A method and system for detecting vehicle queue status

Abstract

The present invention provides a method and system for detecting the state of vehicle queues, the method comprising determining a scanning range for obtaining blocking obstacles in front of the vehicle according to the current speed of the vehicle, a set scanning time and a minimum scanning distance; generating a valid obstacle list according to the running speed of all blocking obstacles in the scanning range; determining the final driving state of each blocking obstacle according to the information of each blocking obstacle in the valid obstacle list and a set state threshold; and determining the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list. The method and system solve the problems of large data volume and high computing power caused by vehicle queue state detection based on neural networks and deep learning in actual engineering, which is faster and more efficient, and it is easy to perform a jump design of the vehicle state machine based on this detection result, which not only ensures the traffic efficiency of the vehicle, but also improves the intelligence of the vehicle.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving planning, and more specifically, to a method and system for detecting a vehicle queuing state. Background Art

[0002] The autonomous driving planning module is generally divided into lateral path planning and longitudinal speed planning. Among them, lateral path planning is responsible for generating a spatial path that does not contain time information. In order to ensure traffic efficiency, the vehicle (the vehicle to be detected) will bypass the blocked obstacles in front based on the above spatial path. However, bypassing in the state of vehicle queues will not only cause road congestion and inability to return, but also easily cause collision risks. Therefore, it is necessary to identify and judge the scene to ensure rapid and accurate identification of the traffic queue status, so as to help the vehicle make more reasonable decisions. In the existing technology, the traffic queue status is mainly identified based on machine learning or deep learning models to make corresponding bypass decisions, but this method has high requirements on data quality and computing power. Summary of the invention

[0003] In order to solve the technical problem in the prior art that identifying the queuing status of vehicles based on machine learning or deep learning models to make corresponding detour decisions requires high data quality and computing power, the present invention provides a method and device for detecting the queuing status of vehicles.

[0004] According to one aspect of the present invention, the present invention provides a method for detecting a vehicle queue state, comprising:

[0005] The scanning range for obtaining the blocked obstacles in front of the vehicle is determined according to the current vehicle speed, the set scanning time and the minimum scanning distance;

[0006] Generate a valid obstacle list according to the running speeds of all blocked obstacles within the scanning range;

[0007] Determining a final driving state of each blocking obstacle according to information of each blocking obstacle in the valid obstacle list and a set state threshold, wherein the final driving state includes a parking state and a non-parking state;

[0008] The final detection result of the vehicle queue state is determined according to the final driving state of each blocking obstacle in the valid obstacle list, wherein the final detection result includes the vehicle being in the vehicle queue state and the vehicle being in the non-vehicle queue state.

[0009] According to another aspect of the present invention, the present invention provides a system for detecting a vehicle queue state, the system comprising:

[0010] The scanning range module is used to determine the scanning range of the blocked obstacles in front of the vehicle according to the current vehicle speed, the set scanning time and the minimum scanning distance;

[0011] An obstacle list module, used to generate a valid obstacle list according to the running speeds of all blocking obstacles within the scanning range;

[0012] A first detection module, configured to determine a final driving state of each blocking obstacle according to information of each blocking obstacle in the valid obstacle list and a set state threshold, wherein the final driving state includes a parking state and a non-parking state;

[0013] The second detection module is used to determine the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list, wherein the final detection result includes the vehicle being in the vehicle queue state and the vehicle being in the non-vehicle queue state.

[0014] According to another aspect of the present invention, the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0016] The method and system for detecting the vehicle queue state of the present invention, wherein the method includes determining the scanning range for obtaining the blocking obstacles in front of the vehicle according to the current speed of the vehicle, the set scanning time and the minimum scanning distance; generating a valid obstacle list according to the running speed of all the blocking obstacles in the scanning range; determining the final driving state of each blocking obstacle according to the information of each blocking obstacle in the valid obstacle list and the set state threshold; determining the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list. The method and system solve the problems of large data volume and high computing power caused by vehicle queue state detection based on neural network and deep learning in actual engineering, and the detection accuracy of vehicle queue reaches more than 97%, which is fast and efficient, and it is easy to design the jump of the vehicle state machine based on this detection result, which not only ensures the traffic efficiency of the vehicle, but also improves the intelligence of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0018] Figure 1 A flowchart of a method for detecting a vehicle queue state according to a preferred embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the structure of a system for detecting a vehicle queue state according to a preferred embodiment of the present invention;

[0020] Figure 3 Schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0021] Now, exemplary embodiments of the present invention are described with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely and to fully convey the scope of the present invention to those skilled in the art. The terms used in the exemplary embodiments shown in the accompanying drawings are not intended to limit the present invention. In the accompanying drawings, the same units / elements are marked with the same reference numerals.

[0022] Unless otherwise specified, the terms (including technical terms) used herein have the commonly understood meanings to those skilled in the art. In addition, it is understood that the terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0023] Exemplary Methods

[0024] Figure 1 FIG. 1 is a flow chart of a method for detecting a vehicle queue state according to a preferred embodiment of the present invention. Figure 1 As shown, the method for detecting the vehicle queuing status described in this preferred embodiment starts from step 101.

[0025] In step 101, a scanning range for acquiring blocked obstacles in front of the vehicle is determined according to the current vehicle speed, the set scanning time and the minimum scanning distance.

[0026] Preferably, determining the scanning range of the blocking obstacle in front of the vehicle according to the current vehicle speed, the set scanning time and the minimum scanning distance includes:

[0027] According to the current speed v of the vehicle and the set scanning time t y Calculate the current scanning distance d y , and its calculation formula is:

[0028] d y =v*t y

[0029] According to the current scanning distance d y and set the minimum scanning distance d min Determine the actual scanning distance d f , whose expression is:

[0030] d f =max{d y , d min}

[0031] In the Frenet coordinate system, the vertical direction starts from the current position of the vehicle to the actual scanning distance d f The end is taken as the longitudinal length. In the horizontal direction, the longitudinal length is discretized, and the left and right side boundaries of the lane are traversed for each discretized point. The minimum value from the left and right side boundaries is taken as the horizontal width.

[0032] The scanning range of the blocking obstacle in front of the vehicle in the Frenet coordinate system is determined according to the longitudinal length and the lateral width.

[0033] In this preferred embodiment, in order to determine the queue status in front of the vehicle, it is first necessary to dynamically scan the situation in front through the vehicle radar to obtain information about the blocked obstacles in front of the vehicle. Based on the configuration of different vehicles, the corresponding scanning time is set according to experience, and the current scanning distance of the vehicle is calculated by combining the scanning time with the current speed of the vehicle. Then, the current scanning distance is compared with the set minimum scanning distance, and the maximum value is selected as the actual scanning distance of the vehicle, so that the scanning range of the blocked obstacles in front of the vehicle obtained by the vehicle at the current speed is maximized, thereby providing more obstacle information for the subsequent detection of vehicle queue status information, and ensuring the accuracy of vehicle queue status detection at the source of data collection.

[0034] In step 102, a valid obstacle list is generated according to the running speeds of all blocking obstacles within the scanning range.

[0035] The generating of a valid obstacle list according to the running speeds of all blocked obstacles within the scanning range comprises:

[0036] directly adding the first blocking obstacle with a running speed of 0 within the scanning range into the initial obstacle list; and

[0037] For each second blocking obstacle whose running speed is greater than 0 within the scanning range, scanning is performed in front of the second blocking obstacle according to the set first scanning distance, and when other obstacles that block the second blocking obstacle in a lateral position within the first scanning distance are scanned, the second blocking obstacle is included in the initial obstacle list;

[0038] For the first and second blocking obstacles in the initial obstacle list, the blocking obstacles are merged according to the set obstacle merging rule according to the lateral distance and the longitudinal distance between the blocking obstacles to generate a third blocking obstacle, wherein the obstacle merging rule includes:

[0039] When at least one of the lateral distance between the two blocking obstacles is less than a set first distance threshold, and the longitudinal distance between the two blocking obstacles is less than a set second distance threshold is satisfied, the two blocking obstacles are combined as a third blocking obstacle;

[0040] A valid obstacle list is generated according to the first blocking obstacle and the second blocking obstacle excluding the third blocking obstacle in the initial obstacle list, and the third blocking obstacle.

[0041] Preferably, after generating a valid obstacle list according to the running speeds of all blocking obstacles within the scanning range, the method further comprises:

[0042] Calculate the expected safe passage width of the ego vehicle relative to each blocking obstacle in the valid obstacle list according to the ego vehicle's current speed, the set default speed and the default value of the safe passage width;

[0043] Determining a first detection result of the vehicle according to the expected safe passage width and a set passage width threshold, wherein the first detection result includes not performing vehicle queue detection and performing vehicle queue detection;

[0044] When the first detection result is that the vehicle queuing detection is not performed, the vehicle detours around the blocking obstacle and the vehicle queuing status detection ends; when the first detection result is that the vehicle queuing detection is performed, the final driving status of each blocking obstacle is determined according to the information of each blocking obstacle in the valid obstacle list and the set status threshold.

[0045] Preferably, the expected safe passage width of the vehicle relative to each blocking obstacle in the valid obstacle list is calculated according to the current vehicle speed, the set default vehicle speed and the default value of the safe passage width, and the calculation formula is:

[0046]

[0047] Where v is the current speed of the vehicle, The default value of the vehicle speed is set. The default value of the safe passage width of the vehicle relative to the blocking obstacles in the valid obstacle list. It is the expected safe passage width of the vehicle relative to the blocking obstacles in the valid obstacle list.

[0048] Preferably, the determining the first detection result of the vehicle according to the expected safe passage width and the set passage width threshold comprises:

[0049] When the expected safe passage width is not less than a set passage width threshold, determining that the first detection result is not to perform vehicle queuing detection;

[0050] When the expected safe passage width is less than a set passage width threshold, the first detection result is determined to be performing vehicle queuing detection.

[0051] In actual applications, when the vehicle finds an obstacle ahead, if the field of vision is sufficient, even if the vehicle ahead may be in a queue, it can be judged whether it can be bypassed through the data collected by itself. Therefore, after determining the scanning range for obtaining the blocked obstacles ahead of the vehicle and generating a valid obstacle list based on the running speed of all blocked obstacles within the scanning range, a more preferred method is to first detect whether the vehicle can directly bypass all obstacles ahead. If it is determined that it can be bypassed based on the analysis and calculation of the collected data, the bypass operation is directly executed without the need to collect data for the detection of the vehicle queue status, thereby greatly reducing the data processing volume of the vehicle data processing system, improving work efficiency, and further increasing the intelligence of the vehicle.

[0052] In step 103, the final driving state of each blocking obstacle is determined according to the information of each blocking obstacle in the valid obstacle list and the set state threshold, wherein the final driving state includes a parking state and a non-parking state.

[0053] The determining the final driving state of each blocking obstacle according to the information of each blocking obstacle in the valid obstacle list and the set state threshold comprises:

[0054] Determine the predicted driving state of each blocking obstacle in the current frame according to the information of each blocking obstacle in the valid obstacle list, wherein the information includes the lane type of each blocking obstacle in the current time frame, the distance from the right road boundary, the proportion of the lane occupied, and the parking angle on the lane, the predicted driving state includes a parking state and a non-parking state, when the predicted driving state is a parking state, the predicted state value is set to 1, and when the predicted driving state is a non-parking state, the predicted state value is set to 0;

[0055] For each blocking obstacle, starting from the current time frame, the predicted state values ​​of N-1 time frames adjacent to the current time frame are selected from the historical frames and the predicted state value of the current time frame are weighted averaged to determine the final state value of each blocking obstacle in the current time frame. The calculation formula is:

[0056]

[0057]

[0058] Where x is the final state value of each blocking obstacle in the current time frame, and are the weight factor and predicted state value of the i-th time frame, respectively. is the impact factor attenuation rate;

[0059] When the final state value of the blocking obstacle in the current time frame is greater than the set state threshold, it is determined that the final driving state of the blocking obstacle in the current time frame is a parking state, otherwise, it is a non-parking state.

[0060] In this preferred embodiment, in order to detect the vehicle queue status, it is necessary to first predict and judge the driving status of the blocking obstacles in the effective obstacle list. When determining the predicted driving status, it is necessary to make a comprehensive judgment on the information of the blocking obstacles, such as the distance between the vehicle and the right road boundary. There are relevant regulations requiring that the side parking distance is 30cm to the right. If it is too far from the right, it will block traffic. The roadside parked vehicles will not be too far from the right side of the road. If it is too far, it is definitely not a non-parking state; however, it is also impossible to avoid some large vehicles such as buses. The body is large and may be very close to the right side, but the proportion of the entire lane it occupies is very high. If it is greater than 0.8, it is considered not roadside parking; at the same time, the angle formed by the parking angle on the roadside and the road is large, which can also be considered abnormal, not normal roadside parking.

[0061] Since there may be calculation errors in the predicted driving state of the blocked obstacle determined by the current frame, in order to improve the accuracy of identifying the driving state of the blocked obstacle, the predicted driving state of the historical frame can be further combined, and the predicted driving state of multiple frames adjacent to the current frame can be weighted averaged through sliding window processing to determine the final driving state of the current frame.

[0062] In step 104, a final detection result of the vehicle queue state is determined according to the final driving state of each blocking obstacle in the valid obstacle list, wherein the final detection result includes the vehicle being in the vehicle queue state and the vehicle being in the non-vehicle queue state.

[0063] Preferably, the determining of the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list includes:

[0064] When there is at least one blocking obstacle in the valid obstacle list whose final driving state is a parking state, determining that the final detection result is that the vehicle is in a non-vehicle queue state;

[0065] When the final driving state of all the blocking obstacles in the valid obstacle list is a non-parking state, if the number of blocking obstacles is greater than 1, the final detection result is that the vehicle is in a vehicle queue state; if the number of blocking obstacles is equal to 1, then:

[0066] When the blocking obstacle is located in a lane other than the right lane, the final detection result is that the vehicle is in a vehicle queue state;

[0067] When the blocking obstacle is located in the right lane, then:

[0068] When a vehicle passes by in the left lane of the vehicle, the final detection result is that the vehicle is in a vehicle queue state;

[0069] When there is no vehicle passing in the left lane of the vehicle and the height of the blocking obstacle is not less than the set height threshold, if the blocking obstacle is located at the intersection, the final detection result is that the vehicle is in a vehicle queue state;

[0070] When there is no vehicle passing in the left lane of the own vehicle and the height of the blocking obstacle is less than the set height threshold, the front of the blocking obstacle is scanned according to the set second scanning distance. When other obstacles that block the blocking obstacle in a lateral position are scanned within the second scanning distance, the final driving state of the other obstacles is determined according to the collected information of the other obstacles and the set state threshold; when the final driving state of the other obstacles is a non-parking state, the final detection result is that the own vehicle is in a vehicle queuing state, otherwise, the final detection result is that the own vehicle is in a non-vehicle queuing state.

[0071] In this preferred embodiment, since there may be errors in the determination of the final driving state of a blocking obstacle, for a traffic flow formed by multiple blocking obstacles, theoretically, when the final driving state of any blocking obstacle is a parking state, the queuing detection state of the vehicle can only be a non-vehicle queuing state. Therefore, the present invention uniformly processes the final driving state of the traffic flow formed by multiple blocking obstacles. As long as there is at least one blocking obstacle in the valid obstacle list whose final driving state is a parking state, it is determined that the entire traffic flow is in a parking state, thereby further simplifying the steps of detecting the vehicle queuing state and improving the intelligence of the vehicle.

[0072] Preferably, after determining the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list, the method further includes:

[0073] When the final detection result is that the vehicle is not in a vehicle queue state, the vehicle bypasses the blocked obstacles in the valid obstacle list and makes a regression decision based on the collision time TTC principle, wherein the regression decision includes:

[0074] The lane in front of the blocked obstacle in the valid obstacle list that the vehicle is bypassing is taken as the target lane, and the blocked obstacle in the bypassing process is obtained by scanning according to the set scanning range, wherein the scanning range is a rectangle formed by the forward scanning distance, the lateral scanning distance and the backward scanning distance, and correspondingly, the blocked obstacle in the bypassing process includes the forward obstacle, the lateral obstacle and the backward obstacle;

[0075] When there is a lateral obstacle, the vehicle continues to detour and does not return to the target lane;

[0076] When there is a forward obstacle, a forward safety check is performed, where:

[0077] According to the relative speed of the vehicle and the front vehicle , the initial distance between the two vehicles , the minimum distance between the two , and the maximum deceleration a1 is set to calculate the collision time between the two , and its calculation formula is:

[0078]

[0079] The collision time The time threshold is set Compare, when ≥ , it is determined that the forward security check passes, otherwise it fails; or

[0080] Assuming that the vehicle is moving at the maximum deceleration a1 and the obstacle is moving at a constant speed, the time it takes for the vehicle to decelerate to the speed of the obstacle is the safety time. ;

[0081] When the vehicle and the obstacle ahead are within the safety time When the relative distance is less than the initial vehicle distance s, it is determined that the forward safety detection has passed, otherwise it has failed;

[0082] When there is a rearward obstacle, a rearward safety check is performed, where:

[0083] Assuming that both the ego vehicle and the rear obstacle are moving at a constant speed, according to the relative speed between the ego vehicle and the rear vehicle , the initial distance between the two vehicles , the minimum distance between the two , calculate the collision time of the two , and its calculation formula is:

[0084]

[0085] The collision time The time threshold is set Compare, when ≥ When , it is determined that the backward safety test has passed, otherwise it has failed;

[0086] If both the forward safety check and the backward safety check are passed, the vehicle returns to the target lane, otherwise it does not return to the target lane.

[0087] Since there may be blocked obstacles ahead that block the vehicle's line of sight, when the final detection result shows that the vehicle is not in a queue and attempts to make a detour, after the field of vision is expanded, it may be found that regression is required due to congestion. Therefore, it is also necessary to establish a corresponding regression strategy after determining the final detection result of the vehicle's queue status, so as to further ensure the vehicle's traffic efficiency.

[0088] The method for detecting the vehicle queue status described in this preferred embodiment identifies the obstacle in front of the vehicle, determines the final driving state of the obstacle, and determines the final detection result of the vehicle queue status based on the final driving state, thereby solving the problems of large data volume and high computing power brought about by queue detection schemes based on neural networks and deep learning. It is faster and more efficient, and it is easy to design the jump of the state machine based on this detection result, which not only ensures the traffic efficiency of the vehicle, but also improves the intelligence of the vehicle.

[0089] Exemplary Systems

[0090] Figure 2 FIG. 2 is a structural diagram of a system for detecting a vehicle queue state according to a preferred embodiment of the present invention. Figure 2 As shown, the system 200 for detecting the vehicle queue status according to the preferred embodiment includes:

[0091] The scanning range module 201 is used to determine the scanning range of the blocking obstacle in front of the vehicle according to the current vehicle speed, the set scanning time and the minimum scanning distance;

[0092] The obstacle list module 202 is used to generate a valid obstacle list according to the running speeds of all blocking obstacles within the scanning range;

[0093] A first detection module 203, configured to determine a final driving state of each blocking obstacle according to information of each blocking obstacle in the valid obstacle list and a set state threshold, wherein the final driving state includes a parking state and a non-parking state;

[0094] The second detection module 204 is used to determine the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list, wherein the final detection result includes the vehicle being in the vehicle queue state and the vehicle being in the non-vehicle queue state.

[0095] Preferably, the scanning range module 201 determines the scanning range for obtaining the blocking obstacle in front of the vehicle according to the current vehicle speed, the set scanning time and the minimum scanning distance, including:

[0096] According to the current speed v of the vehicle and the set scanning time t y Calculate the current scanning distance d y , and its calculation formula is:

[0097] d y =v*t y

[0098] According to the current scanning distance d y and set the minimum scanning distance d min Determine the actual scanning distance d f , whose expression is:

[0099] d f =max{d y , d min}

[0100] In the Frenet coordinate system, the vertical direction starts from the current position of the vehicle to the actual scanning distance d f The end is taken as the longitudinal length. In the horizontal direction, the longitudinal length is discretized, and the left and right side boundaries of the lane are traversed for each discretized point. The minimum value from the left and right side boundaries is taken as the horizontal width.

[0101] The scanning range of the blocking obstacle in front of the vehicle in the Frenet coordinate system is determined according to the longitudinal length and the lateral width.

[0102] Preferably, the obstacle list module 202 generates a valid obstacle list according to the running speeds of all blocking obstacles within the scanning range, including:

[0103] directly adding the first blocking obstacle with a running speed of 0 within the scanning range into the initial obstacle list; and

[0104] For each second blocking obstacle whose running speed is greater than 0 within the scanning range, scanning is performed in front of the second blocking obstacle according to the set first scanning distance, and when other obstacles that block the second blocking obstacle in a lateral position within the first scanning distance are scanned, the second blocking obstacle is included in the initial obstacle list;

[0105] For the first and second blocking obstacles in the initial obstacle list, the blocking obstacles are merged according to the set obstacle merging rule according to the lateral distance and the longitudinal distance between the blocking obstacles to generate a third blocking obstacle, wherein the obstacle merging rule includes:

[0106] When at least one of the lateral distance between the two blocking obstacles is less than a set first distance threshold, and the longitudinal distance between the two blocking obstacles is less than a set second distance threshold is satisfied, the two blocking obstacles are combined as a third blocking obstacle;

[0107] A valid obstacle list is generated according to the first blocking obstacle and the second blocking obstacle excluding the third blocking obstacle in the initial obstacle list, and the third blocking obstacle.

[0108] Preferably, the system further comprises a third detection module, which is used to calculate the expected safe passage width of the vehicle relative to each blocking obstacle in the valid obstacle list according to the current vehicle speed, the set default vehicle speed and the default value of the safe passage width; determine the first detection result of the vehicle according to the expected safe passage width and the set passage width threshold, wherein the first detection result includes not performing vehicle queue detection and performing vehicle queue detection;

[0109] When the first detection result is that the vehicle queue detection is not performed, the vehicle detours around the blocking obstacle and the vehicle queue status detection ends; when the first detection result is that the vehicle queue detection is performed, go to the first detection module 203.

[0110] Preferably, the third detection module calculates the expected safe passage width of the vehicle relative to each blocking obstacle in the valid obstacle list according to the current speed of the vehicle, the set default speed and the default value of the safe passage width, and the calculation formula is:

[0111]

[0112] Where v is the current speed of the vehicle, The default value of the vehicle speed is set. The default value of the safe passage width of the vehicle relative to the blocking obstacles in the valid obstacle list. It is the expected safe passage width of the vehicle relative to the blocking obstacles in the valid obstacle list.

[0113] Preferably, the third detection module determines the first detection result of the vehicle according to the expected safe passage width and the set passage width threshold, including:

[0114] When the expected safe passage width is not less than a set passage width threshold, determining that the first detection result is not to perform vehicle queuing detection;

[0115] When the expected safe passage width is less than a set passage width threshold, the first detection result is determined to be performing vehicle queuing detection.

[0116] Preferably, the first detection module 203 determines the final driving state of each blocking obstacle according to the information of each blocking obstacle in the valid obstacle list and the set state threshold, including:

[0117] Determine the predicted driving state of each blocking obstacle in the current frame according to the information of each blocking obstacle in the valid obstacle list, wherein the information includes the lane type of each blocking obstacle in the current time frame, the distance from the right road boundary, the proportion of the lane occupied, and the parking angle on the lane, the predicted driving state includes a parking state and a non-parking state, when the predicted driving state is a parking state, the predicted state value is set to 1, and when the predicted driving state is a non-parking state, the predicted state value is set to 0;

[0118] For each blocking obstacle, starting from the current time frame, the predicted state values ​​of N-1 time frames adjacent to the current time frame are selected from the historical frames and the predicted state value of the current time frame are weighted averaged to determine the final state value of each blocking obstacle in the current time frame. The calculation formula is:

[0119]

[0120]

[0121] Where x is the final state value of each blocking obstacle in the current time frame, and are the weight factor and predicted state value of the i-th time frame, respectively. is the impact factor attenuation rate;

[0122] When the final state value of the blocking obstacle in the current time frame is greater than the set state threshold, it is determined that the final driving state of the blocking obstacle in the current time frame is a parking state, otherwise, it is a non-parking state.

[0123] Preferably, the second detection module 204 determines the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list, including:

[0124] When there is at least one blocking obstacle in the valid obstacle list whose final driving state is a parking state, determining that the final detection result is that the vehicle is in a non-vehicle queue state;

[0125] When the final driving state of all the blocking obstacles in the valid obstacle list is a non-parking state, if the number of blocking obstacles is greater than 1, the final detection result is that the vehicle is in a vehicle queue state; if the number of blocking obstacles is equal to 1, then:

[0126] When the blocking obstacle is located in a lane other than the right lane, the final detection result is that the vehicle is in a vehicle queue state;

[0127] When the blocking obstacle is located in the right lane, then:

[0128] When a vehicle passes by in the left lane of the vehicle, the final detection result is that the vehicle is in a vehicle queue state;

[0129] When there is no vehicle passing in the left lane of the vehicle and the height of the blocking obstacle is not less than the set height threshold, if the blocking obstacle is located at the intersection, the final detection result is that the vehicle is in a vehicle queue state;

[0130] When there is no vehicle passing in the left lane of the own vehicle and the height of the blocking obstacle is less than the set height threshold, the front of the blocking obstacle is scanned according to the set second scanning distance. When other obstacles that block the blocking obstacle in a lateral position are scanned within the second scanning distance, the final driving state of the other obstacles is determined according to the collected information of the other obstacles and the set state threshold; when the final driving state of the other obstacles is a non-parking state, the final detection result is that the own vehicle is in a vehicle queuing state, otherwise, the final detection result is that the own vehicle is in a non-vehicle queuing state.

[0131] Preferably, the system further comprises a regression decision module, which is used for, when the final detection result is that the vehicle is in a non-vehicle queue state, causing the vehicle to bypass the blocked obstacle in the valid obstacle list and making a regression decision based on the collision time TTC principle, wherein the regression decision comprises:

[0132] The lane in front of the blocked obstacle in the valid obstacle list that the vehicle is bypassing is taken as the target lane, and the blocked obstacle in the bypassing process is obtained by scanning according to the set scanning range, wherein the scanning range is a rectangle formed by the forward scanning distance, the lateral scanning distance and the backward scanning distance, and correspondingly, the blocked obstacle in the bypassing process includes the forward obstacle, the lateral obstacle and the backward obstacle;

[0133] When there is a lateral obstacle, the vehicle continues to detour and does not return to the target lane;

[0134] When there is a forward obstacle, a forward safety check is performed, where:

[0135] According to the relative speed of the vehicle and the front vehicle , the initial distance between the two vehicles , the minimum distance between the two , and the maximum deceleration a1 is set to calculate the collision time between the two , and its calculation formula is:

[0136]

[0137] The collision time The time threshold is set Compare, when ≥ , it is determined that the forward security check passes, otherwise it fails; or

[0138] Assuming that the vehicle is moving at the maximum deceleration a1 and the obstacle is moving at a constant speed, the time it takes for the vehicle to decelerate to the speed of the obstacle is the safety time. ;

[0139] When the vehicle and the obstacle ahead are within the safety time When the relative distance is less than the initial vehicle distance s, it is determined that the forward safety detection has passed, otherwise it has failed;

[0140] When there is a rearward obstacle, a rearward safety check is performed, where:

[0141] Assuming that both the ego vehicle and the rear obstacle are moving at a constant speed, according to the relative speed between the ego vehicle and the rear vehicle , the initial distance between the two vehicles , the minimum distance between the two , calculate the collision time of the two , and its calculation formula is:

[0142]

[0143] The collision time The time threshold is set Compare, when ≥ When , it is determined that the backward safety test has passed, otherwise it has failed;

[0144] If both the forward safety check and the backward safety check are passed, the vehicle returns to the target lane, otherwise it does not return to the target lane.

[0145] The system for detecting the vehicle queue status described in this preferred embodiment has the same steps as the method for detecting the vehicle queue status in performing vehicle queue status detection, and the technical effects achieved are also the same, which will not be described in detail here.

[0146] Exemplary Electronic Devices

[0147] Figure 3 The electronic device according to the preferred embodiment of the present invention is a schematic diagram of the structure of the electronic device. The electronic device can be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device can communicate with the first device and the second device to receive the collected input signal from them. Figure 3 FIG. 1 is a block diagram of an electronic device according to an embodiment of the present disclosure. Figure 3 As shown, the electronic device includes one or more processors 301 and a memory 302 .

[0148] The processor 301 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0149] The memory 302 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may run the program instructions to implement the energy consumption anomaly diagnosis method based on the enterprise energy consumption space of the various embodiments disclosed above and / or other desired functions. In one example, the electronic device may also include: an input device 303 and an output device 304, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0150] In addition, the input device 303 may also include, for example, a keyboard, a mouse, and the like.

[0151] The output device 304 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0152] Of course, to simplify, Figure 3 Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0153] Exemplary computer program products and computer-readable storage media

[0154] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for detecting the vehicle queuing status according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0155] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0156] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the method for detecting the vehicle queuing status according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0157] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0158] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0159] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0160] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0161] The apparatus and method of the present disclosure may be implemented in many ways. For example, the apparatus and method of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0162] It should also be noted that in the apparatus, equipment and method of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present disclosure. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present disclosure. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown here, but to the widest scope consistent with the principles and novel features disclosed herein.

[0163] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for detecting a vehicle queue state, characterized in that: The method comprises: The scanning range for obtaining the blocked obstacles in front of the vehicle is determined according to the current vehicle speed, the set scanning time and the minimum scanning distance; Generate a valid obstacle list according to the running speeds of all blocked obstacles within the scanning range; Calculate the expected safe passage width of the ego vehicle relative to each blocking obstacle in the valid obstacle list according to the ego vehicle's current speed, the set default speed and the default value of the safe passage width; Determining a first detection result of the vehicle according to the expected safe passage width and a set passage width threshold, wherein the first detection result includes not performing vehicle queue detection and performing vehicle queue detection; When the first detection result is that the vehicle queue detection is not performed, the vehicle detours around the blocking obstacle and the vehicle queue state detection ends; when the first detection result is that the vehicle queue detection is performed, the final driving state of each blocking obstacle is determined according to the information of each blocking obstacle in the valid obstacle list and the set state threshold, wherein the final driving state includes a parking state and a non-parking state; The final detection result of the vehicle queue state is determined according to the final driving state of each blocking obstacle in the valid obstacle list, wherein the final detection result includes the vehicle being in the vehicle queue state and the vehicle being in the non-vehicle queue state.

2. The method according to claim 1, characterized in that The method of determining the scanning range of the blocking obstacle in front of the vehicle according to the current vehicle speed, the set scanning time and the minimum scanning distance includes: According to the current vehicle speed v and the set scanning time t y Calculate the current scanning distance d y , and its calculation formula is: d y =v*t y According to the current scanning distance d y and set the minimum scanning distance d min Determine the actual scanning distance d f , whose expression is: d f =max{d y ,d min } In the Frenet coordinate system, the vertical direction starts from the current position of the vehicle to the actual scanning distance d f The end is taken as the longitudinal length. In the horizontal direction, the longitudinal length is discretized, and the left and right side boundaries of the lane are traversed for each discretized point. The minimum value from the left and right side boundaries is taken as the horizontal width. The scanning range of the blocking obstacle in front of the vehicle in the Frenet coordinate system is determined according to the longitudinal length and the lateral width.

3. The method according to claim 1, wherein generating a valid obstacle list according to the running speeds of all blocking obstacles within the scanning range comprises: The first blocking obstacle with a running speed of 0 within the scanning range is directly included in the initial obstacle list; as well as For each second blocking obstacle whose running speed is greater than 0 within the scanning range, scanning is performed in front of the second blocking obstacle according to the set first scanning distance, and when other obstacles that block the second blocking obstacle in a lateral position within the first scanning distance are scanned, the second blocking obstacle is included in the initial obstacle list; For the first and second blocking obstacles in the initial obstacle list, the blocking obstacles are merged according to the set obstacle merging rule according to the lateral distance and the longitudinal distance between the blocking obstacles to generate a third blocking obstacle, wherein the obstacle merging rule includes: When at least one of the lateral distance between the two blocking obstacles is less than a set first distance threshold, and the longitudinal distance between the two blocking obstacles is less than a set second distance threshold is satisfied, the two blocking obstacles are combined as a third blocking obstacle; A valid obstacle list is generated according to the first blocking obstacle and the second blocking obstacle excluding the third blocking obstacle in the initial obstacle list, and the third blocking obstacle.

4. The method according to claim 1, characterized in that The expected safe passage width of the vehicle relative to each blocking obstacle in the valid obstacle list is calculated according to the current vehicle speed, the set default vehicle speed and the default value of the safe passage width, and the calculation formula is: Where v is the current speed of the vehicle, The default value of the vehicle speed is set. The default value of the safe passage width of the vehicle relative to the blocking obstacles in the valid obstacle list. It is the expected safe passage width of the vehicle relative to the blocking obstacles in the valid obstacle list.

5. The method according to claim 1, characterized in that The determining a first detection result of the vehicle according to the expected safe passage width and a set passage width threshold comprises: When the expected safe passage width is not less than a set passage width threshold, determining that the first detection result is not to perform vehicle queuing detection; When the expected safe passage width is less than a set passage width threshold, the first detection result is determined to be performing vehicle queuing detection.

6. The method according to claim 1, characterized in that The determining the final driving state of each blocking obstacle according to the information of each blocking obstacle in the valid obstacle list and the set state threshold comprises: Determine the predicted driving state of each blocking obstacle in the current frame according to the information of each blocking obstacle in the valid obstacle list, wherein the information includes the lane type of each blocking obstacle in the current time frame, the distance from the right road boundary, the proportion of the lane occupied, and the parking angle on the lane, the predicted driving state includes a parking state and a non-parking state, when the predicted driving state is a parking state, the predicted state value is set to 1, and when the predicted driving state is a non-parking state, the predicted state value is set to 0; For each blocking obstacle, starting from the current time frame, the predicted state values ​​of N-1 time frames adjacent to the current time frame are selected from the historical frames and the predicted state value of the current time frame are weighted averaged to determine the final state value of each blocking obstacle in the current time frame. The calculation formula is: Where x is the final state value of each blocking obstacle in the current time frame, and are the weight factor and predicted state value of the i-th time frame, respectively. is the impact factor attenuation rate; When the final state value of the blocking obstacle in the current time frame is greater than the set state threshold, it is determined that the final driving state of the blocking obstacle in the current time frame is a parking state, otherwise, it is a non-parking state.

7. The method according to claim 1, characterized in that The final detection result of the vehicle queue state is determined according to the final driving state of each blocking obstacle in the valid obstacle list, including: When there is at least one blocking obstacle in the valid obstacle list whose final driving state is a parking state, determining that the final detection result is that the vehicle is in a non-vehicle queue state; When the final driving state of all the blocking obstacles in the valid obstacle list is a non-parking state, if the number of blocking obstacles is greater than 1, the final detection result is that the vehicle is in a vehicle queue state; if the number of blocking obstacles is equal to 1, then: When the blocking obstacle is located in a lane other than the right lane, the final detection result is that the vehicle is in a vehicle queue state; When the blocking obstacle is located in the right lane, then: When a vehicle passes by in the left lane of the vehicle, the final detection result is that the vehicle is in a vehicle queue state; When there is no vehicle passing in the left lane of the vehicle and the height of the blocking obstacle is not less than the set height threshold, if the blocking obstacle is located at the intersection, the final detection result is that the vehicle is in a vehicle queue state; When there is no vehicle passing in the left lane of the own vehicle and the height of the blocking obstacle is less than the set height threshold, the front of the blocking obstacle is scanned according to the set second scanning distance. When other obstacles that block the blocking obstacle in a lateral position are scanned within the second scanning distance, the final driving state of the other obstacles is determined according to the collected information of the other obstacles and the set state threshold; when the final driving state of the other obstacles is a non-parking state, the final detection result is that the own vehicle is in a vehicle queuing state, otherwise, the final detection result is that the own vehicle is in a non-vehicle queuing state.

8. The method according to claim 1, characterized in that After determining the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the effective obstacle list, the method further includes: When the final detection result is that the vehicle is not in a vehicle queue state, the vehicle bypasses the blocked obstacles in the valid obstacle list and makes a regression decision based on the collision time TTC principle, wherein the regression decision includes: The lane in front of the blocked obstacle in the valid obstacle list that the vehicle is bypassing is taken as the target lane, and the blocked obstacle in the bypassing process is obtained by scanning according to the set scanning range, wherein the scanning range is a rectangle formed by the forward scanning distance, the lateral scanning distance and the backward scanning distance, and correspondingly, the blocked obstacle in the bypassing process includes the forward obstacle, the lateral obstacle and the backward obstacle; When there is a lateral obstacle, the vehicle continues to detour and does not return to the target lane; When there is a forward obstacle, a forward safety check is performed, where: According to the relative speed of the vehicle and the front vehicle , the initial distance between the two vehicles , the minimum distance between the two , and the maximum deceleration a1 is set to calculate the collision time between the two , and its calculation formula is: The collision time The time threshold is set Compare, when ≥ , it is determined that the forward security check has passed, otherwise it has failed; or Assuming that the vehicle is moving at the maximum deceleration a1 and the obstacle is moving at a constant speed, the time it takes for the vehicle to decelerate to the speed of the obstacle is the safety time. ; When the vehicle and the obstacle ahead are within the safety time When the relative distance is less than the initial vehicle distance s, it is determined that the forward safety detection has passed, otherwise it has failed; When there is a rearward obstacle, a rearward safety check is performed, where: Assuming that both the ego vehicle and the rear obstacle are moving at a constant speed, according to the relative speed between the ego vehicle and the rear vehicle , the initial distance between the two vehicles , the minimum distance between the two , calculate the collision time of the two , and its calculation formula is: The collision time The time threshold is set Compare, when ≥ When , it is determined that the backward safety test has passed, otherwise it has failed; If both the forward safety check and the backward safety check are passed, the vehicle returns to the target lane, otherwise it does not return to the target lane.

9. A system for detecting vehicle queue status information, characterized in that: The system comprises: The scanning range module is used to determine the scanning range of the blocked obstacles in front of the vehicle according to the current vehicle speed, the set scanning time and the minimum scanning distance; An obstacle list module, used to generate a valid obstacle list according to the running speeds of all blocking obstacles within the scanning range; The third detection module is used to calculate the expected safe passage width of the vehicle relative to each blocking obstacle in the valid obstacle list according to the current speed of the vehicle, the set default speed and the default value of the safe passage width; determine the first detection result of the vehicle according to the expected safe passage width and the set passage width threshold, wherein the first detection result includes not performing vehicle queue detection and performing vehicle queue detection; when the first detection result is not performing vehicle queue detection, the vehicle detours around the blocking obstacle and the vehicle queue state detection ends; when the first detection result is performing vehicle queue detection, go to the first detection module; A first detection module, configured to determine a final driving state of each blocking obstacle according to information of each blocking obstacle in the valid obstacle list and a set state threshold, wherein the final driving state includes a parking state and a non-parking state; The second detection module is used to determine the final detection result of the vehicle queue state according to the final driving state of each blocking obstacle in the valid obstacle list, wherein the final detection result includes the vehicle being in the vehicle queue state and the vehicle being in the non-vehicle queue state.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 8.

11. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 8.

Images