CN113581208B - Driving assistance mode switching method, device, equipment and storage medium - Google Patents
Driving assistance mode switching method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113581208B CN113581208B CN202110893742.1A CN202110893742A CN113581208B CN 113581208 B CN113581208 B CN 113581208B CN 202110893742 A CN202110893742 A CN 202110893742A CN 113581208 B CN113581208 B CN 113581208B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- state
- determining
- driving
- preset
- 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.)
- Active
Links
Images
Classifications
-
- 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
- B60W60/005—Handover processes
- B60W60/0051—Handover processes from occupants to vehicle
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- 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
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
- B60W2050/0031—Mathematical model of the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a driving assistance mode switching method, a driving assistance mode switching device, driving assistance mode switching equipment and a storage medium. The method comprises the following steps: determining driving intention according to the obtained vehicle control information obtained by the vehicle sensor; the vehicle deviation degree is determined by sensing the surrounding environment through a vehicle body sensor, and the current vehicle speed is obtained; determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed; and determining a corresponding target driving auxiliary mode according to the driving intention and the running state of the vehicle, and switching the current mode to the target driving auxiliary mode. By the method, the vehicle running state is determined according to the vehicle deviation degree and the current vehicle speed, and the switching mode is determined according to the intention of the driver and the vehicle running state, so that the driving auxiliary mode is switched more intelligently, the influence of subjective consciousness of the driver on the auxiliary mode switching is avoided, the accuracy of the driving auxiliary mode judgment is improved, and the driving safety is improved.
Description
Technical Field
The present invention relates to the field of driving assistance technologies, and in particular, to a driving assistance mode switching method, device, apparatus, and storage medium.
Background
When a driver drives a vehicle, a driving auxiliary mode is manually selected according to driving experience, and if the danger exists in front or the sight of the driver is blocked, the driver has judgment deviation, so that the adjustment is not timely, and the driving safety is difficult to ensure.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a driving assistance mode switching method, a driving assistance mode switching device, driving assistance mode switching equipment and a storage medium, and aims to solve the technical problems that driving assistance mode judgment is inaccurate and driving safety is difficult to guarantee.
To achieve the above object, the present invention provides a driving assistance mode switching method including the steps of:
acquiring vehicle control information through a vehicle sensor, and determining driving intention according to the vehicle control information;
sensing the surrounding environment through a vehicle body sensor, determining the vehicle offset degree, and acquiring the current vehicle speed;
determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed;
and determining a corresponding target driving auxiliary mode according to the driving intention and the vehicle running state, and switching the current mode to the target driving auxiliary mode.
Optionally, the determining the vehicle running state according to the vehicle deviation degree and the current vehicle speed through a preset vehicle random motion prediction model includes:
determining a state transition probability matrix corresponding to the Markov chain;
determining a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle offset degree and the current vehicle speed;
determining a current vehicle state according to the preset vehicle random motion prediction model;
matching the current vehicle state with a preset typical dangerous scene to obtain a matching result;
and determining the running state of the vehicle according to the matching result.
Optionally, the determining a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle offset degree and the current vehicle speed includes:
coding the vehicle offset degree and the current vehicle speed according to a Markov chain, and randomly forming a plurality of state groups;
determining a first state group corresponding to a first moment according to the state transition probability matrix and the state groups, and determining a first state meeting preset requirements according to the first state group;
determining a second state group corresponding to a second moment according to the first state group and the state transition probability matrix, and determining a second state meeting preset requirements according to the second state group;
Similarly, determining a prediction state meeting a preset requirement within a preset prediction time;
and determining a preset vehicle random motion prediction model according to the target state, the first state, the second state and the prediction state.
Optionally, the determining the current vehicle state according to the preset vehicle random motion prediction model includes:
decoding according to a state code corresponding to the preset vehicle random motion prediction model, and determining a predicted vehicle deviation degree and a predicted vehicle speed;
and determining the current vehicle state according to the predicted vehicle deviation degree and the predicted vehicle speed.
Optionally, before the matching between the current vehicle state and the preset typical dangerous scene and obtaining the matching result, the method further includes:
in the running process of the vehicle, obtaining running lane number information, road opening shape information, homodromous lane number information, time period information, scene area information and traffic flow information;
forming a sample set according to a plurality of groups of the lane number information, the shape information of the road mouth, the equidirectional lane number information, the time period information, the scene area information and the traffic flow information;
And carrying out cluster analysis according to the sample set to generate a preset typical dangerous scene.
Optionally, the performing cluster analysis according to the sample set, generating a preset typical dangerous scene includes:
determining a sample distance between samples according to the sample set;
determining typical features corresponding to each scene according to the sample distance;
and generating a preset typical dangerous scene according to the typical characteristics.
Optionally, the determining a corresponding target driving assistance mode according to the driving intention and the vehicle running state, and switching the current mode to the target driving assistance mode, includes:
when the driving intention is urgent or the vehicle running state is dangerous, determining that a corresponding target driving auxiliary mode is an urgent auxiliary mode, and switching a current mode to the urgent auxiliary mode;
determining that a corresponding target driving assistance mode is a cautious assistance mode when the driving intention is normal and the vehicle running state is a safe state, and switching a current mode to the cautious assistance mode;
and when the driving intention is slow and the vehicle running state is a safe state, determining that the corresponding target driving auxiliary mode is a normal auxiliary mode, and switching the current mode to the normal auxiliary mode.
In addition, in order to achieve the above object, the present invention also proposes a driving assistance mode switching apparatus including:
the acquisition module is used for acquiring vehicle control information through a vehicle sensor and determining driving intention according to the vehicle control information;
the determining module is used for sensing the surrounding environment through the vehicle body sensor, determining the vehicle offset degree and acquiring the current vehicle speed;
the determining module is further used for determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed;
and the switching module is used for determining a corresponding target driving auxiliary mode according to the driving intention and the vehicle running state and switching the current mode to the target driving auxiliary mode.
In addition, to achieve the above object, the present invention also proposes a driving assistance mode switching apparatus including: a memory, a processor, and a driving assistance mode switching program stored on the memory and executable on the processor, the driving assistance mode switching program configured to implement the driving assistance mode switching method as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a driving assistance mode switching program which, when executed by a processor, implements the driving assistance mode switching method as described above.
The method comprises the steps of acquiring vehicle control information through a vehicle sensor, and determining driving intention according to the vehicle control information; sensing the surrounding environment through a vehicle body sensor, determining the vehicle offset degree, and acquiring the current vehicle speed; determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed; and determining a corresponding target driving auxiliary mode according to the driving intention and the running state of the vehicle, and switching the current mode to the target driving auxiliary mode. By the method, the driving intention is determined according to the vehicle control information, the vehicle driving state is determined according to the vehicle deviation degree and the current vehicle speed, the switching mode is selected according to the driver intention and the vehicle driving state, the intelligence of the switching of the driving auxiliary mode is improved, the mode to be switched is determined according to the objective sensing data around the vehicle, the influence of the subjective consciousness of the driver on the switching of the auxiliary mode is avoided, the driving safety is improved, and the problem of inaccurate judgment of the driving auxiliary mode is solved.
Drawings
Fig. 1 is a schematic structural diagram of a driving assistance mode switching apparatus of a hardware operation environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a driving assistance mode switching method according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a driving assistance mode switching method according to a second embodiment of the present invention;
fig. 4 is a block diagram showing the construction of a first embodiment of the driving assistance mode switching apparatus of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a driving assistance mode switching device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the driving assistance mode switching apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the driving assist mode switching device, and may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a driving assistance mode switching program may be included in the memory 1005 as one type of storage medium.
In the driving assistance mode switching apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the driving assistance mode switching apparatus of the present invention may be provided in the driving assistance mode switching apparatus, which invokes the driving assistance mode switching program stored in the memory 1005 through the processor 1001 and executes the driving assistance mode switching method provided by the embodiment of the present invention.
An embodiment of the present invention provides a driving assistance mode switching method, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the driving assistance mode switching method of the present invention.
In this embodiment, the driving assistance mode switching method includes the steps of:
step S10: and acquiring vehicle control information through a vehicle sensor, and determining the driving intention according to the vehicle control information.
It may be understood that the execution body of the embodiment is a driving assistance mode switching device, and the driving assistance mode switching device may be a vehicle controller, a controller connected to a vehicle control end, or other devices with the same or similar functions, and the embodiment is described by taking the domain controller as an example. The domain controller is connected with a sensor which is arranged on the vehicle and used for collecting vehicle control information, receives the vehicle control information sent by the sensor, and determines the driving intention according to the vehicle control information.
The vehicle control information includes an accelerator pedal opening, an accelerator pedal opening change rate, a brake pedal opening change rate, a steering wheel angle opening change rate, an accelerator pedal cycle control number, a brake pedal cycle control number, and a steering wheel cycle control number, the accelerator pedal opening change rate, the brake pedal opening change rate, the steering wheel angle opening, and the steering wheel angle opening change rate are input into a pre-established preset driver state model, the model is analyzed and optimized by a preset adaptive particle swarm algorithm, an initial driving intention is determined, and the periodic driving intention is determined according to the accelerator pedal cycle control number, the brake pedal cycle control number, and the steering wheel cycle control number, and the initial driving intention is analyzed in combination to obtain the driving intention.
It will be appreciated that the pre-built pre-set driver state model is determined by equation (1):
wherein x is 1 ∈(α，dα/dt)，x 2 ∈(θ，dθ/dt)，x 3 ∈(δ，dδ/dt)，f(x 1 ，x 2 ，x 3 )∈[1，3]1 represents emergency driving, 2 represents normal driving, 3 represents slow driving, alpha is accelerator pedal opening, dα/dt is accelerator pedal opening change rate, θ is brake pedal opening, dθ/dt is brake pedal opening change rate, δ is steering wheel angle opening, and dδ/dt is steering wheel angle opening change rate.
The optimal value is obtained by optimizing a preset adaptive particle swarm algorithm according to a preset driver state model, and the initial driving intention, which is the actual optimal value, is output as emergency driving, normal driving or moderate driving by the input accelerator pedal, brake pedal, steering opening of the steering wheel and corresponding change rate.
It can be appreciated that the preset adaptive particle swarm algorithm is characterized by the formula (2) and the formula (3):
explaining the optimization process in combination with the formula (2) and the formula (3), the ith particle in the training set L is expressed as a vector of L, X i ＝(x i1 ，x i2 ，...，x iL ) I=1, 2,3, i.e. the position of the ith particle in the training set is X i The optimal position experienced by the ith particle is Pbest i ＝(p i1 ，p i2 ，...，p iL ) I=1, 2,3, i.e. the current individual optimal position, each position of the particle represents a potential solution of the requirement, and the particle position is input into the objective function to obtain the fitness value of the ith particle, so as to judge the particle quality. The optimal position searched by the whole particle swarm is Gbest g ＝(p jg ) I=1, 2,3, i.e. the current global optimum position, g denotes the index of the optimum particle position. ω represents the inertial weight and,
for the i-th particle to t-th generation, starting from the searched historical optimal solution, ++>
The global optimum thus far searched for the entire particle swarm is>
Respectively represent the firsti current position and flight speed of particles c 1 ，c 2 Represents a constant other than negative, r 1 ，r 2 Is [0,1 ]]Random numbers in between. In this embodiment, the iterative evolutionary frequency of the algorithm is set to 1000 times, and the acceleration factor c is preset 1 ＝1.4，c 2 =1.5, preset inertial weight ω=0.8. In the optimization process, for each particle, the fitness value of the particle is compared with the fitness value of the experienced current individual optimal position Pbesti, and if the fitness value is good, the position of the particle is taken as a new current individual optimal position. For each particle, its fitness value is compared with the best global position Gbest g If the fitness value of the particle is better, the position of the particle is taken as a new global optimal position. If the global optimal position cannot meet the minimum error requirement, the initial driving intention of the output is represented to be inconsistent with the actual, the speed and the position of the particles are optimized according to the formula (2) and the formula (3), and the new particles are compared with the current individual optimal position and the global optimal position until the global optimal position meets the minimum error requirement.
The process of determining the periodic driving intention according to the number of accelerator pedal periodic control, the number of brake pedal periodic control and the number of steering wheel periodic control is as follows: describing the first 10 seconds of taking the acquisition period as the current time, the periodic driving intention is determined by the formula (4):
wherein the periodic driving intention T epsilon [1,3 ]]1 represents emergency driving, 2 represents normal driving, 3 represents moderate driving, F α For controlling the number of times of the accelerator pedal, F θ For controlling the number of times of the brake pedal, F δ The number of steering wheel controls; in a preset acquisition period, if the control times of a driver on an accelerator pedal, a brake pedal and a steering wheel are less than 3 times, the periodic driving intention is considered to be mild driving; if the control times of the accelerator pedal and the brake pedal are more than or equal to 3 times and the control times of the steering wheel are less than 3 times, the control method comprises the following steps ofConsider the periodic driving intention to be normal driving; if the number of times of control of the accelerator pedal, the brake pedal and the steering wheel by the driver is 3 or more, the periodic driving intention is considered to be emergency driving.
In a specific implementation, the driving intention is determined by the formula (5) in combination with the initial driving intention and the initial driving intention:
In a specific implementation, the periodic driving intention T is taken as the main, and when the periodic driving intention t=1, the driving intention identity is determined as emergency driving; when the periodic driving intention T is equal to or greater than 2 and the initial driving intention f (x 1 ，x 2 ，x 3 ) When the driving intention is less than 3, the driving intention is considered to be normal driving; when the periodic driving intention t=3 and the initial driving intention f (x 1 ，x 2 ，x 3 ) When=3, the driving intention is considered as moderate driving.
Step S20: and sensing the surrounding environment through a vehicle body sensor, determining the vehicle offset degree, and acquiring the current vehicle speed.
It can be understood that the vehicle offset degree refers to the ratio of the distance between the vehicle and the road center line to the road width, in a specific implementation, the position of the lane line is identified by a camera installed around the vehicle by adopting a lane line identification technology, the distance between the vehicle and the lane line is determined according to the internal and external parameters of the camera and the installation height, the distance between the vehicle and the road center line is further determined, the road width is a fixed value, and the vehicle offset degree can be obtained according to the pre-stored road width when the distance between the vehicle and the road center line is obtained. The current speed is the running speed of the vehicle at the current moment, and is acquired through a speed sensor arranged on the vehicle.
Step S30: and determining the running state of the vehicle through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed.
It should be noted that, a random array is constructed according to the vehicle offset degree and the current vehicle speed, and is used for representing the current state, a state transition matrix is constructed based on a markov chain model, states corresponding to the next time are predicted according to the state transition matrix and the current state, states corresponding to a plurality of times are determined by such pushing, a preset vehicle random motion prediction model is generated according to the states corresponding to the plurality of times, and the vehicle running state is determined according to the preset vehicle random motion prediction model.
Step S40: and determining a corresponding target driving auxiliary mode according to the driving intention and the vehicle running state, and switching the current mode to the target driving auxiliary mode.
Specifically, the step S40 includes: when the driving intention is urgent or the vehicle running state is dangerous, determining that a corresponding target driving auxiliary mode is an urgent auxiliary mode, and switching a current mode to the urgent auxiliary mode; determining that a corresponding target driving assistance mode is a cautious assistance mode when the driving intention is normal and the vehicle running state is a safe state, and switching a current mode to the cautious assistance mode; and when the driving intention is slow and the vehicle running state is a safe state, determining that the corresponding target driving auxiliary mode is a normal auxiliary mode, and switching the current mode to the normal auxiliary mode.
It should be noted that, when the domain controller acquires the driving intention and the vehicle running state, the domain controller determines the corresponding target driving assistance mode according to formula (6):
wherein, a driving assistance Mode (DAS) E [1,3],1 represents an imminace emergency assistance Mode, 2 represents a Cautious Cautious assistance Mode, and 3 represents a Normal assistance Mode; the driving intention is expressed as an element E [1,3],1 represents emergency driving, 2 represents moderate driving, and 3 represents normal driving; the Vehicle running state Vehicle includes a dangerous state Danger and a normal running state ratio.
It should be appreciated that when the driving assistance mode is an imminace emergency assistance mode, the following manner of assistance of the vehicle in the imminace emergency assistance mode is indicative of the current driver or vehicle being in a dangerous environment: the driving assistance such as automatic emergency braking, safety belts, safety airbags and the like can set the automatic adjustment function, such as automatic emergency braking sensitivity, braking distance and the like, to the highest, and the safety belts and the safety airbags can be triggered at any time so as to prevent vehicle collision and maximally protect the safety of a driver. When the driving assistance mode is a Cautious Cautious assistance mode, the driving state of the driver is normal, the environment where the vehicle is located is safe, and the driving assistance is in a Cautious state; when the driving assistance mode is Normal, the driving state of the driver is relaxed, the environment where the vehicle is located is safe, and the driving assistance is in a Normal state.
In the embodiment, vehicle control information is acquired through a vehicle sensor, and driving intention is determined according to the vehicle control information; sensing the surrounding environment through a vehicle body sensor, determining the vehicle offset degree, and acquiring the current vehicle speed; determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed; and determining a corresponding target driving auxiliary mode according to the driving intention and the running state of the vehicle, and switching the current mode to the target driving auxiliary mode. By the method, the driving intention is determined according to the vehicle control information, the vehicle driving state is determined according to the vehicle deviation degree and the current vehicle speed, the switching mode is selected according to the driver intention and the vehicle driving state, the intelligence of the switching of the driving auxiliary mode is improved, the mode to be switched is determined according to the objective sensing data around the vehicle, the influence of the subjective consciousness of the driver on the switching of the auxiliary mode is avoided, the driving safety is improved, and the problem of inaccurate judgment of the driving auxiliary mode is solved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a driving assistance mode switching method according to a second embodiment of the present invention.
Based on the above-described first embodiment, the step S30 of the driving assistance mode switching method of the present embodiment includes:
Step S301: and determining a state transition probability matrix corresponding to the Markov chain.
It can be understood that, in this embodiment, a discrete adaptive markov chain is adopted, and a markov chain model (S, P) is provided, S is a non-empty state set formed by all states of the mahalanobis chain, and P is a state transition probability matrix of the mahalanobis chain. The specific process can be as follows: determining a state transition probability by equation (7) through conditional probability definition:
p ij ＝P{X{t+1}＝s j |X(t)＝s i } (7)
wherein p is ij The transition probability of the Markov chain { X (t) } at the time t represents the time from the time t to the time s i Transition to time t+1 s j I.e. the probability that the current time vehicle state transitions to the next time vehicle state. In the training set, the vehicle deviation degree and the vehicle speed are divided into a plurality of segments to form different states, and a state transition probability matrix P is formed according to different state transitions and is expressed as a formula (8):
wherein N is ij Representing the current vehicle state s i The next time shifts to s j Frequency, sigma of j N ij Representing the current state s i The next time the frequency of transition to all states.
Step S302: and determining a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle offset degree and the current vehicle speed.
The preset vehicle random motion prediction model is a state of a plurality of moments determined according to a state transition probability matrix, a vehicle deviation degree and a current vehicle speed, and is formed according to the states of the plurality of moments.
Specifically, the step S302 includes: coding the vehicle offset degree and the current vehicle speed according to a Markov chain, and randomly forming a plurality of state groups; determining a first state group corresponding to a first moment according to the state transition probability matrix and the state groups, and determining a first state meeting preset requirements according to the first state group; determining a second state group corresponding to a second moment according to the first state group and the state transition probability matrix, and determining a second state meeting preset requirements according to the second state group; similarly, determining a prediction state meeting a preset requirement within a preset prediction time; and determining a preset vehicle random motion prediction model according to the target state, the first state, the second state and the prediction state.
It will be appreciated that suppose [ d ] 0 ，v 0 ]Corresponding to the state s of the vehicle at the current moment 0 At the current moment U 0 ＝s 0 Generating a random array, i.e. a plurality of state sets { r } 1 ，r 2 ，r 3 ,., a random array characterizes the state in which a vehicle is likely to travel, e.g., r 1 Representing left turn, r 2 Representing straight movement, r 3 Representing right turn, at the current vehicle state X (0) =s 0 Under the condition that the prediction of the vehicle state at the next moment happens, the conditional distribution probability of the vehicle state X (1) at the next moment is p 0j ＝P{X{1}＝s j |X(0)＝s i The state transition probability matrix indicates a probability that the state of the vehicle at the present time transitions to a certain state of the vehicle at the next time, for example, a matrix of a probability that the vehicle is straight at this time, a probability that the vehicle is turning left, a probability that the vehicle is straight at the next time, a probability that the vehicle is turning right, and the like.
It should be noted that, the process of predicting the state at the next moment according to the state transition probability matrix and the state groups may be: fetching the kth from the state transition probability matrix P 0 All elements are lined; taking random number r 1 If there is a certain k 1 Satisfy the following requirements
I.e. it can be determined that the next time the vehicle is in the state s 1 U, i.e. U 1 ＝s 1 。
It will be appreciated that the random number r is assumed 1 K representing the probability matrix of taking out the state transition assuming the vehicle is ready for left turn 1 A row representing the probability of taking out the state transition of the vehicle at the next moment, if it is assumed that the state of the left turn of the vehicle satisfies k 1 The condition of the state transition of the vehicle at the moment is considered to be that the vehicle is ready for left turn at the next moment, and the like, if the condition is not satisfied, the random number r is taken 2 Continuing at k 1 And comparing the time and the vehicle state transition probability. Until the state of the assumed vehicle transition satisfies the vehicle state transition probability. And so on, according to k 1 Time vehicle state and state transition probability matrix pair k 2 Predicting the vehicle states at the moment to obtain a plurality of vehicle states to form a preset vehicle random motion prediction model U n ＝{s 1 ，s 2 ，...)。
Step S303: and determining the current vehicle state according to the preset vehicle random motion prediction model.
Specifically, the step S303 includes: decoding according to a state code corresponding to the preset vehicle random motion prediction model, and determining a predicted vehicle deviation degree and a predicted vehicle speed; and determining the current vehicle state according to the predicted vehicle deviation degree and the predicted vehicle speed.
It can be understood that the corresponding vehicle deviation state and vehicle speed information are determined through inverse check coding according to the preset vehicle random motion prediction model, and the current vehicle state is obtained.
Step S304: and matching the current vehicle state with a preset typical dangerous scene to obtain a matching result.
Further, before the step S304, the method further includes: in the running process of the vehicle, obtaining running lane number information, road opening shape information, homodromous lane number information, time period information, scene area information and traffic flow information; forming a sample set according to a plurality of groups of the lane number information, the shape information of the road mouth, the equidirectional lane number information, the time period information, the scene area information and the traffic flow information; and carrying out cluster analysis according to the sample set to generate a preset typical dangerous scene.
It should be noted that, when analyzing a preset typical dangerous scene, the method collects characteristics of 7 scene elements, including: driving lane number information, road junction shape information, equidirectional lane number information, time period information, scene area information, and traffic flow information. In a specific implementation, a distance between different variables is defined as 1, a distance between the same variables is defined as 0, and variable codes in each scene element in the collected sample set are converted into vectors, for example: the time period information has the variables of day and night, and the corresponding vectors are encoded with day [1,0] and night [0,1]. And carrying out cluster analysis according to the converted sample set to generate a preset typical dangerous scene.
Specifically, cluster analysis is performed according to the sample set, and a preset typical dangerous scene is generated, including: determining a sample distance between samples according to the sample set; determining typical features corresponding to each scene according to the sample distance; and generating a preset typical dangerous scene according to the typical characteristics.
It will be appreciated that assume X 1 ，X 2 ，X 3 ，...，X n For p-ary samples from the sample set, the ith sample is denoted as X i ＝(x i1 ，x i2 ，x i3 ，...，x ip ) (i=1, 2,3,., n), distance d between the i-th sample and the j-th sample ij Expressed by formula (9):
according to the comparison of the ratio of the sample spacing in each scene to the ratio of the scene in the overall training set, the typical characteristics of each scene element are determined, in this embodiment, 3 preset typical dangerous scenes are determined, and the first is: the road traffic system comprises a running lane number (lane 1), a road opening shape (non-intersection), the number of equidirectional lanes (2 lanes), a time period (daytime), a scene area (city) and traffic flow (right side has vehicles); second kind: the number of driving tracks (number 3 lanes), the shape of the road mouth (T-junction), the number of equidirectional lanes (3 lanes), the time period (night), the scene area (high speed), the traffic flow (intrusion from both sides); third kind: the road traffic system comprises a running lane number (lane 1), a road opening shape (non-intersection), the same-direction lane number (lane 1), a time period (daytime), a scene area (suburban area) and traffic flow (left side has vehicles).
In a specific implementation, when the current vehicle state is matched with a preset typical dangerous scene, discrete information is selected from the preset typical dangerous scene, and the discrete information is matched with the current vehicle state, so that a matching result is obtained.
Step S305: and determining the running state of the vehicle according to the matching result.
It should be noted that, whether the current Vehicle state belongs to a typical dangerous scene is determined to obtain the Vehicle driving state Vehicle at the Vehicle end, including a dangerous state Danger and a normal driving state ratio.
The embodiment determines a state transition probability matrix corresponding to the Markov chain; determining a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle offset degree and the current vehicle speed; determining a current vehicle state according to a preset vehicle random motion prediction model; matching the current vehicle state with a preset typical dangerous scene to obtain a matching result; and determining the running state of the vehicle according to the matching result. And determining a corresponding target driving auxiliary mode according to the driving intention and the running state of the vehicle, and switching the current mode to the target driving auxiliary mode. By means of the method, the vehicle state is predicted according to the Markov chain state transition probability matrix, the vehicle running state is determined according to the matching result of the vehicle state and the preset typical dangerous scene, the switching mode is selected according to the intention of the driver and the vehicle running state, the intelligence of switching the driving auxiliary mode is improved, the dangerous running state is predicted in advance, the driving safety is improved, and the problem that the driving auxiliary mode is inaccurate in judgment is solved.
In addition, the embodiment of the invention also provides a storage medium, wherein a driving assistance mode switching program is stored on the storage medium, and the driving assistance mode switching program realizes the driving assistance mode switching method when being executed by a processor.
Because the storage medium adopts all the technical schemes of all the embodiments, the storage medium has at least all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
Referring to fig. 4, fig. 4 is a block diagram showing the structure of a first embodiment of the driving assistance mode switching apparatus of the present invention.
As shown in fig. 4, the driving assistance mode switching apparatus provided by the embodiment of the present invention includes:
an acquisition module 10 for acquiring vehicle control information by a vehicle sensor, and determining a driving intention based on the vehicle control information.
The determining module 20 is configured to determine a vehicle offset degree by sensing a surrounding environment through a vehicle body sensor, and acquire a current vehicle speed.
The determining module 20 is further configured to determine a vehicle driving state according to the vehicle deviation degree and the current vehicle speed through a preset vehicle random motion prediction model.
And a switching module 30, configured to determine a corresponding target driving assistance mode according to the driving intention and the vehicle driving state, and switch the current mode to the target driving assistance mode.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
In the embodiment, vehicle control information is acquired through a vehicle sensor, and driving intention is determined according to the vehicle control information; sensing the surrounding environment through a vehicle body sensor, determining the vehicle offset degree, and acquiring the current vehicle speed; determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed; and determining a corresponding target driving auxiliary mode according to the driving intention and the running state of the vehicle, and switching the current mode to the target driving auxiliary mode. By the method, the driving intention is determined according to the vehicle control information, the vehicle driving state is determined according to the vehicle deviation degree and the current vehicle speed, the switching mode is selected according to the driver intention and the vehicle driving state, the intelligence of the switching of the driving auxiliary mode is improved, the mode to be switched is determined according to the objective sensing data around the vehicle, the influence of the subjective consciousness of the driver on the switching of the auxiliary mode is avoided, the driving safety is improved, and the problem of inaccurate judgment of the driving auxiliary mode is solved.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in the present embodiment may refer to the driving assistance mode switching method provided in any embodiment of the present invention, and are not described herein.
In an embodiment, the determining module 20 is further configured to determine a state transition probability matrix corresponding to a mahalanobis chain, determine a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle deviation degree, and the current vehicle speed, determine a current vehicle state according to the preset vehicle random motion prediction model, match the current vehicle state with a preset typical dangerous scene, obtain a matching result, and determine a vehicle driving state according to the matching result.
In an embodiment, the determining module 20 is further configured to encode the vehicle offset degree and the current vehicle speed according to a mahalanobis chain, randomly form a plurality of state groups, determine a first state group corresponding to a first time according to the state transition probability matrix and the state groups, determine a first state meeting a preset requirement according to the first state group, determine a second state group corresponding to a second time according to the first state group and the state transition probability matrix, determine a second state meeting the preset requirement according to the second state group, and so on, determine a prediction state meeting the preset requirement within a preset prediction time, and determine a prediction model of random motion of the preset vehicle according to the target state, the first state, the second state and the prediction state.
In an embodiment, the determining module 20 is further configured to decode according to a state code corresponding to the preset vehicle random motion prediction model, determine a predicted vehicle offset degree and a predicted vehicle speed, and determine a current vehicle state according to the predicted vehicle offset degree and the predicted vehicle speed.
In an embodiment, the driving assistance mode switching device further includes a scene generation module;
the scene generation module is used for acquiring driving lane number information, road mouth shape information, same-direction lane number information, time period information, scene area information and traffic flow information in the driving process of the vehicle, forming a sample set according to a plurality of groups of the driving lane number information, the road mouth shape information, the same-direction lane number information, the time period information, the scene area information and the traffic flow information, and performing cluster analysis according to the sample set to generate a preset typical dangerous scene.
In an embodiment, the scene generating module is further configured to determine a sample distance between samples according to the sample set, determine typical features corresponding to each scene according to the sample distance, and generate a preset typical dangerous scene according to the typical features.
In an embodiment, the switching module 30 is further configured to determine that the corresponding target driving assistance mode is an emergency assistance mode when the driving intention is emergency or the vehicle running state is dangerous, switch the current mode to the emergency assistance mode, determine that the corresponding target driving assistance mode is a cautious assistance mode when the driving intention is normal and the vehicle running state is safe, switch the current mode to the cautious assistance mode, and determine that the corresponding target driving assistance mode is a normal assistance mode when the driving intention is slow and the vehicle running state is safe, and switch the current mode to the normal assistance mode.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. A driving assistance mode switching method, characterized by comprising:
acquiring vehicle control information through a vehicle sensor, and determining driving intention according to the vehicle control information;
sensing the surrounding environment through a vehicle body sensor, determining the vehicle offset degree, and acquiring the current vehicle speed;
determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed;
determining a corresponding target driving auxiliary mode according to the driving intention and the vehicle running state, and switching the current mode to the target driving auxiliary mode;
the method for acquiring the vehicle control information through the vehicle sensor, determining the driving intention according to the vehicle control information comprises the following steps:
when the periodic driving intention t=1, the driving intention is recognized as emergency driving; when the periodic driving intention T is equal to or greater than 2 and the initial driving intention f (x 1, x2, x 3) < 3, recognizing the driving intention as normal driving; when the periodic driving intention t=3 and the initial driving intention f (x 1, x2, x 3) =3, the driving intention is considered to be a moderate driving; wherein, periodic driving intentions T epsilon [1,3], f (x 1, x2, x 3) epsilon [1,3],1 represents emergency driving, 2 represents normal driving, 3 represents moderate driving; x1 ε (α, dα/dt), x2 ε (θ, dθ/dt), x3 ε (δ, dδ/dt), α is accelerator pedal opening, dα/dt is accelerator pedal opening rate of change, θ is brake pedal opening, dθ/dt is brake pedal opening rate of change, δ is steering wheel angle opening, dδ/dt is steering wheel angle opening rate of change;
Wherein, the determining the vehicle running state according to the vehicle deviation degree and the current vehicle speed through a preset vehicle random motion prediction model comprises the following steps:
determining a state transition probability matrix corresponding to the Markov chain;
determining a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle offset degree and the current vehicle speed;
determining a current vehicle state according to the preset vehicle random motion prediction model;
matching the current vehicle state with a preset typical dangerous scene to obtain a matching result;
determining a vehicle running state according to the matching result;
the determining a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle offset degree and the current vehicle speed comprises the following steps:
coding the vehicle offset degree and the current vehicle speed according to a Markov chain, and randomly forming a plurality of state groups;
determining a first state group corresponding to a first moment according to the state transition probability matrix and the state groups, and determining a first state meeting preset requirements according to the first state group;
determining a second state group corresponding to a second moment according to the first state group and the state transition probability matrix, and determining a second state meeting preset requirements according to the second state group;
Similarly, determining a prediction state meeting a preset requirement within a preset prediction time;
determining a preset vehicle random motion prediction model according to the first state, the second state and the prediction state;
wherein, the determining the current vehicle state according to the preset vehicle random motion prediction model includes:
decoding according to a state code corresponding to the preset vehicle random motion prediction model, and determining a predicted vehicle deviation degree and a predicted vehicle speed;
and determining the current vehicle state according to the predicted vehicle deviation degree and the predicted vehicle speed.
2. The driving assistance mode switching method according to claim 1, wherein said matching said current vehicle state with a preset typical dangerous scene, before obtaining a matching result, said method further comprises:
in the running process of the vehicle, obtaining running lane number information, road opening shape information, homodromous lane number information, time period information, scene area information and traffic flow information;
forming a sample set according to a plurality of groups of the lane number information, the shape information of the road mouth, the equidirectional lane number information, the time period information, the scene area information and the traffic flow information;
And carrying out cluster analysis according to the sample set to generate a preset typical dangerous scene.
3. The driving assistance mode switching method according to claim 2, wherein the performing cluster analysis according to the sample set to generate a preset typical dangerous scene includes:
determining a sample distance between samples according to the sample set;
determining typical features corresponding to each scene according to the sample distance;
and generating a preset typical dangerous scene according to the typical characteristics.
4. A driving assistance mode switching method according to any one of claims 1 to 3, wherein said determining a corresponding target driving assistance mode according to said driving intention and said vehicle running state, switching a current mode to said target driving assistance mode, comprises:
when the driving intention is urgent or the vehicle running state is dangerous, determining that a corresponding target driving auxiliary mode is an urgent auxiliary mode, and switching a current mode to the urgent auxiliary mode;
determining that a corresponding target driving assistance mode is a cautious assistance mode when the driving intention is normal and the vehicle running state is a safe state, and switching a current mode to the cautious assistance mode;
And when the driving intention is slow and the vehicle running state is a safe state, determining that the corresponding target driving auxiliary mode is a normal auxiliary mode, and switching the current mode to the normal auxiliary mode.
5. A driving assistance mode switching device, characterized by comprising:
the acquisition module is used for acquiring vehicle control information through a vehicle sensor and determining driving intention according to the vehicle control information;
the determining module is used for sensing the surrounding environment through the vehicle body sensor, determining the vehicle offset degree and acquiring the current vehicle speed;
the determining module is further used for determining a vehicle running state through a preset vehicle random motion prediction model according to the vehicle deviation degree and the current vehicle speed;
the switching module is used for determining a corresponding target driving auxiliary mode according to the driving intention and the vehicle running state and switching the current mode to the target driving auxiliary mode;
the acquisition module is further used for recognizing the driving intention as emergency driving when the periodic driving intention T=1; when the periodic driving intention T is equal to or greater than 2 and the initial driving intention f (x 1, x2, x 3) < 3, recognizing the driving intention as normal driving; when the periodic driving intention t=3 and the initial driving intention f (x 1, x2, x 3) =3, the driving intention is considered to be a moderate driving; wherein, periodic driving intentions T epsilon [1,3], f (x 1, x2, x 3) epsilon [1,3],1 represents emergency driving, 2 represents normal driving, 3 represents moderate driving; x1 ε (α, dα/dt), x2 ε (θ, dθ/dt), x3 ε (δ, dδ/dt), α is accelerator pedal opening, dα/dt is accelerator pedal opening rate of change, θ is brake pedal opening, dθ/dt is brake pedal opening rate of change, δ is steering wheel angle opening, dδ/dt is steering wheel angle opening rate of change;
The determining module is further used for determining a state transition probability matrix corresponding to the mahalanobis chain; determining a preset vehicle random motion prediction model according to the state transition probability matrix, the vehicle offset degree and the current vehicle speed; determining a current vehicle state according to the preset vehicle random motion prediction model; matching the current vehicle state with a preset typical dangerous scene to obtain a matching result; determining a vehicle running state according to the matching result;
the determining module is further used for encoding the vehicle offset degree and the current vehicle speed according to a Markov chain, and randomly forming a plurality of state groups; determining a first state group corresponding to a first moment according to the state transition probability matrix and the state groups, and determining a first state meeting preset requirements according to the first state group; determining a second state group corresponding to a second moment according to the first state group and the state transition probability matrix, and determining a second state meeting preset requirements according to the second state group; similarly, determining a prediction state meeting a preset requirement within a preset prediction time; determining a preset vehicle random motion prediction model according to the first state, the second state and the prediction state;
The determining module is further used for decoding according to the state code corresponding to the preset vehicle random motion prediction model, and determining the predicted vehicle deviation degree and the predicted vehicle speed; and determining the current vehicle state according to the predicted vehicle deviation degree and the predicted vehicle speed.
6. A driving assistance mode switching apparatus, characterized in that the apparatus comprises: a memory, a processor, and a driving assistance mode switching program stored on the memory and executable on the processor, the driving assistance mode switching program configured to implement the driving assistance mode switching method according to any one of claims 1 to 4.
7. A storage medium having stored thereon a driving assistance mode switching program which, when executed by a processor, implements the driving assistance mode switching method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893742.1A CN113581208B (en) | 2021-08-04 | 2021-08-04 | Driving assistance mode switching method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893742.1A CN113581208B (en) | 2021-08-04 | 2021-08-04 | Driving assistance mode switching method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113581208A CN113581208A (en) | 2021-11-02 |
| CN113581208B true CN113581208B (en) | 2023-06-20 |
Family
ID=78255271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110893742.1A Active CN113581208B (en) | 2021-08-04 | 2021-08-04 | Driving assistance mode switching method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113581208B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114435407A (en) * | 2022-03-24 | 2022-05-06 | 广州小鹏自动驾驶科技有限公司 | Vehicle control method and device and vehicle |
| CN116101303B (en) * | 2023-04-07 | 2023-07-07 | 成都理工大学工程技术学院 | Vehicle driving assisting method, system, device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102006060849A1 (en) * | 2006-12-22 | 2008-07-03 | Daimler Ag | Vehicle driver condition e.g. fatigue, determining method, involves developing probabilistic model representing cumulated probabilities, and determining condition as driver condition based on cumulated probabilities using model |
| JP2010069983A (en) * | 2008-09-17 | 2010-04-02 | Fuji Heavy Ind Ltd | Drive assistance device |
| JP2010274679A (en) * | 2009-05-26 | 2010-12-09 | Isuzu Motors Ltd | Traveling control device for vehicle |
| JP2012014713A (en) * | 2011-08-10 | 2012-01-19 | Nissan Motor Co Ltd | Operation aiding method, operation aiding device, control program, and vehicle |
| CN108297864A (en) * | 2018-01-25 | 2018-07-20 | 广州大学 | The control method and control system of driver and the linkage of vehicle active safety technologies |
| JP2019077290A (en) * | 2017-10-24 | 2019-05-23 | マツダ株式会社 | Vehicle control device |
| CN112277955A (en) * | 2020-10-30 | 2021-01-29 | 安徽江淮汽车集团股份有限公司 | Driving assistance method, device, equipment and storage medium |
| CN112477884A (en) * | 2020-11-11 | 2021-03-12 | 东风汽车集团有限公司 | Automatic driving control method and device and vehicle |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4752679B2 (en) * | 2005-10-13 | 2011-08-17 | 日産自動車株式会社 | Driving assistance device for vehicle |
| US10994729B2 (en) * | 2017-03-29 | 2021-05-04 | Mitsubishi Electric Research Laboratories, Inc. | System and method for controlling lateral motion of vehicle |
| EP3495223A1 (en) * | 2017-12-11 | 2019-06-12 | Volvo Car Corporation | Driving intervention in vehicles |
-
2021
- 2021-08-04 CN CN202110893742.1A patent/CN113581208B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102006060849A1 (en) * | 2006-12-22 | 2008-07-03 | Daimler Ag | Vehicle driver condition e.g. fatigue, determining method, involves developing probabilistic model representing cumulated probabilities, and determining condition as driver condition based on cumulated probabilities using model |
| WO2008083731A1 (en) * | 2006-12-22 | 2008-07-17 | Daimler Ag | Method for determining a driver state using a markov model |
| JP2010069983A (en) * | 2008-09-17 | 2010-04-02 | Fuji Heavy Ind Ltd | Drive assistance device |
| JP2010274679A (en) * | 2009-05-26 | 2010-12-09 | Isuzu Motors Ltd | Traveling control device for vehicle |
| JP2012014713A (en) * | 2011-08-10 | 2012-01-19 | Nissan Motor Co Ltd | Operation aiding method, operation aiding device, control program, and vehicle |
| JP2019077290A (en) * | 2017-10-24 | 2019-05-23 | マツダ株式会社 | Vehicle control device |
| CN108297864A (en) * | 2018-01-25 | 2018-07-20 | 广州大学 | The control method and control system of driver and the linkage of vehicle active safety technologies |
| CN112277955A (en) * | 2020-10-30 | 2021-01-29 | 安徽江淮汽车集团股份有限公司 | Driving assistance method, device, equipment and storage medium |
| CN112477884A (en) * | 2020-11-11 | 2021-03-12 | 东风汽车集团有限公司 | Automatic driving control method and device and vehicle |
Non-Patent Citations (3)
| Title |
|---|
| 基于双层隐马尔可夫模型的重型车辆行驶状态辨识方法研究;朱天军;孔现伟;李彬;;兵工学报(第10期);第10-18页 * |
| 基于驾驶员意图及行驶场景判断的智能驾驶模式识别策略;郑羿方;卢萍;;汽车实用技术(第09期);第61-65页 * |
| 汽车转向时驾驶员驾驶意图辨识与行为预测;宗长富;杨肖;王畅;张广才;;吉林大学学报(工学版)(第S1期);第30-35页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113581208A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111523643B (en) | Track prediction method, device, equipment and storage medium | |
| CN111942407B (en) | Trajectory prediction method, apparatus, device and storage medium | |
| US11458972B2 (en) | Vehicle control apparatus | |
| CN113581209B (en) | Driving assistance mode switching method, device, equipment and storage medium | |
| CN106740864B (en) | A kind of driving behavior is intended to judgement and prediction technique | |
| CN113581208B (en) | Driving assistance mode switching method, device, equipment and storage medium | |
| Kose et al. | Real-time driver state monitoring using a CNN based spatio-temporal approach | |
| JP2023510136A (en) | Geolocation models for perception, prediction or planning | |
| US20210276598A1 (en) | Machine-learning based system for path and/or motion planning and method of training the same | |
| CN114399743B (en) | Method for generating future track of obstacle | |
| Huang et al. | Spatial-temporal ConvLSTM for vehicle driving intention prediction | |
| CN113537445B (en) | Track prediction method, device, equipment and storage medium | |
| CN112435503A (en) | Intelligent automobile active collision avoidance method for identifying intention of high-risk pedestrians | |
| CN112734808A (en) | Trajectory prediction method for vulnerable road users in vehicle driving environment | |
| WO2021028533A1 (en) | Method, device, medium, and vehicle for providing individual driving experience | |
| CN114061581A (en) | Ranking agents in proximity to autonomous vehicles by mutual importance | |
| Griesbach et al. | Lane change prediction with an echo state network and recurrent neural network in the urban area | |
| KR20210152025A (en) | On-Vehicle Active Learning Method and Apparatus for Learning Perception Network of Autonomous Vehicle | |
| US20230038673A1 (en) | Sequential pedestrian trajectory prediction using step attention for collision avoidance | |
| CN116674593A (en) | Security enhanced planning system with anomaly detection for autonomous vehicles | |
| CN116501820A (en) | Vehicle track prediction method, device, equipment and storage medium | |
| WO2022256760A1 (en) | Method and system for predicting behavior of actors in an environment of an autonomous vehicle | |
| CN115092181A (en) | Vehicle control method and device, storage medium and processor | |
| Zhang et al. | Prediction of Pedestrian Risky Level for Intelligent Vehicles | |
| US11760388B2 (en) | Assessing present intentions of an actor perceived by an autonomous vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |