车辆信息及所述环境信息，获取目标矩阵，包括：
    基于所述目标车辆的当前状态及下一个状态，以及对所述下一个状态采样得到的采样点和标准正态分布函数，根据非参数估计的方式确定每个子矩阵中的矩阵元素。
  3. 根据权利要求2所述的方法，其中，所述根据非参数估计的方式确定每个子矩阵中的矩阵元素之后，所述方法还包括：
    对于任一矩阵元素，基于所述矩阵元素进行迭代计算，得到更新后的矩阵元素。
  4. 根据权利要求3所述的方法，其中，所述对于任一矩阵元素，基于所述矩阵元素进行迭代计算，得到更新后的矩阵元素，包括：
    对于任一矩阵元素，确定所述矩阵元素在不同时刻对应的数值；
    响应于所述矩阵元素在不同时刻对应的数值不同，根据所述矩阵元素在不同时刻对应的数值进行迭代计算，得到更新后的矩阵元素，所述更新后的矩阵元素在不同时刻对应有相同的数值。
  5. 根据权利要求1-4任一所述的方法，其中，所述基于每个子矩阵中的矩阵元素以及所述目标车辆的周围车辆的行驶控制信息，获取所述目标车辆的 目标行驶控制信息，包括：
    基于每个子矩阵中的矩阵元素，确定所述目标车辆的一个或多个下一个状态的概率值；
    根据下一个状态的概率值与行驶控制信息的对应关系，获取一个或多个参考行驶控制信息；
    基于所述目标车辆的周围车辆的行驶控制信息，从所述一个或多个参考行驶控制信息中获取所述目标行驶控制信息。
  6. 根据权利要求5所述的方法，其中，所述基于所述目标车辆的周围车辆的行驶控制信息，从所述一个或多个参考行驶控制信息中获取所述目标行驶控制信息，包括：
    基于所述目标车辆的周围车辆的行驶控制信息，确定每个参考行驶控制信息在未来一个或多个时刻中的每个时刻对应的回报数值；
    将每个时刻对应的回报数值之和最大的参考行驶控制信息作为所述目标行驶控制信息。
  7. 一种控制车辆的装置，其中，所述装置包括：
    第一获取模块，用于获取目标车辆的车辆信息以及所述目标车辆所在的参考环境的环境信息；
    第二获取模块，用于基于所述车辆信息及所述环境信息，获取目标矩阵，所述目标矩阵中的元素为所述目标车辆在当前状态下执行动作后转移到下一个状态的概率值；
    拆分模块，用于对所述目标矩阵进行拆分，得到多个子矩阵；
    控制模块，用于基于每个子矩阵中的矩阵元素以及所述目标车辆的周围车辆的行驶控制信息，获取所述目标车辆的目标行驶控制信息，所述目标行驶控制信息用于控制所述目标车辆。
  8. 根据权利要求7所述的装置，其中，所述拆分模块，用于基于所述目标矩阵中所述目标车辆的当前状态及下一个状态，以及对所述下一个状态采样得到的采样点和标准正态分布函数，根据非参数估计的方式确定每个子矩阵中的矩阵元素。
  9. 根据权利要求8所述的装置，其中，所述装置还包括计算模块，用于对于任一矩阵元素，基于所述矩阵元素进行迭代计算，得到更新后的矩阵元素。
  10. 根据权利要求9所述的装置，其中，所述计算模块，用于对于任一矩阵元素，确定所述矩阵元素在不同时刻对应的数值；响应于所述矩阵元素在不同时刻对应的数值不同，根据所述矩阵元素在不同时刻对应的数值进行迭代计算，得到更新后的矩阵元素，所述更新后的矩阵元素在不同时刻对应有相同的数值。
  11. 根据权利要求7-10所述的装置，其中，所述控制模块，用于基于每个子矩阵中的矩阵元素，确定所述目标车辆的一个或多个下一个状态的概率值；根据下一个状态的概率值与行驶控制信息的对应关系，获取一个或多个参考行驶控制信息；基于所述目标车辆的周围车辆的行驶控制信息，从所述一个或多个参考行驶控制信息中获取所述目标行驶控制信息。
  12. 根据权利要求11所述的装置，其中，所述控制模块，用于基于所述目标车辆的周围车辆的行驶控制信息，确定每个参考行驶控制信息在未来一个或多个时刻中的每个时刻对应的回报数值；将每个时刻对应的回报数值之和最大的参考行驶控制信息作为所述目标行驶控制信息。
  13. 一种电子设备，其中，所述设备包括存储器及处理器；所述存储器中存储有至少一条指令，所述至少一条指令由所述处理器加载并执行，以实现权利要求1-6任一所述的控制车辆的方法。
  14. 一种非临时性计算机可读存储介质，其中，所述非临时性计算机可读存储介质中存储有至少一条指令，所述指令由处理器加载并执行以实现如权利要求1-6任一所述的控制车辆的方法。
PCT/CN2020/121620 2019-11-27 2020-10-16 控制车辆 WO2021103841A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP20893631.0A EP3919337B1 (en) 2019-11-27 2020-10-16 Control vehicle
JP2021555012A JP2023504945A (ja) 2019-11-27 2020-10-16 制御車両
US17/677,671 US20220176977A1 (en) 2019-11-27 2022-02-22 Vehicle control

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911185658.3 2019-11-27
CN201911185658.3A CN110920631B (zh) 2019-11-27 2019-11-27 控制车辆的方法、装置、电子设备及可读存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/677,671 Continuation-In-Part US20220176977A1 (en) 2019-11-27 2022-02-22 Vehicle control

Publications (1)

Publication Number Publication Date
WO2021103841A1 true WO2021103841A1 (zh) 2021-06-03

Family

ID=69846973

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/121620 WO2021103841A1 (zh) 2019-11-27 2020-10-16 控制车辆

Country Status (5)

Country Link
US (1) US20220176977A1 (zh)
EP (1) EP3919337B1 (zh)
JP (1) JP2023504945A (zh)
CN (1) CN110920631B (zh)
WO (1) WO2021103841A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210114596A1 (en) * 2019-10-18 2021-04-22 Toyota Jidosha Kabushiki Kaisha Method of generating vehicle control data, vehicle control device, and vehicle control system

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110920631B (zh) * 2019-11-27 2021-02-12 北京三快在线科技有限公司 控制车辆的方法、装置、电子设备及可读存储介质
CN111859549B (zh) * 2020-07-28 2024-05-14 奇瑞汽车股份有限公司 单一配置整车重量与重心信息的确定方法及相关设备
CN112232700B (zh) * 2020-11-04 2024-01-09 广州宸祺出行科技有限公司 一种优化的专车指派的方法及系统
CN113734167B (zh) * 2021-09-10 2023-05-30 苏州智加科技有限公司 车辆控制方法、装置、终端及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2615598A1 (en) * 2012-01-11 2013-07-17 Honda Research Institute Europe GmbH Vehicle with computing means for monitoring and predicting traffic participant objects
CN103381826A (zh) * 2013-07-31 2013-11-06 中国人民解放军国防科学技术大学 基于近似策略迭代的自适应巡航控制方法
CN108725452A (zh) * 2018-06-01 2018-11-02 湖南工业大学 一种基于全声频感知的无人驾驶车辆控制系统及控制方法
CN109572550A (zh) * 2018-12-28 2019-04-05 西安航空学院 一种行车轨迹预测方法、系统、计算机设备及存储介质
CN109727490A (zh) * 2019-01-25 2019-05-07 江苏大学 一种基于行车预测场的周边车辆行为自适应矫正预测方法
CN110386145A (zh) * 2019-06-28 2019-10-29 北京理工大学 一种目标驾驶员驾驶行为实时预测系统
CN110497906A (zh) * 2019-08-30 2019-11-26 北京百度网讯科技有限公司 车辆控制方法、装置、设备和介质
CN110920631A (zh) * 2019-11-27 2020-03-27 北京三快在线科技有限公司 控制车辆的方法、装置、电子设备及可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102717797B (zh) * 2012-06-14 2014-03-12 北京理工大学 一种混合动力车辆能量管理方法及能量管理系统
CN108009524B (zh) * 2017-12-25 2021-07-09 西北工业大学 一种基于全卷积网络的车道线检测方法
US10618522B2 (en) * 2018-03-27 2020-04-14 Hong Kong Productivity Council (HKPC) Drowsiness detection and intervention system and method
CN110077416B (zh) * 2019-05-07 2020-12-11 济南大学 一种基于决策树的驾驶员意图分析方法及系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2615598A1 (en) * 2012-01-11 2013-07-17 Honda Research Institute Europe GmbH Vehicle with computing means for monitoring and predicting traffic participant objects
CN103381826A (zh) * 2013-07-31 2013-11-06 中国人民解放军国防科学技术大学 基于近似策略迭代的自适应巡航控制方法
CN108725452A (zh) * 2018-06-01 2018-11-02 湖南工业大学 一种基于全声频感知的无人驾驶车辆控制系统及控制方法
CN109572550A (zh) * 2018-12-28 2019-04-05 西安航空学院 一种行车轨迹预测方法、系统、计算机设备及存储介质
CN109727490A (zh) * 2019-01-25 2019-05-07 江苏大学 一种基于行车预测场的周边车辆行为自适应矫正预测方法
CN110386145A (zh) * 2019-06-28 2019-10-29 北京理工大学 一种目标驾驶员驾驶行为实时预测系统
CN110497906A (zh) * 2019-08-30 2019-11-26 北京百度网讯科技有限公司 车辆控制方法、装置、设备和介质
CN110920631A (zh) * 2019-11-27 2020-03-27 北京三快在线科技有限公司 控制车辆的方法、装置、电子设备及可读存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3919337A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210114596A1 (en) * 2019-10-18 2021-04-22 Toyota Jidosha Kabushiki Kaisha Method of generating vehicle control data, vehicle control device, and vehicle control system
US11654915B2 (en) * 2019-10-18 2023-05-23 Toyota Jidosha Kabushiki Kaisha Method of generating vehicle control data, vehicle control device, and vehicle control system

Also Published As

Publication number Publication date
US20220176977A1 (en) 2022-06-09
CN110920631B (zh) 2021-02-12
JP2023504945A (ja) 2023-02-08
EP3919337B1 (en) 2023-11-29
EP3919337A1 (en) 2021-12-08
CN110920631A (zh) 2020-03-27
EP3919337A4 (en) 2022-06-22

Similar Documents

Publication Publication Date Title
WO2021103841A1 (zh) 控制车辆
CN109712224B (zh) 虚拟场景的渲染方法、装置及智能设备
CN110986930B (zh) 设备定位方法、装置、电子设备及存储介质
WO2021082483A1 (en) Method and apparatus for controlling vehicle
CN110134744B (zh) 对地磁信息进行更新的方法、装置和系统
CN111553050B (zh) 汽车转向系统的结构校核方法、装置及存储介质
WO2022160727A1 (zh) 组件的吸附操作方法及终端
CN109977570B (zh) 车身噪声确定方法、装置及存储介质
CN111275607A (zh) 界面显示方法、装置、计算机设备及存储介质
CN112734346B (zh) 航线覆盖范围的确定方法、装置、设备及可读存储介质
WO2021218926A1 (zh) 图像显示方法、装置和计算机设备
CN111717205B (zh) 车辆控制方法、装置、电子设备及计算机可读存储介质
CN114594885A (zh) 应用图标的管理方法、装置、设备及计算机可读存储介质
CN114283395A (zh) 车道线检测的方法、装置、设备及计算机可读存储介质
CN111179628B (zh) 自动驾驶车辆的定位方法、装置、电子设备及存储介质
CN112699906B (zh) 获取训练数据的方法、装置及存储介质
CN113359851B (zh) 控制飞行器航行的方法、装置、设备及存储介质
CN114506383B (zh) 方向盘回正的控制方法、装置、终端、存储介质及产品
CN115379274B (zh) 基于图片的互动方法、装置、电子设备及存储介质
CN113734199B (zh) 车辆控制方法、装置、终端及存储介质
CN112000337B (zh) 调整车辆标识的方法、装置、电子设备及可读存储介质
CN113409235B (zh) 一种灭点估计的方法及装置
CN113052408B (zh) 一种社区聚合的方法及装置
CN114566064B (zh) 停车位的位置确定方法、装置、设备及存储介质
CN117269981A (zh) 一种三维点云车辆检测方法、终端及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20893631

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021555012

Country of ref document: JP

Kind code of ref document: A

Ref document number: 2020893631

Country of ref document: EP

Effective date: 20210903

NENP Non-entry into the national phase

Ref country code: DE