CN114633743A - Automatic driving vehicle and collision accident detection method and system thereof - Google Patents
Automatic driving vehicle and collision accident detection method and system thereof Download PDFInfo
- Publication number
- CN114633743A CN114633743A CN202011487872.7A CN202011487872A CN114633743A CN 114633743 A CN114633743 A CN 114633743A CN 202011487872 A CN202011487872 A CN 202011487872A CN 114633743 A CN114633743 A CN 114633743A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- acceleration
- deceleration
- value
- longitudinal acceleration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 78
- 230000001133 acceleration Effects 0.000 claims abstract description 281
- 230000004044 response Effects 0.000 claims abstract description 40
- 238000004364 calculation method Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims description 57
- 230000008569 process Effects 0.000 claims description 16
- 230000003068 static effect Effects 0.000 claims description 8
- 230000003111 delayed effect Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 230000000875 corresponding effect Effects 0.000 description 45
- 230000008859 change Effects 0.000 description 12
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000010355 oscillation Effects 0.000 description 3
- 239000000725 suspension Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000005381 potential energy Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Regulating Braking Force (AREA)
Abstract
The invention provides an automatic driving vehicle and a collision accident detection method and system thereof, belonging to the technical field of automatic driving. The collision accident detection method includes: determining the current running state of the vehicle according to the vehicle speed, the accelerator opening and the brake deceleration of the vehicle at the current moment, wherein the running state of the vehicle comprises at least one of an acceleration state, a deceleration state and an emergency brake parking state; calculating to obtain an expected value of the longitudinal acceleration of the vehicle body at the current moment by utilizing a pre-established longitudinal acceleration calculation model of the vehicle body corresponding to the current vehicle running state and data required by the model; and comparing the expected value of the longitudinal acceleration of the vehicle body at the current moment with the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging whether the vehicle has a collision accident or not according to the difference between the expected value and the actual value. The invention considers the response delay of the automatic driving control signal, the calculated expected value of the longitudinal acceleration of the vehicle body is more accurate, and the effective detection of the collision accident of the vehicle in different running states can be realized.
Description
Technical Field
The invention relates to an automatic driving vehicle and a collision accident detection method and system thereof, belonging to the technical field of automatic driving.
Background
With the development of automatic driving technology, the arrangement of a safer on the vehicle is gradually cancelled, and the L5-level unmanned driving is finally realized. Therefore, the vehicle needs to have the capability of autonomously identifying whether a traffic accident occurs, so that the vehicle can be stopped in time when the traffic accident occurs, the loss caused by the accident caused by restarting is avoided, meanwhile, the accident information can be notified to the background to wait for the traffic police to process, and the hit-and-run is avoided.
The main form of a traffic accident is a collision accident, and currently, a contact switch is usually adopted or an Inertial Measurement Unit (IMU) is used to judge the collision accident. For example: the Chinese invention patent application with the application number of CN110696766A uses a clamping plate mechanism to detect collision, when a collision accident occurs, a double-layer clamping plate is pressed to contact and is conducted, but the method can only detect the condition that a collision point is just provided with the clamping plate, and the detection omission easily occurs; the chinese invention patent application No. CN110766982A discloses that a collision accident is determined by using a GPS and a three-axis acceleration sensor, but the method only uses information obtained by the sensor to detect the collision accident, and does not consider road conditions and vehicle running states, and there is a risk of false detection when a vehicle is suddenly braked or stopped or passes through a special road surface (a speed bump, a bumpy road, a pothole, or the like).
Disclosure of Invention
The invention aims to provide an automatic driving vehicle with high collision accident detection accuracy and a collision accident detection method and system thereof.
In order to achieve the above object, the present invention provides a collision accident detecting method of an autonomous vehicle, the method including the steps of:
(1) in the running process of the automatic driving vehicle, acquiring the speed of the vehicle, an automatic driving control signal of the vehicle and an actual value of the longitudinal acceleration of the vehicle body in real time, wherein the automatic driving control signal comprises the opening degree of an accelerator and the deceleration of a brake;
(2) determining the current running state of the vehicle according to the vehicle speed, the accelerator opening and the brake deceleration of the vehicle at the current moment, wherein the running state of the vehicle comprises at least one of an acceleration state, a deceleration state and an emergency brake parking state;
(3) calculating to obtain an expected value of the longitudinal acceleration of the vehicle body at the current moment by using a pre-established longitudinal acceleration calculation model of the vehicle body corresponding to the current vehicle running state and data required by the model; the vehicle body longitudinal acceleration calculation models corresponding to the acceleration state, the deceleration state and the emergency brake parking state are respectively an acceleration model, a deceleration model and an emergency brake parking model, data required by the acceleration model comprise the vehicle speed at the current moment and the accelerator opening at the previous t1 moment, data required by the deceleration model comprise the brake deceleration at the previous t2 moment, and data required by the emergency brake parking model comprise the actual value of the vehicle body longitudinal acceleration when the acceleration starts to rebound; wherein t1 is the acceleration response delay of the vehicle, and t2 is the deceleration response delay of the vehicle;
(4) and comparing the expected value of the longitudinal acceleration of the vehicle body at the current moment with the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging whether the vehicle has a collision accident or not according to the difference between the expected value and the actual value.
The present invention also provides a collision accident detecting system of an autonomous vehicle, the system including:
the vehicle control unit is used for acquiring the vehicle speed in real time;
the intelligent controller is used for acquiring an automatic driving control signal of the vehicle in real time, wherein the automatic driving control signal comprises an accelerator opening degree and a braking deceleration;
the acceleration sensor is used for acquiring an actual value of the longitudinal acceleration of the vehicle body in real time;
and the collision accident detection module is used for receiving data of the vehicle controller, the intelligent controller and the acceleration sensor and realizing the collision accident detection method of the automatic driving vehicle.
The present invention also provides an autonomous vehicle comprising a vehicle body and a collision accident detection system, the collision accident detection system comprising:
the vehicle control unit is used for acquiring the vehicle speed in real time;
the intelligent controller is used for acquiring an automatic driving control signal of the vehicle in real time, wherein the automatic driving control signal comprises an accelerator opening degree and a braking deceleration;
the acceleration sensor is used for acquiring an actual value of the longitudinal acceleration of the vehicle body in real time;
and the collision accident detection module is used for receiving data of the vehicle control unit, the intelligent controller and the acceleration sensor and realizing the collision accident detection method of the automatic driving vehicle.
The invention has the beneficial effects that: according to the invention, a corresponding vehicle body longitudinal acceleration calculation model is established for each running state of the vehicle, so that the effective detection of collision accidents of the vehicle in different running states can be realized, and false detection can not be brought; when the expected value of the longitudinal acceleration of the vehicle body is calculated, the response delay of the automatic driving control signal is fully considered, and the time alignment of the automatic driving control signal and the longitudinal acceleration signal of the vehicle body is realized, so that the calculation result of the expected value of the longitudinal acceleration of the vehicle body is more accurate, and the accuracy of the detection of the collision accident is further ensured; in conclusion, when the collision accident detection is carried out, the running state of the vehicle and the response delay of the automatic driving control signal are fully considered, and the collision accident detection accuracy is high.
Further, in the above-mentioned autonomous vehicle and the collision accident detecting method and system thereof, the acceleration model is: ay _ except ═ k1 a (t-t1) + k 2V + b 1; the deceleration model is as follows: ay _ extt ═ k3 × B (t-t2) + B2; the emergency braking parking model is as follows:
in the formula, Ay _ extt is an expected value of the longitudinal acceleration of the vehicle body, A (t-t1) is the accelerator opening degree at the time of t-t1, V is the vehicle speed at the time of t, k1, k2 and B1 are fitting parameters in an acceleration state, B (t-t2) is the braking deceleration at the time of t-t2, k3 and B2 are fitting parameters in a deceleration state, A0Is the actual value of the longitudinal acceleration of the body at which the acceleration begins to rebound, a0Is the acceleration value when the acceleration begins to rebound in the typical acceleration rebound model, and a (t) is the value in the typical acceleration rebound model at the time tAn acceleration value.
Further, in the above autonomous vehicle and the collision accident detecting method and system thereof, the running state of the vehicle further includes a stationary state, and the current running state of the vehicle is determined by: if the vehicle speed and the brake deceleration at the current moment meet V < k4 & ltB + B, the current running state of the vehicle is an emergency brake parking state; if the current vehicle is not in the emergency brake parking state and the vehicle speed is 0, the running state of the current vehicle is in a static state; if the current vehicle is not in an emergency braking parking state and the vehicle speed is not 0, the current running state of the vehicle is a deceleration state when the braking deceleration is less than 0, and the current running state of the vehicle is an acceleration state when the accelerator opening is greater than 0; in the formula, V is a vehicle speed at time t, B is an accelerator opening at time t, and k4 and B are fitting parameters.
Further, in the above-described autonomous vehicle and collision accident detection method and system thereof, an acceleration response delay time of the vehicle is based on [0, T [ ]]Calculating vehicle acceleration data of a time period, wherein the vehicle acceleration data comprise the accelerator opening and the longitudinal acceleration of the vehicle body when the accelerator opening is larger than 0, and the acceleration response of the vehicle is delayed to enable the vehicle to be in a delayed mode
The value of Δ t at which the value of (d) is maximum; the deceleration response delay of the vehicle is based on [0, T]Calculating vehicle deceleration data of a time period, wherein the vehicle deceleration data is the braking deceleration when the braking deceleration is less than 0 and the longitudinal acceleration of the vehicle body, and the deceleration response of the vehicle is delayed to ensure that
The value of Δ t at which the value of (d) is maximum; where a (t) is an accelerator opening degree at time t, b (t) is a brake deceleration at time t, and Ay (t + Δ t) is a vehicle body longitudinal acceleration at time t + Δ t.
Further, in the above automatic driving vehicle and the method and system for detecting a collision accident thereof, the process of determining whether a collision accident occurs to the vehicle is as follows: calculating the difference value between the expected value and the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging that the vehicle has a collision accident when the difference value exceeds a collision threshold value; or respectively obtaining difference values of the expected value of the longitudinal acceleration of the vehicle body at the current moment and actual values of the longitudinal acceleration of the vehicle body in a set time period before and after the current moment, taking the difference value with the smallest absolute value as the difference value of the expected value and the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging that the vehicle has a collision accident when the difference value exceeds a collision threshold value; or respectively calculating difference values of the expected value of the longitudinal acceleration of the vehicle body at the current moment and actual values of the longitudinal acceleration of the vehicle body in a set time period before and after the current moment, respectively comparing each calculated difference value with a collision threshold value, and judging that the vehicle has a collision accident when N continuous difference values exceed the collision threshold value, wherein N is more than or equal to 2.
The beneficial effects of doing so are: 3 methods for judging whether a collision accident occurs are provided, and one of the methods can be selected in practical application, wherein the method for directly comparing the difference value between the expected value and the actual value of the longitudinal acceleration of the vehicle body at the current moment with the collision threshold value is simplest and most rapid; the method for comparing the difference value with the minimum absolute value with the collision threshold value can solve the detection error caused by incomplete alignment of the expected value and the actual value of the longitudinal acceleration of the vehicle body on a time axis because the response delay of the automatic driving control signal is slightly changed or the calculation of the rebound point of the acceleration is not accurate during emergency stop, thereby improving the detection precision of the collision accident; when the N continuous difference values exceed the collision threshold value, the vehicle is judged to have a collision accident, the detection error caused by inaccuracy of the actual value of the longitudinal acceleration of the vehicle body due to signal noise of the acceleration sensor can be solved, and the detection precision of the collision accident is improved.
Further, in the above automatic driving vehicle and the method and system for detecting a collision accident thereof, the collision threshold is determined according to an initial threshold and a threshold coefficient corresponding to a current position of the vehicle, the threshold coefficient corresponding to the current position of the vehicle is determined according to a current operating state of the vehicle and a road condition of the current position of the vehicle, the road condition includes a normal road surface and a special road surface, and the special road surface includes a speed bump, a bumpy road surface and a pothole road surface; the threshold coefficient at the normal road surface position is 1, and the threshold coefficient at the special road surface position is greater than 1.
The beneficial effects of doing so are: considering that the longitudinal acceleration of the vehicle body also has unexpected changes when the vehicle passes through a deceleration strip or a bumpy road surface or a hollow road surface or other special road surfaces in the normal running process (no collision occurs), and the degree of the unexpected changes of the longitudinal acceleration of the vehicle body when the vehicle passes through the same special road surface in different running states is different, the unexpected changes are easily detected by mistake as a collision accident, in order to avoid the false detection when the vehicle passes through the special road surfaces, the collision threshold value is associated with the running state of the vehicle and the road condition of the current position of the vehicle, and the collision threshold value at the position of the special road surface is compensated by using the threshold coefficient, so that the false detection rate when the vehicle passes through the special road surface can be effectively reduced, and the accuracy of the detection of the vehicle collision accident is ensured.
Further, in the above method and system for detecting a collision accident of an autonomous vehicle, the threshold coefficient at the position of the special road surface is calibrated by a test, and the calibration process is as follows: the method comprises the steps of measuring actual values of longitudinal acceleration of a vehicle body when the vehicle passes through the special road surface position in different running states aiming at each special road surface position, calculating expected values of the longitudinal acceleration of the vehicle body when the vehicle passes through the special road surface position in different running states respectively based on collected real vehicle data when the vehicle passes through the special road surface position in different running states and a vehicle speed longitudinal acceleration calculation model corresponding to the corresponding running state, calculating difference values of the expected values and the actual values of the longitudinal acceleration of the vehicle body corresponding to the special road surface position in each running state respectively, and taking the ratio of the difference values and an initial threshold value in each running state as a threshold coefficient of the special road surface position in the corresponding running state.
The beneficial effects of doing so are: considering that the unexpected change degree of the longitudinal acceleration of the vehicle body is different when the vehicle passes through the same special road surface in different running states, the threshold coefficient at each special road surface position is calibrated for multiple times in different running states of the vehicle, so that the threshold coefficients at multiple different vehicle running states corresponding to each special road surface position are obtained, and the obtained threshold coefficients in multiple different vehicle running states are used for compensating the collision threshold at the special road surface position, so that the false detection rate of the vehicle passing through the special road surface in different running states can be effectively reduced, and the accuracy of vehicle collision accident detection is ensured.
Further, in the above-mentioned automatically driven vehicle and the method and system for detecting a collision accident thereof, the method for calculating the collision threshold corresponding to the current position of the vehicle is as follows: and T is k T0, wherein T is a collision threshold corresponding to the current position of the vehicle, k is a threshold coefficient corresponding to the current position of the vehicle, k is more than or equal to 1, and T0 is an initial threshold.
Drawings
FIG. 1 is a schematic illustration of a crash event detection system in a vehicle embodiment of the present invention;
FIG. 2 is a schematic view of the vehicle IMU mounting position and acceleration and angular velocity in a vehicle embodiment of the present invention;
FIG. 3 is a flow chart of a collision accident detection method in a vehicle embodiment of the present invention;
FIG. 4 is a schematic illustration of vehicle acceleration response delay and deceleration response delay in a vehicle embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating the acceleration rebound phenomenon during emergency braking of the vehicle according to the embodiment of the present invention;
FIG. 6 is a schematic vehicle speed diagram illustrating acceleration rebound under different braking deceleration conditions in an embodiment of the vehicle of the present invention;
FIG. 7 is a schematic illustration of an exemplary acceleration rebound model in a vehicle embodiment of the present invention;
FIG. 8 is a schematic diagram of signal characteristics at the time of normal running in the embodiment of the vehicle of the invention;
fig. 9 is a schematic diagram of the signal characteristics at the time of a collision accident in the vehicle embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments.
The embodiment of the vehicle is as follows:
the autonomous vehicle of the embodiment includes a vehicle body and a collision accident detection system, as shown in fig. 1, the collision accident detection system includes: the vehicle-mounted collision accident detection system comprises a vehicle control unit, an intelligent controller, an acceleration sensor (such as a three-axis acceleration sensor or a two-axis acceleration sensor), a high-precision map module and a collision accident detection module, wherein the collision accident detection module comprises a vehicle body longitudinal acceleration calculation module, a collision accident logic judgment module and a collision accident judgment result output module.
The vehicle speed control system comprises a vehicle control unit, an intelligent controller, an acceleration sensor, a high-precision map module and a high-precision map module, wherein the vehicle control unit is used for acquiring the vehicle speed of a vehicle in real time, the intelligent controller is used for acquiring automatic driving control signals (including accelerator opening and braking deceleration) of the vehicle in real time, the acceleration sensor is used for acquiring the actual value of the longitudinal acceleration of the vehicle body in real time, the high-precision map module stores a high-precision map which is acquired in advance, special roads (such as speed reducing belts, bumpy roads, hollow roads and the like) are marked in the high-precision map, threshold coefficients corresponding to the corresponding special roads are marked at the positions of each special road in the high-precision map, and the high-precision map module is used for providing the threshold coefficients corresponding to the current position of the vehicle; the collision accident detection module is used for receiving the vehicle speed, the automatic driving control signal of the vehicle, the actual value of the longitudinal acceleration of the vehicle body and the threshold coefficient corresponding to the current position of the vehicle, and is used for realizing the collision accident detection method shown in fig. 3. Specifically, the vehicle body longitudinal acceleration calculation module is used for determining the current vehicle running state according to the vehicle speed, the accelerator opening and the brake deceleration of the vehicle at the current moment, and calculating to obtain the expected value of the vehicle body longitudinal acceleration at the current moment by using a vehicle body longitudinal acceleration calculation model corresponding to the current vehicle running state which is established in advance and data required by the model; the collision accident logic judgment module is used for determining a collision threshold corresponding to the current position of the vehicle according to the initial threshold and a threshold coefficient corresponding to the current position of the vehicle, comparing an expected value of the longitudinal acceleration of the vehicle body at the current moment with an actual value of the longitudinal acceleration of the vehicle body at the current moment by combining the collision threshold corresponding to the current position of the vehicle, and judging whether the vehicle has a collision accident or not according to the difference between the two values; and the collision accident judgment result output module is used for outputting the detection result of the vehicle collision accident.
In this embodiment, a three-axis acceleration sensor IMU is selected as the acceleration sensor, and as shown in fig. 2, the IMU is mounted on the top of the vehicle and can provide acceleration and angular velocity in three directions of the vehicle, where Ay is a longitudinal acceleration of the vehicle body, Ω y is a longitudinal angular velocity of the vehicle body, Ax is a lateral acceleration of the vehicle body, Ω x is a lateral angular velocity of the vehicle body, Az is a vertical acceleration of the vehicle body, and Ω z is a vertical angular velocity of the vehicle body.
The collision accident detection method of the embodiment is a multi-source information fusion collision accident detection method based on vehicle acceleration sensor information, vehicle running state, automatic driving control signals of a vehicle and high-precision map information, and the specific implementation process of the method is shown in fig. 3:
the vehicle body longitudinal acceleration calculation models corresponding to each vehicle running state are different, and the vehicle body longitudinal acceleration calculation models corresponding to the acceleration state, the deceleration state, the emergency braking parking state and the static state are respectively an acceleration model, a deceleration model, an emergency braking parking model and a static model. Each model is described in detail below:
the acceleration model is: ay _ except ═ k1 a (t-t1) + k 2V + b1, wherein a (t-t1) is an accelerator opening at the time of t-t1, t1 is an acceleration response delay of the vehicle, V is a vehicle speed at the time of t, and k1, k2 and b1 are fitting parameters in an acceleration state; the data required by the acceleration model can be seen as the vehicle speed at the current moment and the accelerator opening at the previous t1 moment;
the deceleration model is as follows: ay _ except ═ k3 × B (t-t2) + B2, wherein B (t-t2) is the braking deceleration at time t-t2, t2 is the deceleration response delay of the vehicle, and k3 and B2 are fitting parameters in the deceleration state; it can be seen that the data required for the deceleration model is the brake deceleration at time t 2;
the emergency braking parking model is as follows:
in the formula, A0Is the actual value of the longitudinal acceleration of the body at which the acceleration begins to rebound, a0The acceleration value of the acceleration rebound starting in the typical acceleration rebound model, and a (t) is the acceleration value in the typical acceleration rebound model at the time t; the data required by the emergency braking parking model are the actual value of the longitudinal acceleration of the vehicle body when the acceleration starts rebounding, the acceleration value when the acceleration starts rebounding in the typical acceleration rebounding model and the acceleration value in the typical acceleration rebounding model at the current moment;
the static model is: ay _ expt is 0.
The building process of the vehicle body longitudinal acceleration calculation model corresponding to each vehicle running state is as follows:
1) calculating response time delay (including acceleration response time delay and deceleration response time delay) of the vehicle;
since there is a certain time delay (this time is called response delay) from the time when the automatic driving control signal of the vehicle (i.e. the accelerator opening degree control signal and the brake deceleration control signal) is sent to the time when the vehicle responds to the acceleration and deceleration actions to the time when the acceleration sensor detects the change in the state of the vehicle, the response delay of the vehicle needs to be calculated first in order to establish a mathematical relationship model (i.e. a vehicle body longitudinal acceleration calculation model) between the acceleration of the vehicle and the state of the vehicle and the automatic driving control signal of the vehicle.
As shown in FIG. 4, in the figure, the horizontal axis represents time (unit: second), the vertical axis represents the vehicle body longitudinal acceleration Ay (unit: m/s2), the accelerator opening A (unit: degree, the scale of which is reduced by 40 times for convenient display), the brake deceleration B (unit: m/s2), the vehicle speed V (unit: km/h, the scale of which is reduced by 10 times for convenient display), t1 is the time interval from the transmission of the accelerator opening control signal to the vehicle in response to acceleration, and t2 is the time interval from the transmission of the brake deceleration control signal to the vehicle in response to deceleration.
Because the response delay during acceleration and the response delay during deceleration are different, in order to calculate the acceleration response delay and the deceleration response delay, the data during acceleration and the data during deceleration need to be separated and then calculated respectively, and the calculation methods are respectively as follows:
and (3) taking vehicle acceleration data of [0, T ] time period, wherein the vehicle acceleration data are the accelerator opening and the longitudinal acceleration of the vehicle body when the accelerator opening is greater than 0, and calculating according to a formula (1), and the acceleration response delay is a delta T value when the value of the formula (1) is maximum.
And (3) taking vehicle deceleration data of a [0, T ] time period, wherein the vehicle deceleration data are the brake deceleration and the longitudinal acceleration of the vehicle body when the brake deceleration is less than 0, and calculating according to the formula (2), and the deceleration response delay time is the delta T value when the value of the formula (2) is maximum.
Where a (t) is an accelerator opening degree at time t, b (t) is a brake deceleration at time t, and Ay (t + Δ t) is a vehicle body longitudinal acceleration at time t + Δ t.
2) Fitting to obtain a vehicle body longitudinal acceleration calculation model of each running state of the vehicle based on the response delay of the vehicle and the collected real vehicle data of a large number of vehicles in normal running; wherein, through data analysis, divide into the vehicle running state: the vehicle body longitudinal acceleration calculation model is different when the vehicle is in different running states.
The vehicle body longitudinal acceleration calculation models of the vehicle running states are respectively as follows:
(1) acceleration model
When the vehicle is normally accelerated, the acceleration is a positive value, and the magnitude thereof increases as the accelerator opening increases, but the acceleration value tends to be gentle as the vehicle speed increases. Therefore, when the vehicle is accelerated, the magnitude of the acceleration is related to the accelerator opening and the vehicle speed, and through data analysis, the acceleration calculation model when the vehicle is in an accelerated state is as follows:
Ay_expt＝k1*A(t-t1)+k2*V+b1 (3)
in the formula, a is the accelerator opening, t1 is the acceleration response delay, and k1, k2, and b1 are fitting parameters for acceleration.
In order to obtain the fitting parameters during acceleration, automatic driving data of a period of time need to be collected in advance, data only including an acceleration process are extracted, the relation between the vehicle acceleration and the vehicle speed and the accelerator opening is established by using a formula (3), and the fitting parameters are obtained by using a least square fitting method.
(2) Deceleration model
When the vehicle decelerates normally, the acceleration is negative, the control signal directly sends down the braking deceleration value to the braking component, but the vehicle body response and the control sending down are not completely consistent. Through data analysis, the actual acceleration of the vehicle body is in positive correlation with the braking deceleration sent by the control signal, and the acceleration calculation model when the vehicle is in a deceleration state is as follows:
Ay_expt＝k3*B(t-t2)+b2 (4)
where B is the braking deceleration, t2 is the deceleration response delay, and k3 and B2 are the fitting parameters during deceleration, and the calculation method thereof is the same as that of the fitting parameters during acceleration.
(3) Emergency braking parking model
When the vehicle is braked suddenly and stopped, the vehicle body swings back and forth, and the difference between the acceleration value and the change rule of the acceleration value in the normal braking state is large, so that the calculation cannot be carried out according to the formula (4). The vehicle body and the chassis are connected through the suspension, the suspension is equivalent to a spring structure, when the vehicle is braked suddenly, kinetic energy of the vehicle body is converted into elastic potential energy, and when the vehicle stops or is close to stop, the elastic potential energy is released and converted into the kinetic energy of the vehicle body, so that the vehicle body swings back and forth. The change law of the acceleration of the vehicle body at this time can be observed by the change of the data measured by the acceleration sensor, as shown in fig. 5.
As can be seen in FIG. 5, when the vehicle starts to brake (3 s-4 s), the acceleration and the deceleration of the vehicle are positively correlated and gradually reach about-3 m/s2, and the vehicle speed is gradually reduced; then the acceleration of the vehicle is kept to be about-3 m/s2, and the vehicle is still in a deceleration state (4 s-6 s); when the vehicle speed approaches to 0, the acceleration curve starts to rise and then generates periodic oscillation, the amplitude is gradually reduced, and finally the acceleration curve approaches to 0(6 s-8 s); the position at which the acceleration starts to rise is called the acceleration rebound point.
Through data analysis, the vehicle speed when the acceleration rebound and the brake deceleration have a certain relation, the vehicle speed when the acceleration rebound occurs under different brake decelerations is counted, the result is shown as a blue dispersion point in fig. 6, the dispersion point is fitted, and the relation between the vehicle speed when the acceleration rebound occurs and the brake deceleration can be obtained, as shown as a red straight line in the figure. Therefore, when the vehicle speed satisfies the formula (5), the acceleration starts rebounding:
V<k4*B+b (5)
meanwhile, through data analysis, the frequency of acceleration oscillation is fixed (related to the natural frequency of a vehicle suspension), and the amplitude is only related to the magnitude of the acceleration when the acceleration starts rebounding. Therefore, a typical acceleration rebound model (as shown in fig. 7) is formed by collecting a section of acceleration oscillation signal in advance, and in the actual sudden braking process, the expected acceleration value Ay _ extt at the corresponding moment can be obtained only by scaling the typical acceleration rebound model according to the proportion.
If the acceleration value at the time of actually starting rebound is A0The acceleration of the rebound process, Ay _ expt, can then be expressed as:
in the formula, a0Represents the acceleration at which rebound begins in a typical acceleration rebound model,
for scaling, a (t) is the acceleration at time t in a typical acceleration rebound model.
(4) Static model
When the vehicle is stationary, the vehicle acceleration value is 0, i.e.:
Ay_expt＝0 (7)
because the performance of each automatic driving vehicle is not completely consistent, the response delay time of each vehicle and the parameters in the vehicle body acceleration calculation model corresponding to each running state need to be calibrated, the accuracy of the calculation of the expected result is ensured, and the risk of false detection is reduced.
And 4, comparing the expected value of the longitudinal acceleration of the vehicle body at the current moment with the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging whether the vehicle has a collision accident or not according to the difference between the expected value and the actual value.
The following 3 methods for determining whether a vehicle has a collision accident are provided, and in practical applications, one of the methods may be selected:
method (1): calculating a difference value between an expected value and an actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging that the vehicle has a collision accident when the difference value exceeds a collision threshold value corresponding to the current position of the vehicle; this method is the simplest and the fastest.
Method (2): respectively obtaining difference values of the expected longitudinal acceleration value of the vehicle body at the current moment and actual longitudinal acceleration values of the vehicle body in a set time period before and after the current moment, taking the difference value with the minimum absolute value as the difference value of the expected longitudinal acceleration value and the actual longitudinal acceleration value of the vehicle body at the current moment, and judging that the vehicle has a collision accident when the difference value exceeds a collision threshold value corresponding to the current position of the vehicle; the length of the set time period before and after the current time can be determined according to actual needs, for example, an actual value of the longitudinal acceleration of the vehicle body between 20ms before the current time and 20ms after the current time (if the current time is the time t, the actual value of the longitudinal acceleration of the vehicle body between t-20ms and t +20 ms) is taken, or an actual value of the longitudinal acceleration of the vehicle body between a frame before the current time and a frame after the current time (i.e., the actual values of the longitudinal acceleration of the vehicle body between 1 frame before the current time, the current frame and the frame after the current time) is taken; the method can solve the detection error caused by that the expected value and the actual value of the longitudinal acceleration of the vehicle body are not completely aligned on the time axis because the response delay of the automatic driving control signal is slightly changed or the calculation of the acceleration rebound point is not accurate when the vehicle is stopped at an emergency, thereby improving the detection precision of the collision accident;
method (3): respectively calculating the difference between the expected value of the longitudinal acceleration of the vehicle body at the current moment and the actual value of the longitudinal acceleration of the vehicle body in a set time period (the same as that in the method (2)) before and after the current moment, respectively comparing each calculated difference with a collision threshold, and when N continuous differences exceed the collision threshold corresponding to the current position of the vehicle, judging that the vehicle has a collision accident, wherein N is more than or equal to 2; the method can solve the detection error caused by inaccurate actual longitudinal acceleration value of the vehicle body due to signal noise of the acceleration sensor, and improve the detection precision of the collision accident.
As shown in fig. 3, in the embodiment, the method (3) is selected to perform collision accident detection, and when 2 consecutive difference values all exceed the collision threshold corresponding to the current position of the vehicle, it is determined that the vehicle has a collision accident.
The method for calculating the collision threshold T corresponding to the current position of the vehicle comprises the following steps: t ═ k × T0, where k is a threshold coefficient corresponding to the current position of the vehicle, and T0 is an initial threshold; the threshold coefficient k and the initial threshold value T0 corresponding to the current position of the vehicle are obtained through experimental calibration.
The threshold coefficient k corresponding to the current position of the vehicle is determined according to the running state of the vehicle and the road condition of the current position of the vehicle, wherein the road condition comprises a normal road surface and a special road surface (including a speed bump, a bumpy road surface and a hollow road surface), the threshold coefficient at the position of the normal road surface is 1, the threshold coefficient at the position of the special road surface is greater than 1, namely when the current position of the vehicle is the normal road surface, k is 1, and when the current position of the vehicle is the special road surface, k is greater than 1.
The benefits of this are: considering that the longitudinal acceleration of the vehicle body also has unexpected changes when the vehicle passes through a deceleration strip or a bumpy road surface or a hollow road surface or other special road surfaces in the normal running process (no collision occurs), and the degree of the unexpected changes of the longitudinal acceleration of the vehicle body when the vehicle passes through the same special road surface in different running states is different, the unexpected changes are easily detected by mistake as a collision accident, in order to avoid the false detection when the vehicle passes through the special road surfaces, the collision threshold value is associated with the running state of the vehicle and the road condition of the current position of the vehicle, and the collision threshold value at the position of the special road surface is compensated by using the threshold coefficient, so that the false detection rate when the vehicle passes through the special road surface can be effectively reduced, and the accuracy of the detection of the vehicle collision accident is ensured.
The threshold coefficient of the special road surface position is calibrated through tests, and the calibration process is as follows: respectively measuring actual values of longitudinal acceleration of the vehicle body when the vehicle passes through the special road surface position in different running states aiming at each special road surface position, respectively calculating expected values of the longitudinal acceleration of the vehicle body when the vehicle passes through the special road surface position in different running states based on the acquired real vehicle data when the vehicle passes through the special road surface position in different running states and a vehicle speed longitudinal acceleration calculation model corresponding to the corresponding running state, then respectively calculating difference values of the expected value and the actual value of the longitudinal acceleration of the vehicle body corresponding to the special road surface position in each running state, and taking the ratio of the difference value and the initial threshold value in each running state as a threshold coefficient of the special road surface position in the corresponding running state; that is, for the same special road surface position, the threshold coefficient at the special road surface position needs to be calibrated for multiple times under different running states of the vehicle, so that the same special road surface position corresponds to multiple threshold coefficients, and each threshold coefficient corresponds to one vehicle running state. For example: the threshold coefficient at a specific road position is calibrated when the vehicle is in an acceleration state, and the obtained threshold coefficient is the threshold coefficient at the specific road position when the vehicle is in the acceleration state, in this embodiment, 4 vehicle running states correspond to the vehicle running states, and the specific road position corresponds to the 4 threshold coefficients.
When collision accident detection is carried out, when a vehicle passes through a normal road surface, a collision threshold corresponding to the current position of the vehicle is an initial threshold; when the vehicle passes through a special road surface in an acceleration state, the collision threshold corresponding to the current position of the vehicle is the threshold coefficient at the position of the special road surface multiplied by the initial threshold when the vehicle is in the acceleration state, and similarly, when the vehicle passes through a special road surface in other running states, the collision threshold corresponding to the current position of the vehicle is the threshold coefficient at the position of the special road surface multiplied by the initial threshold when the vehicle is in the corresponding state.
The benefits of this are: considering that the unexpected change degrees of the longitudinal acceleration of the vehicle body are different when the vehicle passes through the same special road surface in different running states, the threshold coefficient at each special road surface position is calibrated for multiple times in different running states of the vehicle, so that the threshold coefficients at a plurality of different vehicle running states corresponding to each special road surface position are obtained, and the obtained threshold coefficients at the different vehicle running states are used for compensating the collision threshold at the special road surface position, so that the false detection rate of the vehicle passing through the special road surface in different running states can be effectively reduced, and the accuracy of vehicle collision accident detection is ensured.
In the embodiment, a specific mode of determining the threshold coefficient in the form of the ratio of the difference value between the expected value and the actual value of the longitudinal acceleration of the vehicle body to the initial threshold is provided, and as other embodiments, the threshold coefficient can be determined in other modes except the ratio; in this embodiment, considering that there is a special road surface in the operation scene of the autonomous vehicle, a threshold coefficient is set to compensate for the influence of the special road surface on the detection result of the collision accident.
The running state of the vehicle in this embodiment includes an acceleration state, a deceleration state, an emergency stop state, and a stationary state, and as another embodiment, the running state of the vehicle may include at least one of the acceleration state, the deceleration state, and the emergency stop state.
In the present embodiment, the vehicle body longitudinal acceleration calculation model takes the automated driving control signals (the accelerator opening and the brake deceleration) as inputs, that is, the vehicle acceleration change caused by the automated driving control signals is taken as a normal change, and the vehicle acceleration change caused by the non-automated driving control signals is taken as a collision accident. In order to verify the effectiveness of the collision accident detection method of the embodiment, manual intervention can be performed by manually pressing a brake pedal during debugging, and unexpected deceleration of the vehicle caused by collision can be simulated. The method has the advantages that the collision simulation signals can be collected without collision experiments, and meanwhile, the verification of the collision accident detection method can be carried out in a collision simulation mode.
As shown in fig. 8, fig. 8 is a signal change characteristic when the vehicle is normally running, and includes an actual acceleration curve, an expected acceleration curve, and a difference S between the calculated expected value and the actual value. As can be seen, the difference S in the whole process is within 1m/S2, so that no collision accident can be judged; as shown in fig. 9, fig. 9 is a signal change characteristic at the time of a collision accident, and if the expected acceleration of the vehicle becomes 0 and the actual acceleration suddenly decreases within 3S to 4S, it is considered that the vehicle decelerates due to the collision, the difference S between the expected acceleration value and the actual acceleration value suddenly increases, and exceeds the initial threshold T0 to 1m/S2, it is determined that the collision accident has occurred. Here, since fig. 8 and 9 illustrate the detection of a collision accident on a non-specific road surface, the initial threshold value T0 is 1m/s 2.
The initial threshold T0 is 1m/s2, which is the result of a large number of data tests, taking into account the measurement error of the acceleration sensor and the fitting calculation error. The significance is as follows: based on the accuracy and algorithm of the current acceleration sensor, a crash accident that causes the acceleration of the own vehicle to change by more than 1m/s2 can be detected. As another embodiment, a high-precision acceleration sensor may be used to reduce the measurement error of the acceleration, optimize the fitting and processing algorithm of the acceleration signal, and reduce the interference caused by the signal noise, thereby improving the accuracy of the detection of the collision accident and being able to detect a more slight collision accident.
The collision accident detection method of the embodiment has the beneficial effects that:
(1) calculating the response delay of the automatic driving control signal, realizing the time alignment of the automatic driving control signal and the vehicle body longitudinal acceleration signal, and ensuring that the calculated vehicle body longitudinal acceleration expected value is more accurate;
(2) a corresponding vehicle body longitudinal acceleration calculation model is established for each running state of the vehicle, so that the effective detection of collision accidents of the vehicle in different running states can be realized, and false detection can not be brought;
(3) by marking the threshold coefficient at the position of the special road surface and compensating the collision threshold at the position of the special road surface by using the threshold coefficient, the collision accident can be realized on the special road surface without false detection and missing detection;
(4) the signal acquisition of the collision accident and the test verification of the collision accident detection method can be completed under the condition that real collision does not occur.
The collision accident detection method of the embodiment can detect the collision of the own vehicle or the rear-end collision of other vehicles and cause the collision accident that the acceleration of the own vehicle changes to a certain extent. The method is not limited to a single vehicle type, and all vehicles capable of acquiring vehicle control signals, vehicle body state signals and acceleration signals can be applied.
The embodiment of the system is as follows:
the collision accident detecting system of the present embodiment is the same as the collision accident detecting system of the vehicle embodiment, and the details thereof are not repeated herein.
The method comprises the following steps:
the collision accident detection method of the present embodiment is the same as the collision accident detection method in the vehicle embodiment, and is not described herein again.
Claims (10)
1. A method of crash accident detection for an autonomous vehicle, the method comprising the steps of:
(1) in the running process of the automatic driving vehicle, acquiring the speed of the vehicle, an automatic driving control signal of the vehicle and an actual value of the longitudinal acceleration of the vehicle body in real time, wherein the automatic driving control signal comprises the opening degree of an accelerator and the deceleration of a brake;
(2) determining the current running state of the vehicle according to the vehicle speed, the accelerator opening and the brake deceleration of the vehicle at the current moment, wherein the running state of the vehicle comprises at least one of an acceleration state, a deceleration state and an emergency brake parking state;
(3) calculating to obtain an expected value of the longitudinal acceleration of the vehicle body at the current moment by using a pre-established longitudinal acceleration calculation model of the vehicle body corresponding to the current vehicle running state and data required by the model; the vehicle body longitudinal acceleration calculation models corresponding to the acceleration state, the deceleration state and the emergency brake parking state are respectively an acceleration model, a deceleration model and an emergency brake parking model, data required by the acceleration model comprise the vehicle speed at the current moment and the accelerator opening degree at the previous t1 moment, data required by the deceleration model comprise the brake deceleration at the previous t2 moment, and data required by the emergency brake parking model comprise the actual value of the vehicle body longitudinal acceleration when the acceleration starts to rebound; wherein t1 is the acceleration response delay of the vehicle, and t2 is the deceleration response delay of the vehicle;
(4) and comparing the expected value of the longitudinal acceleration of the vehicle body at the current moment with the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging whether the vehicle has a collision accident or not according to the difference between the expected value and the actual value.
2. The collision accident detection method of an autonomous vehicle according to claim 1, characterized in that the acceleration model is: ay _ extt ═ k1 a (t-t1) + k 2V + b 1; the deceleration model is as follows: ay _ except — k 3B (t-t2) + B2; the emergency braking parking model is as follows:
in the formula, Ay _ extt is an expected value of the longitudinal acceleration of the vehicle body, A (t-t1) is an accelerator opening degree at the time of t-t1, V is the vehicle speed at the time of t, k1, k2 and B1 are fitting parameters in an acceleration state, B (t-t2) is braking deceleration at the time of t-t2, k3 and B2 are fitting parameters in a deceleration state, A is0Is the actual value of the longitudinal acceleration of the body at which the acceleration begins to rebound, a0The acceleration value of the acceleration rebound starting in the typical acceleration rebound model, and a (t) is the acceleration value in the typical acceleration rebound model at the time t.
3. The method of detecting a collision accident of an autonomous vehicle according to claim 2, characterized in that the running state of the vehicle further includes a stationary state, and the current running state of the vehicle is determined by: if the vehicle speed and the brake deceleration at the current moment meet V < k4 × B + B, the current running state of the vehicle is an emergency brake parking state; if the current vehicle is not in the emergency brake parking state and the vehicle speed is 0, the running state of the current vehicle is in a static state; if the current vehicle is not in an emergency braking parking state and the vehicle speed is not 0, the current running state of the vehicle is a deceleration state when the braking deceleration is less than 0, and the current running state of the vehicle is an acceleration state when the accelerator opening is greater than 0; in the formula, V is a vehicle speed at time t, B is an accelerator opening at time t, and k4 and B are fitting parameters.
4. According to claim 3The method for detecting a collision accident of an autonomous vehicle, characterized in that the acceleration response delay of the vehicle is based on [0, T]Calculating vehicle acceleration data of a time period, wherein the vehicle acceleration data comprise the accelerator opening and the longitudinal acceleration of the vehicle body when the accelerator opening is larger than 0, and the acceleration response of the vehicle is delayed to enable the vehicle to be in a delayed mode
The value of Δ t at which the value of (d) is maximum; the deceleration response delay of the vehicle is based on [0, T]Calculating vehicle deceleration data of a time period, wherein the vehicle deceleration data is the braking deceleration when the braking deceleration is less than 0 and the longitudinal acceleration of the vehicle body, and the deceleration response of the vehicle is delayed to ensure that
The value of Δ t at which the value of (d) is maximum; where a (t) is an accelerator opening degree at time t, b (t) is a brake deceleration at time t, and Ay (t + Δ t) is a vehicle body longitudinal acceleration at time t + Δ t.
5. The method for detecting a collision accident of an autonomous vehicle according to any of claims 1 to 4, characterized in that the process of determining whether a collision accident occurs to the vehicle is: calculating the difference value between the expected value and the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging that the vehicle has a collision accident when the difference value exceeds a collision threshold value; or respectively obtaining difference values of the expected value of the longitudinal acceleration of the vehicle body at the current moment and actual values of the longitudinal acceleration of the vehicle body in a set time period before and after the current moment, taking the difference value with the smallest absolute value as the difference value of the expected value and the actual value of the longitudinal acceleration of the vehicle body at the current moment, and judging that the vehicle has a collision accident when the difference value exceeds a collision threshold value; or respectively calculating difference values of the expected value of the longitudinal acceleration of the vehicle body at the current moment and actual values of the longitudinal acceleration of the vehicle body in a set time period before and after the current moment, respectively comparing each calculated difference value with a collision threshold value, and judging that the vehicle has a collision accident when N continuous difference values exceed the collision threshold value, wherein N is more than or equal to 2.
6. The method of detecting a collision accident with an autonomous vehicle according to claim 5, characterized in that the collision threshold is determined according to an initial threshold and a threshold coefficient corresponding to the current position of the vehicle, the threshold coefficient corresponding to the current position of the vehicle is determined according to the current operating state of the vehicle and the road conditions of the current position of the vehicle, the road conditions include a normal road surface and a special road surface, and the special road surface includes a deceleration strip, a bumpy road surface and a pothole road surface; the threshold coefficient at the normal road surface position is 1, and the threshold coefficient at the special road surface position is greater than 1.
7. The method of claim 6, wherein the threshold coefficient at the specific road surface location is calibrated by a test by: the method comprises the steps of measuring actual values of longitudinal acceleration of a vehicle body when the vehicle passes through the special road positions in different running states aiming at each special road position, calculating expected values of the longitudinal acceleration of the vehicle body when the vehicle passes through the special road positions in different running states based on collected real vehicle data when the vehicle passes through the special road positions in different running states and vehicle speed longitudinal acceleration calculation models corresponding to the corresponding running states, calculating difference values of the expected values and the actual values of the longitudinal acceleration of the vehicle body corresponding to the special road positions in each running state, and taking the ratio of the difference values and initial threshold values in each running state as a threshold coefficient of the special road positions in the corresponding running states.
8. The method of claim 7, wherein the collision threshold corresponding to the current position of the vehicle is calculated by: and T is k T0, wherein T is a collision threshold corresponding to the current position of the vehicle, k is a threshold coefficient corresponding to the current position of the vehicle, k is more than or equal to 1, and T0 is an initial threshold.
9. A collision accident detection system for an autonomous vehicle, the system comprising:
the vehicle control unit is used for acquiring the vehicle speed in real time;
the intelligent controller is used for acquiring an automatic driving control signal of the vehicle in real time, wherein the automatic driving control signal comprises an accelerator opening degree and a braking deceleration;
the acceleration sensor is used for acquiring an actual value of the longitudinal acceleration of the vehicle body in real time;
and a collision accident detection module for receiving data of the vehicle control unit, the intelligent controller and the acceleration sensor, and for implementing the collision accident detection method of the autonomous vehicle according to any one of claims 1 to 8.
10. An autonomous vehicle comprising a vehicle body and a collision accident detection system, characterized in that the collision accident detection system comprises:
the vehicle control unit is used for acquiring the vehicle speed in real time;
the intelligent controller is used for acquiring an automatic driving control signal of the vehicle in real time, wherein the automatic driving control signal comprises an accelerator opening degree and a braking deceleration;
the acceleration sensor is used for acquiring an actual value of the longitudinal acceleration of the vehicle body in real time;
and a collision accident detection module for receiving data of the vehicle control unit, the intelligent controller and the acceleration sensor, and for implementing the collision accident detection method of the autonomous vehicle according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011487872.7A CN114633743B (en) | 2020-12-16 | 2020-12-16 | Automatic driving vehicle and collision accident detection method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011487872.7A CN114633743B (en) | 2020-12-16 | 2020-12-16 | Automatic driving vehicle and collision accident detection method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114633743A true CN114633743A (en) | 2022-06-17 |
| CN114633743B CN114633743B (en) | 2024-05-28 |
Family
ID=81945450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011487872.7A Active CN114633743B (en) | 2020-12-16 | 2020-12-16 | Automatic driving vehicle and collision accident detection method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114633743B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6233515B1 (en) * | 1998-12-07 | 2001-05-15 | Jaguar Car, Limited | Adaptive vehicle cruise control system and methodology |
| CN102616235A (en) * | 2012-04-09 | 2012-08-01 | 北京航空航天大学 | Cooperative anti-collision device based on vehicle-vehicle communication and anti-collision method |
| KR20140140845A (en) * | 2013-05-30 | 2014-12-10 | 서강대학교산학협력단 | Method of characterizing driver propensity for different forward collision warning times |
| CN105493165A (en) * | 2013-09-02 | 2016-04-13 | 丰田自动车株式会社 | Vehicle driving situation determination apparatus and vehicle driving situation determination method |
| CN106891846A (en) * | 2016-12-30 | 2017-06-27 | 上海蔚来汽车有限公司 | Safety warning system and method based on Doppler effect |
| CN106934876A (en) * | 2017-03-16 | 2017-07-07 | 广东翼卡车联网服务有限公司 | A kind of recognition methods of vehicle abnormality driving event and system |
| CN107264527A (en) * | 2017-06-08 | 2017-10-20 | 广州汽车集团股份有限公司 | Intelligent vehicle prevents the control method and device of other car |
| CN109117709A (en) * | 2017-06-23 | 2019-01-01 | 优步技术公司 | Collision avoidance system for automatic driving vehicle |
| JP2019139331A (en) * | 2018-02-06 | 2019-08-22 | パナソニックＩｐマネジメント株式会社 | Vehicle management system and control method of vehicle management system |
| CN110435647A (en) * | 2019-07-26 | 2019-11-12 | 大连理工大学 | A kind of vehicle safety anticollision control method of the TTC based on rolling optimization parameter |
| WO2020082778A1 (en) * | 2018-10-25 | 2020-04-30 | 广州小鹏汽车科技有限公司 | Vehicle collision detection method and vehicle control system |
| WO2020187259A1 (en) * | 2019-03-18 | 2020-09-24 | 长城汽车股份有限公司 | Safety monitoring method and system for autonomous vehicle, and motion control system |
| WO2020187254A1 (en) * | 2019-03-18 | 2020-09-24 | 长城汽车股份有限公司 | Longitudinal control method and system for automatic driving vehicle |
| CN111746555A (en) * | 2019-03-26 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Identification and avoidance of collision behavior |
| CN111976638A (en) * | 2020-08-28 | 2020-11-24 | 广州市网优优信息技术开发有限公司 | Vehicle collision detection method and system based on vehicle-mounted intelligent terminal |
-
2020
- 2020-12-16 CN CN202011487872.7A patent/CN114633743B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6233515B1 (en) * | 1998-12-07 | 2001-05-15 | Jaguar Car, Limited | Adaptive vehicle cruise control system and methodology |
| CN102616235A (en) * | 2012-04-09 | 2012-08-01 | 北京航空航天大学 | Cooperative anti-collision device based on vehicle-vehicle communication and anti-collision method |
| KR20140140845A (en) * | 2013-05-30 | 2014-12-10 | 서강대학교산학협력단 | Method of characterizing driver propensity for different forward collision warning times |
| CN105493165A (en) * | 2013-09-02 | 2016-04-13 | 丰田自动车株式会社 | Vehicle driving situation determination apparatus and vehicle driving situation determination method |
| CN106891846A (en) * | 2016-12-30 | 2017-06-27 | 上海蔚来汽车有限公司 | Safety warning system and method based on Doppler effect |
| WO2018120831A1 (en) * | 2016-12-30 | 2018-07-05 | 上海蔚来汽车有限公司 | Doppler effect-based vehicle safety forewarning system and method |
| CN106934876A (en) * | 2017-03-16 | 2017-07-07 | 广东翼卡车联网服务有限公司 | A kind of recognition methods of vehicle abnormality driving event and system |
| CN107264527A (en) * | 2017-06-08 | 2017-10-20 | 广州汽车集团股份有限公司 | Intelligent vehicle prevents the control method and device of other car |
| CN109117709A (en) * | 2017-06-23 | 2019-01-01 | 优步技术公司 | Collision avoidance system for automatic driving vehicle |
| JP2019139331A (en) * | 2018-02-06 | 2019-08-22 | パナソニックＩｐマネジメント株式会社 | Vehicle management system and control method of vehicle management system |
| WO2020082778A1 (en) * | 2018-10-25 | 2020-04-30 | 广州小鹏汽车科技有限公司 | Vehicle collision detection method and vehicle control system |
| WO2020187259A1 (en) * | 2019-03-18 | 2020-09-24 | 长城汽车股份有限公司 | Safety monitoring method and system for autonomous vehicle, and motion control system |
| WO2020187254A1 (en) * | 2019-03-18 | 2020-09-24 | 长城汽车股份有限公司 | Longitudinal control method and system for automatic driving vehicle |
| CN111746555A (en) * | 2019-03-26 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Identification and avoidance of collision behavior |
| CN110435647A (en) * | 2019-07-26 | 2019-11-12 | 大连理工大学 | A kind of vehicle safety anticollision control method of the TTC based on rolling optimization parameter |
| CN111976638A (en) * | 2020-08-28 | 2020-11-24 | 广州市网优优信息技术开发有限公司 | Vehicle collision detection method and system based on vehicle-mounted intelligent terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114633743B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108466616B (en) | Method for automatically identifying collision event, storage medium and vehicle-mounted terminal | |
| CN105109490B (en) | Method for judging sharp turn of vehicle based on three-axis acceleration sensor | |
| CN113340615B (en) | Automobile automatic driving function simulation test system and method | |
| CN107031552A (en) | A kind of car crass detection method and system | |
| EP3098130A2 (en) | Vehicle speed control apparatus and vehicle speed limiting apparatus | |
| CN110388913A (en) | Positioning enhancing based on deceleration strip | |
| US8666563B2 (en) | Determination apparatus for determining erroneous application of accelerator rather than brake | |
| CN109774473B (en) | Speed limit control method based on camera and navigation data fusion | |
| CN113702067B (en) | Self-adaptive cruise system evaluation system and method for commercial vehicle | |
| JPH11248734A (en) | Device for computing evaluated value of car body roll | |
| CN113640017A (en) | Test evaluation system and method for automatic emergency braking system of commercial vehicle | |
| CN106043279A (en) | Lane shift control system based on crosswind influences and control method of lane shift control system | |
| CN113232643B (en) | Self-adaptive auxiliary driving system and method based on road surface environment | |
| CN113968231B (en) | Intelligent driver model parameter determination method conforming to driver habits | |
| CN112046455B (en) | Automatic emergency braking method based on vehicle quality identification | |
| CN108062856B (en) | Vehicle collision detection system and method based on vehicle-mounted OBD interface | |
| CN115158304B (en) | Automatic emergency braking control system and method | |
| EP3891512B1 (en) | System and method for providing an indication of driving performance | |
| JP2024032849A (en) | Information processing device, information processing system, information processing method and program | |
| CN114633743B (en) | Automatic driving vehicle and collision accident detection method and system thereof | |
| CN108956156A (en) | The performance test methods and its device of the seized system of vehicle | |
| CN111483458B (en) | Power system control method and device | |
| JP2023099687A (en) | Information processing device, information processing system, information processing method and program | |
| CN114264486B (en) | Vehicle three-emergency detection method based on low-cost sensor | |
| CN103158718A (en) | Detection device and detection method of road longitudinal slope based on accelerator pedal position and vehicle speed |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: No. 6, Yutong Road, Guancheng Hui District, Zhengzhou, Henan 450061 Applicant after: Yutong Bus Co.,Ltd. Address before: No.1, Shibali Heyu Road, Guancheng Hui District, Zhengzhou City, Henan Province Applicant before: ZHENGZHOU YUTONG BUS Co.,Ltd. Country or region before: China |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |