Safety range prompting method and system for unmanned vehicle and storage medium

Abstract

The invention relates to a safety range prompting method and system for an unmanned vehicle and a storage medium, and the method comprises the steps: W1, enabling the vehicle to run on a road, arranging a laser generator facing the ground at the top end of the unmanned vehicle, and obtaining the point cloud data information of the ground around the vehicle in real time, data information of parameters of the size of a vehicle body, data information of vehicle motion state parameters and data information of road traffic state parameters are collected; and W2, on the basis of the point cloud data information of the ground around the vehicle, the data information of the parameters of the size of the vehicle body and the data information of the motion state parameters of the vehicle, constructing a non-uniform Gaussian variation vehicle expansion range prediction model, and predicting the expansion range of the vehicle. And obtaining data information of the predicted expansion range of the vehicle. According to the method, other traffic participants are reminded of leading avoidance in actual operation, the operation environment of the automatic driving vehicle is improved, and the occurrence probability of braking faults is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned vehicle, and in particular to a safety range prompting method, system and storage medium for an unmanned vehicle. Background Art

[0002] There are more and more self-driving vehicles operating on public roads in cities, which have more intersections with surrounding social vehicles, pedestrians, various obstacles, etc. Social vehicle drivers and passers-by do not understand the internal working logic of self-driving vehicles, and naturally form a distance from self-driving vehicles based on experience or their own needs. In complex driving conditions with heavy traffic, objects or pedestrians often intrude into the expansion range of the vehicle body, causing the self-driving vehicle to brake, and they are unable to understand and execute the traffic police's instructions, aggravating traffic congestion and causing inconvenience to people's travel.

[0003] In the early stages of the development of autonomous vehicles, in order to minimize the impact on traffic, safety officers were usually deployed on board to intervene in time, release the brakes, and quickly restore traffic. Later, they transitioned to remote monitoring and intervention. Both methods are solutions proposed from the perspective of vehicle-side intervention. As more and more vehicles are put into operation in the market, the number of on-board safety officers or remote monitoring and intervention personnel is increasingly required, increasing the operating costs of each company. Summary of the invention

[0004] In view of the above problems, the present invention provides a safety range prompt method, system and storage medium for unmanned vehicles, which not only remind other traffic participants to take the lead in avoidance during actual operation, but also improve the operating environment of autonomous driving vehicles and reduce the probability of brake failure.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0006] A safety range prompting method for an unmanned vehicle, the method comprising:

[0007] W1. The vehicle is driving on the road, and a laser generator facing the ground is set on the top of the autonomous driving vehicle to obtain point cloud data information of the ground around the vehicle in real time, and collect data information of parameters of the vehicle body size, vehicle motion state parameters and road traffic state parameters;

[0008] W2. Based on the point cloud data information of the ground around the vehicle, the data information of the parameters of the vehicle body size and the data information of the vehicle motion state parameters, a vehicle expansion range prediction model of non-uniform Gaussian variation is constructed to predict the expansion range of the vehicle to obtain data information of the predicted vehicle expansion range;

[0009] W3. Based on the data information of the predicted expansion range of the vehicle and the data information of the road traffic state parameter, a collision point prediction model of the vehicle for global search is constructed to predict the collision point of the vehicle and obtain the data information of the predicted collision point of the vehicle;

[0010] W4. Based on the data information of the predicted collision point of the vehicle, a vehicle safety range warning function G is constructed to characterize the warning information of the vehicle's safety range, and obtain the warning data information of the vehicle's safety range.

[0011] Furthermore, in step W2, the vehicle expansion range prediction model of non-uniform Gaussian variation is constructed to predict the expansion range of the vehicle, including:

[0012] W21. Based on the point cloud data information of the ground around the vehicle and the data information of the parameters of the vehicle body size, establish the vehicle's periscopic function Q,

[0013]

[0014] Among them, x1 is the point cloud data information of the ground around the vehicle, x2 is the data information of the parameters of the vehicle body size, α1, α2 and α3 are differential factors, which characterize the safety boundary of the vehicle body and obtain the data information of the safety boundary of the vehicle body;

[0015] W22. Based on the data information of the safety boundary of the vehicle body and the data information of the vehicle motion state parameters, a prediction function R of the expansion range of the non-uniform Gaussian variation of the vehicle is established.

[0016]

[0017] Among them, y1 is the data information of the safety boundary of the vehicle body, y2 is the data information of the vehicle motion state parameters, β1, β2 and β3 are Gaussian variation factors;

[0018] W23. Based on the prediction function R of the expansion range of the non-uniform Gaussian variation of the vehicle, the expansion range of the vehicle is predicted to obtain data information of the predicted expansion range of the vehicle.

[0019] Furthermore, the Gaussian variation factors β1, β2 and β3 are,

[0020]

[0021] Among them, y1 is the data information of the safety boundary of the vehicle body, and y2 is the data information of the vehicle motion state parameters.

[0022] Furthermore, the constraints of the difference factors α1, α2 and α3 are:

[0023]

[0024] Furthermore, in step W3, the construction of a global search-oriented adaptive vehicle collision point prediction model to predict the collision point of the vehicle includes:

[0025] W31. Based on the predicted expansion range of the vehicle and the road traffic state parameter data information, establish the superposition function P of the expansion range of the vehicle and the road traffic state,

[0026]

[0027] Among them, z1 is the data information of the predicted expansion range of the vehicle, z2 is the data information of the road traffic state parameter, δ1, δ2 and δ3 are the penalty coefficients of the expansion range of the vehicle and the road traffic state, and the overlap degree between the collision range of the vehicle and the road traffic state is calculated to obtain the data information of the overlap degree between the collision range of the vehicle and the road traffic state;

[0028] W32. Based on the data information of the overlap degree between the collision range of the vehicle and the road traffic state, a collision point prediction function S of the vehicle is established.

[0029]

[0030] Among them, r is the data information of the overlap degree between the collision range of the vehicle and the road traffic state, γ1, γ2 and γ3 are the adaptive adjustment factors of the global search of the collision point of the vehicle;

[0031] W33. Based on the collision point prediction function S of the vehicle, the collision point of the vehicle is predicted to obtain data information of the predicted collision point of the vehicle.

[0032] Furthermore, the adaptive adjustment factors γ1, γ2 and γ3 of the global search of the collision point of the vehicle are,

[0033]

[0034] Among them, r is the data information of the overlap degree between the collision range of the vehicle and the road traffic status.

[0035] Furthermore, the vehicle's safety range prompt function G is:

[0036]

[0037] Among them, h is the data information of the predicted collision point of the vehicle, and η1, η2 and η3 are the safety range prompt factors of the vehicle.

[0038] Furthermore, the constraint function f of the vehicle's safety range prompt factors η1, η2 and η3 is,

[0039]

[0040] The value range of the constraint function f is (0,1).

[0041] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a safety range prompt system for an unmanned vehicle, including a computer device, which is programmed or configured to execute the steps of any one of the safety range prompt methods for an unmanned vehicle.

[0042] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the safety range prompt methods for unmanned vehicles.

[0043] The present invention has the following positive effects:

[0044] 1. The present invention predicts the collision point of the vehicle by constructing a vehicle expansion range prediction model with non-uniform Gaussian variation and combining it with a collision point prediction model for adaptive vehicles for global search. It can not only accurately predict the collision point of the vehicle, but also after the autonomous driving vehicle is stopped by social vehicles and pedestrians, the social vehicle drivers and pedestrians can judge by themselves through the prompt box how to make the autonomous driving vehicle resume normal driving to avoid traffic jams.

[0045] 2. The present invention constructs a vehicle safety range prompt function G to characterize the warning information of the vehicle's safety range, which not only reminds other traffic participants to take the lead in avoidance during actual operation, but also improves the operating environment of the autonomous driving vehicle and reduces the probability of braking failure. At the same time, it reduces on-site manpower, saves labor costs, and prevents social vehicles and pedestrians from braking the autonomous driving vehicle due to lack of understanding of the autonomous driving vehicle, causing traffic jams. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0047] Figure 2 A schematic diagram of a process for constructing a vehicle expansion range prediction model with non-uniform Gaussian variation according to the present invention;

[0048] Figure 3 The present invention is a flow chart of constructing a global search-oriented adaptive vehicle collision point prediction model. DETAILED DESCRIPTION

[0049] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0050] Example 1: Figure 1 As shown, a safety range prompting method for an unmanned vehicle, the method comprising:

[0051] W1. The vehicle is driving on the road, and a laser generator facing the ground is set on the top of the autonomous driving vehicle to obtain point cloud data information of the ground around the vehicle in real time, and collect data information of parameters of the vehicle body size, vehicle motion state parameters and road traffic state parameters;

[0052] W2. Based on the point cloud data information of the ground around the vehicle, the data information of the parameters of the vehicle body size and the data information of the vehicle motion state parameters, a vehicle expansion range prediction model of non-uniform Gaussian variation is constructed to predict the expansion range of the vehicle to obtain data information of the predicted vehicle expansion range;

[0053] W3. Based on the data information of the predicted expansion range of the vehicle and the data information of the road traffic state parameter, a collision point prediction model of the vehicle for global search is constructed to predict the collision point of the vehicle and obtain the data information of the predicted collision point of the vehicle;

[0054] W4. Based on the data information of the predicted collision point of the vehicle, a vehicle safety range warning function G is constructed to characterize the warning information of the vehicle's safety range, and obtain the warning data information of the vehicle's safety range.

[0055] In this embodiment, if Figure 2 As shown, in step W2, the vehicle expansion range prediction model of non-uniform Gaussian variation is constructed to predict the expansion range of the vehicle, including:

[0056] W21. Based on the point cloud data information of the ground around the vehicle and the data information of the parameters of the vehicle body size, establish the vehicle's periscopic function Q,

[0057]

[0058] Among them, x1 is the point cloud data information of the ground around the vehicle, x2 is the data information of the parameters of the vehicle body size, α1, α2 and α3 are differential factors, which characterize the safety boundary of the vehicle body and obtain the data information of the safety boundary of the vehicle body;

[0059] W22. Based on the data information of the safety boundary of the vehicle body and the data information of the vehicle motion state parameters, a prediction function R of the expansion range of the non-uniform Gaussian variation of the vehicle is established.

[0060]

[0061] Among them, y1 is the data information of the safety boundary of the vehicle body, y2 is the data information of the vehicle motion state parameters, β1, β2 and β3 are Gaussian variation factors;

[0062] W23. Based on the prediction function R of the expansion range of the non-uniform Gaussian variation of the vehicle, the expansion range of the vehicle is predicted to obtain data information of the predicted expansion range of the vehicle.

[0063] In this embodiment, the Gaussian variation factors β1, β2 and β3 are,

[0064]

[0065]

[0066] Among them, y1 is the data information of the safety boundary of the vehicle body, and y2 is the data information of the vehicle motion state parameters.

[0067] In this embodiment, the constraints of the difference factors α1, α2 and α3 are:

[0068]

[0069] In this embodiment, if Figure 3 As shown, in step W3, the construction of a global search-oriented adaptive vehicle collision point prediction model to predict the collision point of the vehicle includes:

[0070] W31. Based on the predicted expansion range of the vehicle and the road traffic state parameter data information, establish the superposition function P of the expansion range of the vehicle and the road traffic state,

[0071]

[0072] Among them, z1 is the data information of the predicted expansion range of the vehicle, z2 is the data information of the road traffic state parameter, δ1, δ2 and δ3 are the penalty coefficients of the expansion range of the vehicle and the road traffic state, and the overlap degree between the collision range of the vehicle and the road traffic state is calculated to obtain the data information of the overlap degree between the collision range of the vehicle and the road traffic state;

[0073] W32. Based on the data information of the overlap degree between the collision range of the vehicle and the road traffic state, a collision point prediction function S of the vehicle is established.

[0074]

[0075] Among them, r is the data information of the overlap degree between the collision range of the vehicle and the road traffic state, γ1, γ2 and γ3 are the adaptive adjustment factors of the global search of the collision point of the vehicle;

[0076] W33. Based on the collision point prediction function S of the vehicle, the collision point of the vehicle is predicted to obtain data information of the predicted collision point of the vehicle.

[0077] In this embodiment, the adaptive adjustment factors γ1, γ2 and γ3 of the global search of the collision point of the vehicle are,

[0078]

[0079] Among them, r is the data information of the overlap degree between the collision range of the vehicle and the road traffic status.

[0080] Real-time Example 2: Based on the safety range prompting method for an unmanned vehicle in Example 1, the present invention is further illustrated and described below.

[0081] like Figure 1 As shown, a safety range prompting method for an unmanned vehicle, the method comprising:

[0082] W1. The vehicle is driving on the road, and a laser generator facing the ground is set on the top of the autonomous driving vehicle to obtain point cloud data information of the ground around the vehicle in real time, and collect data information of parameters of the vehicle body size, vehicle motion state parameters and road traffic state parameters;

[0083] W2. Based on the point cloud data information of the ground around the vehicle, the data information of the parameters of the vehicle body size and the data information of the vehicle motion state parameters, a vehicle expansion range prediction model of non-uniform Gaussian variation is constructed to predict the expansion range of the vehicle to obtain data information of the predicted vehicle expansion range;

[0084] W3. Based on the data information of the predicted expansion range of the vehicle and the data information of the road traffic state parameter, a collision point prediction model of the vehicle for global search is constructed to predict the collision point of the vehicle and obtain the data information of the predicted collision point of the vehicle;

[0085] W4. Based on the data information of the predicted collision point of the vehicle, a vehicle safety range warning function G is constructed to characterize the warning information of the vehicle's safety range, and obtain the warning data information of the vehicle's safety range.

[0086] In this embodiment, the vehicle safety range prompt function G is:

[0087]

[0088] Among them, h is the data information of the predicted collision point of the vehicle, and η1, η2 and η3 are the safety range prompt factors of the vehicle.

[0089] In this embodiment, the constraint function f of the vehicle's safety range prompt factors η1, η2 and η3 is,

[0090]

[0091] The value range of the constraint function f is (0,1).

[0092] In this embodiment, the present invention provides a safety range prompt system for an unmanned vehicle, including a computer device, which is programmed or configured to execute the steps of any one of the safety range prompt methods for an unmanned vehicle.

[0093] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the safety range prompting methods for an unmanned vehicle.

[0094] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0095] In this embodiment, after the autonomous driving vehicle brakes to a stop due to the intrusion of an obstacle within the expansion range, the safety officer on the vehicle and the surrounding social vehicle drivers and passers-by are more intuitively reminded of the reason why the vehicle brakes to a stop; after the social vehicle drivers and passers-by intrude into the expansion range of the autonomous driving vehicle and cause the vehicle to brake to a stop, they can intuitively understand how far they should evacuate to exit the vehicle's expansion range so that the autonomous driving vehicle can resume normal driving; and a safe distance for active avoidance is provided to other traffic participants to reduce the chance of braking.

[0096] In this embodiment, a laser generator is arranged on the top of the autonomous driving vehicle and faces the ground, and a frame surrounding the vehicle is formed on the ground by laser irradiation.

[0097] In this embodiment, the movable shaft is used to adjust the angle between the laser generator and the ground to ensure that after the expansion range-related parameters of the autonomous driving vehicle are modified during testing and operation, the size of the box formed by the laser generator irradiating the ground can be synchronously adjusted to be consistent with the expansion range of the vehicle.

[0098] In summary, the present invention not only reminds other traffic participants to take the lead in avoiding the vehicle during actual operation, but also improves the operating environment of the autonomous driving vehicle and reduces the probability of brake failure.

[0099] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A safety range prompting method for an unmanned vehicle, characterized in that: The method comprises: W1. The vehicle is driving on the road, and a laser generator facing the ground is set on the top of the autonomous driving vehicle to obtain point cloud data information of the ground around the vehicle in real time, and collect data information of parameters of the vehicle body size, vehicle motion state parameters and road traffic state parameters; W2. Based on the point cloud data information of the ground around the vehicle, the data information of the parameters of the vehicle body size and the data information of the vehicle motion state parameters, a vehicle expansion range prediction model of non-uniform Gaussian variation is constructed to predict the expansion range of the vehicle to obtain data information of the predicted vehicle expansion range; W3. Based on the data information of the predicted expansion range of the vehicle and the data information of the road traffic state parameter, a collision point prediction model of the vehicle for global search is constructed to predict the collision point of the vehicle and obtain the data information of the predicted collision point of the vehicle; W4. Based on the data information of the predicted collision point of the vehicle, a vehicle safety range warning function G is constructed to characterize the warning information of the vehicle's safety range, and obtain the warning data information of the vehicle's safety range.

2. The safety range prompting method for an unmanned vehicle according to claim 1, characterized in that: In step W2, the construction of a vehicle expansion range prediction model with non-uniform Gaussian variation to predict the expansion range of the vehicle includes: W21. Based on the point cloud data information of the ground around the vehicle and the data information of the parameters of the vehicle body size, establish the vehicle's periscopic function Q, Among them, x1 is the point cloud data information of the ground around the vehicle, x2 is the data information of the parameters of the vehicle body size, α1, α2 and α3 are differential factors, which characterize the safety boundary of the vehicle body and obtain the data information of the safety boundary of the vehicle body; W22. Based on the data information of the safety boundary of the vehicle body and the data information of the vehicle motion state parameters, a prediction function R of the expansion range of the non-uniform Gaussian variation of the vehicle is established. Among them, y1 is the data information of the safety boundary of the vehicle body, y2 is the data information of the vehicle motion state parameters, β1, β2 and β3 are Gaussian variation factors; W23. Based on the prediction function R of the expansion range of the non-uniform Gaussian variation of the vehicle, the expansion range of the vehicle is predicted to obtain data information of the predicted expansion range of the vehicle.

3. The safety range prompting method for an unmanned vehicle according to claim 2, characterized in that: The Gaussian variation factors β1, β2 and β3 are, Among them, y1 is the data information of the safety boundary of the vehicle body, and y2 is the data information of the vehicle motion state parameters.

4. The safety range prompting method for an unmanned vehicle according to claim 2, characterized in that: The constraints of the difference factors α1, α2 and α3 are:

5. The safety range prompting method for an unmanned vehicle according to claim 1, characterized in that: In step W3, the construction of a global search-oriented adaptive vehicle collision point prediction model to predict the collision point of the vehicle includes: W31. Based on the predicted expansion range of the vehicle and the road traffic state parameter data information, establish the superposition function P of the expansion range of the vehicle and the road traffic state, Among them, z1 is the data information of the predicted expansion range of the vehicle, z2 is the data information of the road traffic state parameter, δ1, δ2 and δ3 are the penalty coefficients of the expansion range of the vehicle and the road traffic state, and the overlap degree between the collision range of the vehicle and the road traffic state is calculated to obtain the data information of the overlap degree between the collision range of the vehicle and the road traffic state; W32. Based on the data information of the overlap degree between the collision range of the vehicle and the road traffic state, a collision point prediction function S of the vehicle is established. Among them, r is the data information of the overlap degree between the collision range of the vehicle and the road traffic state, γ1, γ2 and γ3 are the adaptive adjustment factors of the global search of the collision point of the vehicle; W33. Based on the collision point prediction function S of the vehicle, the collision point of the vehicle is predicted to obtain data information of the predicted collision point of the vehicle.

6. The safety range prompting method for an unmanned vehicle according to claim 5, characterized in that: The adaptive adjustment factors γ1, γ2 and γ3 of the global search for the collision point of the vehicle are, Among them, r is the data information of the overlap degree between the collision range of the vehicle and the road traffic status.

7. The safety range prompting method for an unmanned vehicle according to claim 1, characterized in that: The safety range prompt function G of the vehicle is: Among them, h is the data information of the predicted collision point of the vehicle, and η1, η2 and η3 are the safety range prompt factors of the vehicle.

8. The safety range prompting method for an unmanned vehicle according to claim 7, characterized in that: The constraint function f of the vehicle's safety range prompt factors η1, η2 and η3 is, The value range of the constraint function f is (0,1).

9. A safety range prompting system for an unmanned vehicle, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the safety range prompt method for an unmanned vehicle as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the safety range prompt method for an unmanned vehicle as described in any one of claims 1 to 8.

Images