CN114185340B - Obstacle position abnormality detection method and device - Google Patents
Obstacle position abnormality detection method and device Download PDFInfo
- Publication number
- CN114185340B CN114185340B CN202111350552.1A CN202111350552A CN114185340B CN 114185340 B CN114185340 B CN 114185340B CN 202111350552 A CN202111350552 A CN 202111350552A CN 114185340 B CN114185340 B CN 114185340B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- jump
- distance
- time
- speed
- 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
- 238000001514 detection method Methods 0.000 title claims description 56
- 230000005856 abnormality Effects 0.000 title claims description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 23
- 239000013598 vector Substances 0.000 claims description 26
- 230000004888 barrier function Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000008447 perception Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
Abstract
The invention discloses a method and a device for detecting abnormal positions of obstacles, wherein the method comprises the following steps: acquiring a first speed, a first position, a first distance from a host vehicle and a first direction relative to the host vehicle of an obstacle at a time T1, and a second position of the obstacle at a time T2; calculating the predicted position of the obstacle at the time T2 according to the first speed, the first position and the interval duration between the time T1 and the time T2; calculating a jump distance in a preset direction according to the second position and the predicted position; inputting the first speed, the first distance and the first direction into a preset jump analysis model, so that the jump analysis model calculates a jump distance threshold value of the obstacle in the preset direction according to the first speed, the first distance and the first direction; and comparing the jump distance with a jump distance threshold value, and judging that the second position is abnormal when the jump distance exceeds the jump distance threshold value. By implementing the invention, the abnormal obstacle position perceived by the vehicle perception module can be detected.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method and a device for detecting abnormal positions of obstacles.
Background
An autonomous vehicle needs to sense the position of an obstacle (e.g., other vehicles) through a sensing module on the vehicle, such as a camera and radar, during autonomous driving, to control the vehicle to avoid the obstacle. However, in actual situations, due to errors of the sensing module or interference of external environments, inaccurate abnormal situations may occur in the position of the obstacle determined by the sensing module, and if the autonomous driving vehicle cannot identify the abnormal obstacle position, the autonomous driving host vehicle is controlled according to the abnormal obstacle position, which may cause potential safety hazards.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting abnormal obstacle positions, which can detect abnormal obstacle positions sensed by a vehicle sensing module.
An embodiment of the present invention provides a method for detecting abnormality in the position of an obstacle, including: acquiring a first speed, a first position, a first distance from a host vehicle and a first direction relative to the host vehicle of an obstacle at a time T1, and a second position of the obstacle at a time T2; wherein, the time T1 is the time before the time T2;
Calculating the predicted position of the obstacle at the time T2 according to the first speed, the first position and the interval duration between the time T1 and the time T2;
calculating a jump distance of the obstacle from the time T1 to the time T2 in a preset direction according to the second position and the predicted position;
inputting the first speed, the first distance and the first direction into a preset jump analysis model, so that the jump analysis model calculates a jump distance threshold value in the preset direction from the moment T1 to the moment T2 of the obstacle according to the first speed, the first distance and the first direction;
And comparing the jump distance with a jump distance threshold value, and judging that the second position is abnormal when the jump distance exceeds the jump distance threshold value.
Further, before acquiring the first speed, the first position, the first distance from the host vehicle and the first direction relative to the host vehicle of the obstacle at the time T1, and the second position of the obstacle at the time T2, the method further comprises:
Constructing a first obstacle detection area by taking a position point which is positioned in the advancing direction of the main vehicle and is separated from the main vehicle by a second distance as a circle center and taking a first length as a radius;
constructing a second obstacle detection area by taking the main vehicle as a circle center and taking the second length as a radius;
Removing the overlapping area of the first obstacle detection area and the second obstacle detection area to obtain an actual obstacle detection area;
and performing obstacle detection according to the actual obstacle detection area.
Further, the second distance is calculated by the following formula:
The first length is calculated by the following formula:
the second length is calculated by the following formula:
Wherein R is a second distance; d is a first length; r is a second length; v car is the main vehicle travel speed; A. b, C, F are preset parameters.
Further, calculating the jump distance of the obstacle from the time T1 to the time T2 according to the second position and the predicted position in the preset direction specifically includes:
Calculating a jump vector of the obstacle from the moment T1 to the moment T2 according to the second position and the predicted position;
performing orthogonal decomposition on the jump vectors to obtain a first jump vector of the barrier in the forward direction of the main vehicle and a second jump vector of the barrier in the vertical direction of the forward direction of the main vehicle;
Determining a first jump distance of the obstacle from the time T1 to the time T2 in the forward direction of the main vehicle according to the first jump vector; and determining a second jump distance of the obstacle from the time T1 to the time T2 in the vertical direction of the advancing direction of the main vehicle according to the second jump vector.
Further, the step of inputting the first speed, the first distance and the first direction into a preset jump analysis model to enable the jump analysis model to generate a jump distance threshold value of the obstacle from the time T1 to the time T2 in the preset direction according to the first speed, the first distance and the first direction specifically includes:
Inputting the first speed, the first distance and the first direction into a preset jump analysis model, so that the jump analysis model generates a first jump distance threshold value in the forward direction of the main vehicle and a second jump distance threshold value in the vertical direction of the forward direction of the main vehicle from the time T1 to the time T2 of the obstacle according to the first speed, the first distance and the first direction.
Further, the comparing the jump distance with the jump distance threshold, and when the jump distance exceeds the jump distance threshold, determining that the second position is abnormal specifically includes:
Comparing the first jump distance with a first jump distance threshold value, comparing the second jump distance with a second jump distance threshold value, and judging that the second position is abnormal when the first jump distance exceeds the second jump distance threshold value or the second jump distance exceeds the second jump distance threshold value.
Further, the construction of the preset jump analysis model specifically includes:
constructing regression variables according to the speed of the obstacle, the distance between the obstacle and the main vehicle and the direction between the obstacle and the main vehicle at each moment;
Calculating the corresponding jump distance of the obstacle at each moment according to the position of the obstacle at each moment, and constructing an interpretation variable according to the calculated jump distances;
Constructing a quantile regression model according to regression variables, interpretation variables and preset quantile conditions, and taking the constructed quantile regression model as the jump analysis model.
Further, after determining that the second position is abnormal, the method further includes: the second location is replaced with the predicted location.
On the basis of the method item embodiment, the invention correspondingly provides a device item embodiment;
The embodiment of the invention provides an obstacle position abnormality detection device, which comprises a data acquisition module, a predicted position calculation module, a jump distance threshold calculation module and an abnormality judgment module;
The data acquisition module is used for acquiring a first speed, a first position, a first distance from the host vehicle and a first direction relative to the host vehicle of the obstacle at the moment T1 and a second position of the obstacle at the moment T2; wherein, the time T1 is the time before the time T2;
The predicted position calculation module is used for calculating the predicted position of the obstacle at the time T2 according to the first speed, the first position and the interval duration between the time T1 and the time T2;
The jump distance calculation module is used for calculating the jump distance of the obstacle from the moment T1 to the moment T2 in the preset direction according to the second position and the predicted position;
the jump distance threshold calculation module is used for inputting the first speed, the first distance and the first direction into a preset jump analysis model so that the jump analysis model calculates a jump distance threshold in the preset direction when the obstacle goes from the moment T1 to the moment T2 according to the first speed, the first distance and the first direction;
the abnormality determination module is configured to compare the jump distance with a jump distance threshold, and determine that the second position is abnormal when the jump distance exceeds the jump distance threshold.
Further, the device also comprises a position correction module; and the position correction module is used for replacing the second position with the predicted position after judging that the second position is abnormal.
The embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides a method and a device for detecting abnormal positions of obstacles, wherein the method calculates the predicted positions of the obstacles at the current moment according to the speeds and the positions of the obstacles at the previous moment and the interval moment between the previous moment and the current moment; and then calculating a jump distance threshold value according to the calculated predicted position and the obtained jump distance of the position at the current moment, and meanwhile, calculating a jump distance threshold value through a jump analysis model based on the speed of the obstacle at the previous moment, the distance between the obstacle and the main vehicle and the direction relative to the main vehicle, and finally comparing the jump distance with the jump distance threshold value, if the jump distance exceeds the jump distance threshold value, judging that the position of the obstacle obtained at the current moment is abnormal, thereby realizing the detection of the abnormal position of the obstacle, and further improving the running safety of the automatic driving vehicle.
Drawings
Fig. 1 is a flowchart of a method for detecting an abnormality in a position of an obstacle according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of an actual obstacle detection area according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an obstacle position abnormality detection device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, an embodiment of the present invention provides a method for detecting an abnormality in a position of an obstacle, including at least the following steps:
S101, acquiring a first speed, a first position, a first distance from a main vehicle and a first direction relative to the main vehicle of an obstacle at a time T1, and a second position of the obstacle at a time T2; wherein, the time T1 is the time immediately before the time T2.
S102, calculating the predicted position of the obstacle at the time T2 according to the first speed, the first position and the interval duration between the time T1 and the time T2.
S103, calculating the jump distance of the obstacle from the time T1 to the time T2 in the preset direction according to the second position and the predicted position.
S104, inputting the first speed, the first distance and the first direction into a preset jump analysis model, so that the jump analysis model calculates a jump distance threshold value in the preset direction when the obstacle is from the moment T1 to the moment T2 according to the first speed, the first distance and the first direction.
S105, comparing the jump distance with a jump distance threshold value, and judging that the second position is abnormal when the jump distance exceeds the jump distance threshold value.
For step S101, the autonomous driving host vehicle passes through the sensing module (such as the camera device and the radar) mounted thereon, the state information of the obstacle (such as other target vehicles) at each moment, such as the speed, the position, the distance from the host vehicle, the direction relative to the host vehicle, etc., can be sensed during the driving process, so as to obtain the first speed, the first position, the first distance from the host vehicle and the first direction relative to the host vehicle of the obstacle at the moment T1, and the second position of the obstacle at the moment T2;
In order to sense an obstacle, it is necessary to set a detection area in advance, and sense the obstacle through the detection area. Thus in a preferred embodiment, before acquiring the first speed, the first position, the first distance from and the first direction relative to the host vehicle of the obstacle at time T1, and the second position of the obstacle at time T2, further comprises: constructing a first obstacle detection area by taking a position point which is positioned in the advancing direction of the main vehicle and is separated from the main vehicle by a second distance as a circle center and taking a first length as a radius; constructing a second obstacle detection area by taking the main vehicle as a circle center and taking the second length as a radius; removing the overlapping area of the first obstacle detection area and the second obstacle detection area to obtain an actual obstacle detection area; and performing obstacle detection according to the actual obstacle detection area.
As shown in fig. 2, a point 5 in the diagram is a center point of the host vehicle 1, a point 6 is a center point of a first obstacle detection area, a distance d between the point 5 and the point 6 is the second distance, R is the first length, and a circular detection area is constructed by taking the point 6 as the center point and taking R as a radius, so that the first obstacle detection area 3 can be obtained; and constructing a circular detection area by taking the point 5 as the center and taking the second length r as the radius, so as to obtain the second obstacle detection area, combining the first obstacle detection area and the second obstacle detection area, and removing the repeated area, so as to obtain the actual obstacle detection area consisting of the 3 and 4 shown in the figure (the 4 shown in the figure is the part of the second obstacle detection area which is remained after the repeated area is removed). The actual obstacle detection area is used for detecting the obstacles around the host vehicle, if the obstacles are detected to fall into the actual obstacle detection area, data such as the speed, the distance between the position and the host vehicle, the direction relative to the host vehicle and the like of the obstacles are collected, and as shown in fig. 2, the state information of the obstacles 2 can be collected when the obstacles 2 fall into the actual obstacle detection area. By adopting the mode to set the obstacle detection area, the obstacle detection can be simultaneously carried out on the front and the rear of the main vehicle in the running process.
In a preferred embodiment, the second distance, the first length, and the second length may be predetermined values. Illustratively, the second distance may be set to 2 meters, the first length to 3 meters, and the first length to 1.5 meters; the specific setting can be set according to the actual length of the main vehicle and the requirement of the detection range.
In the actual driving process, the speed of the main vehicle may be different at each moment, the faster the speed, the larger the safety distance needs to be reserved, the actual obstacle detection range should be enlarged along with the increase of the speed of the main vehicle, the slower the speed, the smaller the safety distance needs to be reserved, the actual obstacle detection range should be reduced along with the decrease of the speed of the main vehicle, so that enough safety distance can be reserved for the main vehicle to ensure the safety of the main vehicle in the driving process, and in another preferred embodiment, the second distance is calculated by the following formula: the first length is calculated by the following formula: /(I) The second length is calculated by the following formula: /(I)Wherein R is a second distance; d is a first length; r is a second length; v car is the main vehicle travel speed; A. b, C, F are preset parameters. Schematic a may be 2, B and F may be 5; c may be 10. Based on the embodiment, the size of the actual obstacle detection area can be automatically adjusted according to the running speed of the main vehicle so as to ensure the safety of the main vehicle in the running process.
For step S102, specifically, calculating the predicted position of the obstacle at the time T2 by the following formula;
pospredict=poscurrent+vcurrent*delta_time;
In the above equation, pos predict is the predicted position of the obstacle at time T2, pos current is the position of the obstacle at time T1 (i.e., the first position) sensed by the sensing module mounted on the host vehicle, v current is the speed of the obstacle at time T1 (i.e., the first speed) sensed by the sensing module mounted on the host vehicle, delta_time is the duration of the interval between time T1 and time T2.
For step S103, in a preferred embodiment, the calculating the jump distance of the obstacle from the time T1 to the time T2 according to the second position and the predicted position in the preset direction specifically includes:
Calculating a jump vector of the obstacle from the moment T1 to the moment T2 according to the second position and the predicted position;
performing orthogonal decomposition on the jump vectors to obtain a first jump vector of the barrier in the forward direction of the main vehicle and a second jump vector of the barrier in the vertical direction of the forward direction of the main vehicle;
Determining a first jump distance of the obstacle from the time T1 to the time T2 in the forward direction of the main vehicle according to the first jump vector; and determining a second jump distance of the obstacle from the time T1 to the time T2 in the vertical direction of the advancing direction of the main vehicle according to the second jump vector.
Specifically, the jump vector of the obstacle from the time T1 to the time T2 is calculated by the following formula:
jump=posnext-pospredict;
jump is a jump vector of the obstacle from the time T1 to the time T2, and pos next is a position of the obstacle at the time T2 (i.e. the second position) sensed by a sensing module mounted on the host vehicle;
performing orthogonal decomposition on the hopping vector through the following formula to obtain a first hopping vector and a second hopping vector;
jump=jumplongitude+jumplatitude;
jump longitude is the first jump vector in the forward direction of the host vehicle, and jump latitude is the second jump variable in the vertical direction of the forward direction of the host vehicle;
And determining the first hopping distance and the second hopping distance according to the calculated first hopping vector and the second hopping vector.
For step S104, a jump analysis model is first described: in a preferred embodiment, the construction of the preset jump analysis model specifically includes:
constructing regression variables according to the speed of the obstacle, the distance between the obstacle and the main vehicle and the direction between the obstacle and the main vehicle at each moment;
Calculating the corresponding jump distance of the obstacle at each moment according to the position of the obstacle at each moment, and constructing an interpretation variable according to the calculated jump distances;
Constructing a quantile regression model according to regression variables, interpretation variables and preset quantile conditions, and taking the constructed quantile regression model as the jump analysis model.
Schematically, 200 scenes are randomly selected, all video frames in a detection range are obtained, the speed of an obstacle at each moment, the distance between the obstacle and a host vehicle and the direction relative to the host vehicle are determined according to the obtained video frames, the jump distance at each moment is calculated (the jump distance corresponding to each video frame is required to be described in the invention, and the jump distance corresponding to any moment is calculated according to the predicted position at the moment and the position at the moment perceived by a host vehicle perception module), then a regression variable X is constructed according to the speed of the obstacle at each moment, the distance between the obstacle and the host vehicle and the direction relative to the host vehicle, a dataset for explaining the variable Y is constructed according to the jump distance at each moment, a preset quantile condition is set to be 0.95, and a 0.95-quantile regression model is constructed according to the dataset, so that the jump analysis model is obtained;
The jump analysis model includes a first jump analysis sub-model formed by taking the speed of the obstacle at each moment, the distance between the obstacle and the host vehicle and the direction relative to the host vehicle as a regression variable X and taking the jump distance of the obstacle at each moment in the forward direction of the host vehicle as an interpretation variable Y; and a second jump analysis sub-model formed by taking the speed of the obstacle at each moment, the distance from the main vehicle and the direction relative to the main vehicle as regression variables X and taking the jump distance of the obstacle at each moment in the vertical direction of the advancing direction of the main vehicle as interpretation variables Y.
After the jump analysis model is obtained, a first speed, a first distance and a first direction are input into a preset jump analysis model, so that the jump analysis model generates a first jump distance threshold value of an obstacle from a time T1 to a time T2 and a second jump distance threshold value of the obstacle in the forward direction of the main vehicle and a second jump distance threshold value of the obstacle in the vertical direction of the forward direction of the main vehicle according to the first speed, the first distance and the first direction.
Specifically, the model calculates a first transition distance threshold and a second transition distance threshold according to the following formulas:
thresholdlon=paramslon·feature;
thresholdlat=paramslat·feature;
threshold lon is the first hop distance threshold; params lon is the plane parameter of the first hop analysis sub-model; feature is the first speed, first distance, and first direction; threshold lat is the second hop distance threshold; params lat is the plane parameter of the second hop analysis sub-model.
For step S105, in a preferred embodiment, the comparing the jump distance with the jump distance threshold, and when the jump distance exceeds the jump distance threshold, determining that the second position is abnormal specifically includes:
Comparing the first jump distance with a first jump distance threshold value, comparing the second jump distance with a second jump distance threshold value, and judging that the second position is abnormal when the first jump distance exceeds the second jump distance threshold value or the second jump distance exceeds the second jump distance threshold value.
Specifically, after the corresponding first jump distance threshold value and the second jump distance threshold value are obtained according to step S104, whether the first jump distance and the second jump distance of the obstacle at the time T2 are abnormal or not may be determined according to the obtained jump distance threshold value, and if any jump distance exceeds the corresponding jump distance threshold value, it is determined that the second position sensed by the sensing module mounted on the host vehicle is abnormal at the time T2.
In a preferred embodiment, after determining the second location anomaly, further comprising: the second location is replaced with the predicted location. By replacing the abnormal second position with the predicted position, the correction of the obstacle position is realized, so that the host vehicle can accurately determine the position of the obstacle, and the safety of automatic driving is improved.
By implementing the embodiment of the invention, the position information sensed by the sensing module carried by the automatic driving host vehicle can be subjected to abnormality detection, and the correction is carried out after the abnormality is detected, so that the safety of automatic driving is improved.
On the basis of the method item embodiment, the invention correspondingly provides a device item embodiment;
as shown in fig. 3, an embodiment of the present invention provides an obstacle position anomaly detection device, including a data acquisition module, a predicted position calculation module, a jump distance threshold calculation module, and an anomaly determination module;
The data acquisition module is used for acquiring a first speed, a first position, a first distance from the host vehicle and a first direction relative to the host vehicle of the obstacle at the moment T1 and a second position of the obstacle at the moment T2; wherein, the time T1 is the time before the time T2;
The predicted position calculation module is used for calculating the predicted position of the obstacle at the time T2 according to the first speed, the first position and the interval duration between the time T1 and the time T2;
The jump distance calculation module is used for calculating the jump distance of the obstacle from the moment T1 to the moment T2 in the preset direction according to the second position and the predicted position;
the jump distance threshold calculation module is used for inputting the first speed, the first distance and the first direction into a preset jump analysis model so that the jump analysis model calculates a jump distance threshold in the preset direction when the obstacle goes from the moment T1 to the moment T2 according to the first speed, the first distance and the first direction;
the abnormality determination module is configured to compare the jump distance with a jump distance threshold, and determine that the second position is abnormal when the jump distance exceeds the jump distance threshold.
In a preferred embodiment, the system further comprises a position correction module; and the position correction module is used for replacing the second position with the predicted position after judging that the second position is abnormal.
It should be noted that, the embodiment of the apparatus disclosed in the present invention corresponds to the embodiment of the method of the present invention, which is capable of implementing the method for detecting an abnormality of an obstacle position according to any one of the foregoing embodiments of the present invention, and the embodiment of the apparatus described above is merely illustrative, where the units described as separate units may or may not be physically separated, and the units displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (9)
1. An obstacle position abnormality detection method, comprising:
acquiring a first speed, a first position, a first distance from a host vehicle and a first direction relative to the host vehicle of an obstacle at a time T1, and a second position of the obstacle at a time T2; wherein, the time T1 is the time before the time T2;
Calculating the predicted position of the obstacle at the time T2 according to the first speed, the first position and the interval duration between the time T1 and the time T2;
calculating a jump distance of the obstacle from the time T1 to the time T2 in a preset direction according to the second position and the predicted position;
Inputting the first speed, the first distance and the first direction into a preset jump analysis model, so that the jump analysis model calculates a jump distance threshold value in the preset direction when the obstacle is from the moment T1 to the moment T2 according to the first speed, the first distance and the first direction, wherein the construction of the preset jump analysis model specifically comprises the following steps: constructing regression variables according to the speed of the obstacle, the distance between the obstacle and the main vehicle and the direction between the obstacle and the main vehicle at each moment; calculating the corresponding jump distance of the obstacle at each moment according to the position of the obstacle at each moment, and constructing an interpretation variable according to the calculated jump distances; constructing a quantile regression model according to regression variables, interpretation variables and preset quantile conditions, and taking the constructed quantile regression model as the jump analysis model;
And comparing the jump distance with a jump distance threshold value, and judging that the second position is abnormal when the jump distance exceeds the jump distance threshold value.
2. The obstacle position abnormality detection method according to claim 1, characterized by, before acquiring the first speed, the first position, the first distance from the host vehicle, and the first direction with respect to the host vehicle of the obstacle at a time T1, and the second position of the obstacle at a time T2, further comprising:
Constructing a first obstacle detection area by taking a position point which is positioned in the advancing direction of the main vehicle and is separated from the main vehicle by a second distance as a circle center and taking a first length as a radius;
constructing a second obstacle detection area by taking the main vehicle as a circle center and taking the second length as a radius;
Removing the overlapping area of the first obstacle detection area and the second obstacle detection area to obtain an actual obstacle detection area;
and performing obstacle detection according to the actual obstacle detection area.
3. The obstacle position abnormality detection method according to claim 2, wherein said second distance is calculated by the following formula:;
The first length is calculated by the following formula: ;
the second length is calculated by the following formula: ;
Wherein, Is a second distance; /(I)Is of a first length; /(I)Is a second length; /(I)The driving speed of the main vehicle; A. b, C, F are preset parameters.
4. The method for detecting abnormal position of an obstacle according to claim 1, wherein calculating a jump distance of the obstacle from time T1 to time T2 in a preset direction according to the second position and the predicted position specifically comprises:
calculating a jump vector of the obstacle from the moment T1 to the moment T2 according to the second position and the predicted position;
performing orthogonal decomposition on the jump vectors to obtain a first jump vector of the barrier in the forward direction of the main vehicle and a second jump vector of the barrier in the vertical direction of the forward direction of the main vehicle;
Determining a first jump distance of the obstacle from the time T1 to the time T2 in the forward direction of the main vehicle according to the first jump vector; and determining a second jump distance of the obstacle from the time T1 to the time T2 in the vertical direction of the advancing direction of the main vehicle according to the second jump vector.
5. The method for detecting abnormal obstacle position according to claim 4, wherein the step of inputting the first speed, the first distance and the first direction into a predetermined jump analysis model to enable the jump analysis model to generate a jump distance threshold value of the obstacle from time T1 to time T2 in the predetermined direction according to the first speed, the first distance and the first direction specifically comprises:
Inputting the first speed, the first distance and the first direction into a preset jump analysis model, so that the jump analysis model generates a first jump distance threshold value in the forward direction of the main vehicle and a second jump distance threshold value in the vertical direction of the forward direction of the main vehicle from the time T1 to the time T2 of the obstacle according to the first speed, the first distance and the first direction.
6. The method for detecting an abnormality in the position of an obstacle according to claim 5, wherein comparing the jump distance with a jump distance threshold value, and determining that the second position is abnormal when the jump distance exceeds the jump distance threshold value, comprises:
Comparing the first jump distance with a first jump distance threshold value, comparing the second jump distance with a second jump distance threshold value, and judging that the second position is abnormal when the first jump distance exceeds the second jump distance threshold value or the second jump distance exceeds the second jump distance threshold value.
7. The obstacle position abnormality detection method according to any one of claims 1 to 6, characterized by further comprising, after determining that the second position is abnormal: the second location is replaced with the predicted location.
8. The obstacle position abnormality detection device is characterized by comprising a data acquisition module, a predicted position calculation module, a jump distance threshold calculation module and an abnormality judgment module;
The data acquisition module is used for acquiring a first speed, a first position, a first distance from the host vehicle and a first direction relative to the host vehicle of the obstacle at the moment T1 and a second position of the obstacle at the moment T2; wherein, the time T1 is the time before the time T2;
The predicted position calculation module is used for calculating the predicted position of the obstacle at the time T2 according to the first speed, the first position and the interval duration between the time T1 and the time T2;
The jump distance calculation module is used for calculating the jump distance of the obstacle from the moment T1 to the moment T2 in the preset direction according to the second position and the predicted position;
The jump distance threshold calculating module is configured to input a first speed, a first distance and a first direction into a preset jump analysis model, so that the jump analysis model calculates a jump distance threshold in a preset direction when an obstacle is from a time T1 to a time T2 according to the first speed, the first distance and the first direction, where the construction of the preset jump analysis model specifically includes: constructing regression variables according to the speed of the obstacle, the distance between the obstacle and the main vehicle and the direction between the obstacle and the main vehicle at each moment; calculating the corresponding jump distance of the obstacle at each moment according to the position of the obstacle at each moment, and constructing an interpretation variable according to the calculated jump distances; constructing a quantile regression model according to regression variables, interpretation variables and preset quantile conditions, and taking the constructed quantile regression model as the jump analysis model;
the abnormality determination module is configured to compare the jump distance with a jump distance threshold, and determine that the second position is abnormal when the jump distance exceeds the jump distance threshold.
9. The obstacle position anomaly detection device of claim 8, further comprising a position correction module;
And the position correction module is used for replacing the second position with the predicted position after judging that the second position is abnormal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111350552.1A CN114185340B (en) | 2021-11-15 | 2021-11-15 | Obstacle position abnormality detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111350552.1A CN114185340B (en) | 2021-11-15 | 2021-11-15 | Obstacle position abnormality detection method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114185340A CN114185340A (en) | 2022-03-15 |
CN114185340B true CN114185340B (en) | 2024-04-23 |
Family
ID=80540922
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111350552.1A Active CN114185340B (en) | 2021-11-15 | 2021-11-15 | Obstacle position abnormality detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114185340B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5943376A (en) * | 1982-09-06 | 1984-03-10 | Toyoda Autom Loom Works Ltd | Apparatus for positional detection of object |
JP2003344539A (en) * | 2002-05-22 | 2003-12-03 | Toshiba Tec Corp | Autonomous traveling car |
CN106646491A (en) * | 2015-10-30 | 2017-05-10 | 长城汽车股份有限公司 | Ultrasonic crash-proof radar system and barrier positioning method thereof |
CN107578427A (en) * | 2017-07-31 | 2018-01-12 | 深圳市易成自动驾驶技术有限公司 | Detection method, device and the computer-readable recording medium of dynamic barrier |
CN108162973A (en) * | 2016-12-07 | 2018-06-15 | 法乐第(北京)网络科技有限公司 | Improve the device and automated driving system of automatic Pilot reliability |
WO2020137134A1 (en) * | 2018-12-27 | 2020-07-02 | ヤンマー株式会社 | Collision avoidance system for work vehicle |
CN112230642A (en) * | 2019-06-29 | 2021-01-15 | 华为技术有限公司 | Road travelable area reasoning method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20200139125A (en) * | 2018-03-29 | 2020-12-11 | 얀마 파워 테크놀로지 가부시키가이샤 | Obstacle detection system, and work vehicle |
-
2021
- 2021-11-15 CN CN202111350552.1A patent/CN114185340B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5943376A (en) * | 1982-09-06 | 1984-03-10 | Toyoda Autom Loom Works Ltd | Apparatus for positional detection of object |
JP2003344539A (en) * | 2002-05-22 | 2003-12-03 | Toshiba Tec Corp | Autonomous traveling car |
CN106646491A (en) * | 2015-10-30 | 2017-05-10 | 长城汽车股份有限公司 | Ultrasonic crash-proof radar system and barrier positioning method thereof |
CN108162973A (en) * | 2016-12-07 | 2018-06-15 | 法乐第(北京)网络科技有限公司 | Improve the device and automated driving system of automatic Pilot reliability |
CN107578427A (en) * | 2017-07-31 | 2018-01-12 | 深圳市易成自动驾驶技术有限公司 | Detection method, device and the computer-readable recording medium of dynamic barrier |
WO2020137134A1 (en) * | 2018-12-27 | 2020-07-02 | ヤンマー株式会社 | Collision avoidance system for work vehicle |
CN112230642A (en) * | 2019-06-29 | 2021-01-15 | 华为技术有限公司 | Road travelable area reasoning method and device |
Also Published As
Publication number | Publication date |
---|---|
CN114185340A (en) | 2022-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7839272B2 (en) | Vehicle surroundings monitoring apparatus | |
JP5939357B2 (en) | Moving track prediction apparatus and moving track prediction method | |
US20180181142A1 (en) | Object position measurement with automotive camera using vehicle motion data | |
US8175334B2 (en) | Vehicle environment recognition apparatus and preceding-vehicle follow-up control system | |
US9031773B2 (en) | Apparatus and method for detecting narrow road in front of vehicle | |
US9527509B2 (en) | Driver convenience system and method for determining vertical angle abnormality of radar therein | |
KR20180060784A (en) | Method and apparatus for determining abnormal object | |
CN104865579A (en) | Vehicle-installed Obstacle Detection Apparatus Having Function For Judging Motion Condition Of Detected Object | |
KR20130130951A (en) | Lane keeping assist system and method | |
US11753002B2 (en) | Vehicular control system | |
CN110834642A (en) | Vehicle deviation identification method and device, vehicle and storage medium | |
CN108202745B (en) | Method and system for predicting state of obstacle vehicle | |
WO2023050586A1 (en) | Abnormality detection method and apparatus for positioning sensor, and terminal device | |
US20100145618A1 (en) | Vehicle collision management systems and methods | |
US20210034925A1 (en) | Obstacle recognition assistance device, obstacle recognition assistance method, and storage medium | |
CN115993597A (en) | Visual radar perception fusion method and terminal equipment | |
CN105022987B (en) | The method of bias correction and diagnostic function for lane sensing sensor | |
JP2007264717A (en) | Lane deviation decision device, lane deviation prevention device and lane follow-up supporting device | |
CN115223131A (en) | Adaptive cruise following target vehicle detection method and device and automobile | |
CN114185340B (en) | Obstacle position abnormality detection method and device | |
CN114475593A (en) | Travel track prediction method, vehicle, and computer-readable storage medium | |
JP6169270B2 (en) | Method and apparatus for identifying running state of external vehicle | |
CN114194184A (en) | Vehicle and method of controlling vehicle | |
CN116101269B (en) | Method, system and vehicle for safety monitoring of automatic parking process | |
CN112319505A (en) | Automatic driving lane change judgment method, device, equipment and storage medium |
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 |