A driving assistance method, vehicle, computer and storage medium based on V2X perception fusion technology

Abstract

The present invention relates to the field of autonomous driving technology, and in particular to a driving assistance method, a vehicle, a computer and a storage medium based on V2X perception fusion technology; through the assistance method of the present application, when a vehicle merges into a main road from a ramp, the main vehicle's own prediction replaces the driver's advance observation of the main road's road conditions and makes a prediction in advance, and can slow down or stop to avoid target vehicles on the main road, and can also issue a warning, thereby avoiding a traffic accident caused by a vehicle collision due to the driver's inattention and failure to timely and effectively predict the collision risk.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a driving assistance method, a vehicle, a computer and a storage medium based on V2X perception fusion technology. Background Art

[0002] In the field of intelligent connected vehicles, the integration of vehicles, roads and smart cities is the current cross-industry development trend. The development and maturity of the "intelligence" + "connectivity" + "big data" cloud platform technology is the technical foundation and guarantee for realizing "smart car +".

[0003] Intelligent driving technology is one of the core technical fields of intelligent connected vehicles. Among them, environmental perception and control decision-making are the core technical bottlenecks of intelligent driving systems. At present, in the field of intelligent driving technology, the system's environmental perception capability is far from mature, which is the bottleneck among technical bottlenecks and the key constraint on the realization of intelligent driving. Single-vehicle perception (on-board sensors) and vehicle-road collaboration (V2X) each have their limitations. Only the combination of the two can achieve breakthroughs and leaps in intelligent perception technology, which is the most feasible system solution and technical route and direction for intelligent driving. In other words, to realize the environmental perception capability that empowers automobile intelligent driving, it is necessary to integrate on-board sensors and vehicle-road collaborative information technology, thereby greatly enhancing the perception capability of the automobile, and ultimately achieving a significant enhancement of the function, performance, safety and reliability of automobile intelligent driving. At the same time, the popularization of vehicle-road collaborative applications can greatly reduce the cost of single-vehicle intelligent perception.

[0004] Developing intelligent connected vehicles based on vehicle-road collaboration, realizing intelligent driving technology, and solving super-complex and changeable scene problems is a long road and process. Although achieving fully automatic driving is the development direction of intelligent connected vehicle technology, this is a long-term goal, and there is still a long way to go to achieve widespread commercial application. Market demand is the decisive factor in promoting technological progress and implementation. Recently, the industry has begun to reach a consensus that solving driving safety, traffic congestion, and improving traffic efficiency in key dangerous scenes through V2X technology is the most important market demand, and it is also the biggest pain point for safe driving in transportation. This is a problem that needs to be gradually solved in the next few decades. In other words, solving driving safety problems in key dangerous scenes is the most critical goal at present, and promoting the industrialization of technology.

[0005] ADAS is a typical driver assistance system for solving driving safety, and is also the technical basis for realizing autonomous driving. It has been developing rapidly recently and has a huge market. However, although ADAS system products have been used in the market for many years, its technology is far from mature, and the functions and performance of ADAS are also severely restricted by the system's perception capabilities. Especially in some special dangerous scenarios, ADAS cannot achieve effective collision avoidance functions. Through V2X technology, the vehicle-mounted system and roadside perception information can achieve fusion perception, which can break through the technical bottlenecks of the system in perception and decision-making algorithms in some high-risk scenarios, and develop ADAS+ systems with expanded functions and enhanced performance. The purpose of this technical invention is to solve one of the high-risk scenarios that traditional ADAS system technology cannot solve, that is, the driving assistance control decision technology of the advanced driver assistance system (ADAS+) based on V2X perception fusion technology in the scenario where the front vehicle suddenly cuts in.

[0006] Safe driving is the first rigid demand of car users. During driving, vehicle collision is the main factor causing traffic accidents. For example, when a vehicle merges into the main road from a ramp, the driver needs to observe the road conditions of the main road in advance, make predictions in advance, slow down or stop to avoid vehicles on the main road. Once the driver is not focused and fails to predict the collision risk in time and effectively, it will lead to vehicle collision and traffic accidents.

[0007] Although existing technologies attempt to solve this problem, such as traditional assisted driving systems such as forward collision warning (FCW) and emergency braking assistance (AEB), traditional assisted driving systems generally use sensors such as cameras or millimeter waves. Due to physical factors such as sensor detection angle and detection range, as well as limitations of existing target behavior prediction algorithms, the system can only detect target vehicles within a limited range, and the ability to predict risks is greatly reduced.

[0008] In short, there are many core technology bottlenecks in realizing intelligent driving. Among them, environmental perception technology and vehicle control strategy are the core of the core, and are also the constraints on the implementation of intelligent driving systems. Summary of the invention

[0009] The technical problem to be solved by the present invention is to provide a driving assistance method, a vehicle, a computer and a storage medium based on V2X perception fusion technology to reduce the risk of ramp merging.

[0010] In order to solve the above technical problems, the first technical solution adopted by the present invention is:

[0011] A driving assistance method based on V2X perception fusion technology, comprising:

[0012] Step 1: After the main vehicle enters the ramp merging scene, it is determined whether there is a target vehicle on the far right side of the main road. If not, it is recorded as event A and the vehicle is driven normally. If so, it is determined whether the main vehicle reaches the collision point first. If so, it is determined whether the main vehicle satisfies the conditions that TTC is greater than the first preset value and THW is greater than the first set threshold after entering the main road. If so, it is recorded as event C and the vehicle is driven normally. If not, step 2 is executed. If the main vehicle fails to reach the collision point first, it is predicted whether the main vehicle satisfies the conditions that TTC is greater than the first preset value and THW is greater than the second set threshold after entering the main road. If so, it is recorded as event B and the vehicle is driven normally. If not, step 2 is executed.

[0013] Step 2: Determine whether the distance between the safety line and the main vehicle is less than the third set threshold value of emergency braking. If so, emergency braking is performed and step 3 is executed. If not, determine whether the distance between the safety line and the main vehicle is less than the fourth set threshold value of gentle braking. If so, gentle braking is performed and step 3 is executed. If not, determine whether the distance between the safety line and the main vehicle is less than the fifth set threshold value of early warning. If not, normal driving is performed. If so, early warning is performed and step 3 is executed.

[0014] Step 3: When at least one of event A, event B, and event C is satisfied, the system exits the alarm or brakes. If the main vehicle has stopped, the driver is reminded to drive into the main road in time.

[0015] The TTC is the time between the main vehicle and the target vehicle. If the main vehicle reaches the collision point first, the calculation formula of TTC is:

[0016]

[0017] If the main vehicle fails to reach the collision point first, the TTC calculation formula is:

[0018]

[0019] THW is the headway time, and the calculation formula is:

[0020]

[0021] Among them, v SV is the driving speed of the main vehicle; v T is the speed of the target vehicle; a SV is the acceleration of the main vehicle; a T is the acceleration of the target vehicle; d R The distance between the main vehicle and the target vehicle after it enters the main road.

[0022] Furthermore, the third set threshold D stop The calculation formula is:

[0023]

[0024] Among them, t RBR Braking system response time.

[0025] Furthermore, the fourth set threshold d stop The calculation formula is:

[0026]

[0027] Among them, t SVD The driver's reaction time.

[0028] Furthermore, the determination of whether the main vehicle reaches the collision point first further includes:

[0029] First determine the time T1 when the target vehicle reaches the collision point, and the calculation formula is

[0030]

[0031] Among them, d T is the distance from the target vehicle to the collision point;

[0032] Determine the time T2 when the main vehicle reaches the collision point, and the calculation formula is:

[0033]

[0034] Among them, d S is the distance from the main vehicle to the collision point;

[0035] If T1 is greater than or equal to T2, the host vehicle reaches the collision point first, otherwise the target vehicle reaches the collision point first.

[0036] Furthermore, the first set threshold is 4.4s.

[0037] Furthermore, the second set threshold is 1.2s.

[0038] Furthermore, if there are multiple target vehicles, each target vehicle is judged.

[0039] In order to solve the above technical problems, the second technical solution adopted by the present invention is:

[0040] A vehicle includes a controller, wherein the controller executes the above-mentioned driving assistance method based on V2X perception fusion technology.

[0041] In order to solve the above technical problems, the third technical solution adopted by the present invention is:

[0042] A computer comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned driving assistance method based on V2X perception fusion technology when executing the computer program.

[0043] In order to solve the above technical problems, the fourth technical solution adopted by the present invention is:

[0044] A storage medium is computer-readable and stores a computer program, and when the computer program is executed by a processor, the driving assistance method based on V2X perception fusion technology as described above is implemented.

[0045] The beneficial effect of the present invention is that through the auxiliary method of the present application, when a vehicle merges into the main road from the ramp, the main vehicle's own prediction replaces the driver's advance observation of the main road's road condition and makes a prediction in advance, and can slow down or stop to avoid the target vehicle on the main road, and can also issue a warning, avoiding a traffic accident caused by a vehicle collision if the driver is not paying attention and fails to predict the collision risk in a timely and effective manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is an application scenario diagram of a driving assistance method based on V2X perception fusion technology in a specific implementation mode of the present invention;

[0047] Figure 2 A system diagram of various participating entities when applying a driving assistance method based on V2X perception fusion technology in a specific embodiment of the present invention;

[0048] Figure 3 This is a logic control diagram of a main vehicle of a driving assistance method based on V2X perception fusion technology in a specific implementation manner of the present invention (& in the figure means and, TBD in the figure means to be determined, i.e., the corresponding first preset value and second preset value). DETAILED DESCRIPTION

[0049] In order to explain the technical content, achieved objectives and effects of the present invention in detail, the following is an explanation in combination with the implementation modes and the accompanying drawings.

[0050] Please refer to Figures 1 to 3 , a driving assistance method based on V2X perception fusion technology, including

[0051] Step 1: After the main vehicle enters the ramp merging scene, it is determined whether there is a target vehicle on the far right side of the main road. If not, it is recorded as event A and the vehicle is driven normally. If so, it is determined whether the main vehicle reaches the collision point first. If so, it is determined whether the main vehicle satisfies the conditions that TTC is greater than the first preset value and THW is greater than the first set threshold after entering the main road. If so, it is recorded as event C and the vehicle is driven normally. If not, step 2 is executed. If the main vehicle fails to reach the collision point first, it is predicted whether the main vehicle satisfies the conditions that TTC is greater than the first preset value and THW is greater than the second set threshold after entering the main road. If so, it is recorded as event B and the vehicle is driven normally. If not, step 2 is executed.

[0052] Step 2: Determine whether the distance between the safety line and the main vehicle is less than the third set threshold value of emergency braking. If so, emergency braking is performed and step 3 is executed. If not, determine whether the distance between the safety line and the main vehicle is less than the fourth set threshold value of gentle braking. If so, gentle braking is performed and step 3 is executed. If not, determine whether the distance between the safety line and the main vehicle is less than the fifth set threshold value of early warning. If not, normal driving is performed. If so, early warning is performed and step 3 is executed.

[0053] Step 3: When at least one of event A, event B, and event C is satisfied, the system exits the alarm or brakes. If the main vehicle has stopped, the driver is reminded to drive into the main road in time.

[0054] The TTC is the time between the main vehicle and the target vehicle. If the main vehicle reaches the collision point first, the calculation formula of TTC is:

[0055]

[0056] If the main vehicle fails to reach the collision point first, the TTC calculation formula is:

[0057]

[0058] THW is the headway time, and the calculation formula is:

[0059]

[0060] Among them, v SV is the driving speed of the main vehicle; v T is the speed of the target vehicle; a SV is the acceleration of the main vehicle; a T is the acceleration of the target vehicle; d R It is the distance between the vehicle and the target vehicle after it enters the main road.

[0061] From the above description, it can be seen that through the auxiliary method of the present application, when a vehicle merges into the main road from the ramp, the main vehicle's own prediction replaces the driver's observation of the main road's road conditions and makes a prediction in advance. It can slow down or stop to avoid the target vehicle on the main road, and can also issue a warning, avoiding the possibility that the driver is not paying attention and fails to predict the collision risk in a timely and effective manner, which will lead to a traffic accident caused by a vehicle collision.

[0062] Furthermore, the third set threshold D stop The calculation formula is:

[0063]

[0064] Among them, t RBR Braking system response time.

[0065] Furthermore, the fourth set threshold d stop The calculation formula is:

[0066]

[0067] Among them, t SVD The driver's reaction time.

[0068] Furthermore, the determination of whether the main vehicle reaches the collision point first further includes:

[0069] First determine the time T1 when the target vehicle reaches the collision point, and the calculation formula is

[0070]

[0071] Among them, d T is the distance from the target vehicle to the collision point;

[0072] Determine the time T2 when the main vehicle reaches the collision point, and the calculation formula is:

[0073]

[0074] Among them, d S is the distance from the main vehicle to the collision point;

[0075] If T1 is greater than or equal to T2, the host vehicle reaches the collision point first, otherwise the target vehicle reaches the collision point first.

[0076] Furthermore, the first set threshold is 4.4s.

[0077] Furthermore, the second set threshold is 1.2s.

[0078] Furthermore, if there are multiple target vehicles, each target vehicle is judged.

[0079] A vehicle includes a controller, wherein the controller executes the above-mentioned driving assistance method based on V2X perception fusion technology.

[0080] A computer comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the driving assistance method based on V2X perception fusion technology as described above when executing the computer program.

[0081] A storage medium is computer-readable and stores a computer program, and when the computer program is executed by a processor, the driving assistance method based on V2X perception fusion technology as described above is implemented.

[0082] Embodiment 1

[0083] A driving assistance method based on V2X perception fusion technology,

[0084] Use scene reference Figure 1 ;

[0085] System diagram reference for each participant Figure 2 ;

[0086] Reference to the logic control diagram of the main vehicle Figure 3 ,

[0087] To facilitate the explanation of the situation assessment and decision-making logic of the ramp merging scenario, the relevant parameters are defined as follows:

[0088] The speed of the rightmost vehicle on the main road (hereinafter referred to as the target vehicle) is v T ;

[0089] The intersection point of the driving direction of the main vehicle SV and the driving direction of the target vehicle is the collision point O;

[0090] The distance d from the target vehicle to the collision point O T ;

[0091] The target vehicle acceleration is a T ;

[0092] The main vehicle's speed is v SV ;

[0093] The distance between the main vehicle and the safety line (the intersection of the right lane line of the rightmost lane of the main road and the ramp) is d p ;

[0094] The acceleration of the main vehicle is a SV ;

[0095] The distance ds from the main vehicle to the collision point O;

[0096] The driver's reaction time is t SVD , the response time of the main vehicle braking system is t RBR .

[0097] ① Based on the fusion perception results of V2I information, V2V information, main vehicle camera information, forward millimeter-wave radar information, and side angle radar information, determine whether there is a flag of the target vehicle in the rightmost lane of the main road near the scene. If there is no target vehicle, the main vehicle can merge into the main road normally, otherwise, make further risk logic judgment.

[0098] ② If there is a target vehicle in the right lane of the main road, further determine whether there is a risk of collision between the main vehicle and the main vehicle during and after the merging according to the movement and position relationship between the target vehicle and the main vehicle. To this end, first determine the time relationship between the target vehicle and the main vehicle arriving at the collision point O. The calculation formula for the time T1 of the target vehicle arriving at point O is as follows:

[0099]

[0100] The calculation formula for the time T2 of the host vehicle reaching point O is as follows:

[0101]

[0102] If T1 ≥ T2, it means that the host vehicle arrives at the collision point first; otherwise, the target vehicle arrives at the collision point first. If the host vehicle arrives at the collision point first, after the host vehicle enters the main lane, whether there is a collision risk for the target vehicle as the following vehicle to the host vehicle depends on their relative motion relationship and relative position relationship. However, since the logical relationship between the speeds of the target vehicle and the host vehicle is unknown, the TTC and THW (time headway) are used to jointly predict the degree of interference of the host vehicle to the target vehicle after entering the main lane without deceleration:

[0103]

[0104] where d R is the distance between the vehicle and the target vehicle after entering the main lane. If this value is positive, it means that after reaching point O, the host vehicle is in front of the target vehicle; otherwise, the host vehicle is behind the target vehicle. Its calculation formula is as follows:

[0105] d R =d T -T2*v T (3.5)

[0106] When TTC is greater than the set threshold (default is 4.4 s) and THW is greater than the set threshold (default is 1.2 s), it is considered that there is no collision risk between the two, and the host vehicle can merge into the main lane normally; otherwise, there is a collision risk.

[0107] If T1 < T2, it means that the target vehicle arrives at the collision point first. Considering the influence of sensor delay error, measurement error, calculation error, etc., for the case where the target vehicle arrives at the collision point first, it cannot be fully guaranteed that there is no collision risk between the two. Therefore, it is necessary to ensure that when the host vehicle enters the main lane, the target vehicle has traveled a certain distance. Similarly, the TTC and THW are used together to characterize the level of collision risk between the two:

[0108]

[0109] When TTC is greater than the set threshold (default is 4.4 s) and THW is greater than the set threshold (default is 1.2 s), it is considered that there is no collision risk between the two, and the host vehicle can merge into the main lane normally; otherwise, there is a collision risk.

[0110] ③ When there is a risk of collision between the main vehicle and the target vehicle, the degree of deceleration of the main vehicle is controlled according to the degree of collision risk. Therefore, the risk level of collision is determined according to the distance between the main vehicle and the safety line.

[0111] a) The system will first determine whether the main vehicle is in a very emergency state. If human intervention cannot avoid a collision, the system will automatically intervene to avoid or mitigate the collision through strong emergency braking. Set the system emergency braking trigger threshold. When the distance d between the main vehicle and the safety line is p When the emergency braking trigger threshold is less than the emergency braking trigger threshold, the emergency braking is initiated immediately. The emergency braking threshold calculation formula is as follows:

[0112]

[0113] b) Secondly, the system will determine whether the main vehicle is in a relatively urgent state. At this time, the system will remind the driver by slow braking, expecting the driver to take over the vehicle actively. p When it is less than the mild braking trigger threshold, mild braking is initiated. The calculation formula of mild braking threshold is the same as emergency braking, the difference is that a SV The value of is consistent with that of the zebra crossing scene.

[0114] c) At the end of this stage, the system will determine whether the vehicle is in a potential risk state. At this time, the system mainly uses sound and visual reminders. p When it is less than the warning trigger threshold, the warning function is activated. The calculation formula of the warning threshold is as follows:

[0115]

[0116] ④ When at least one of the following events is met: A (the target vehicle does not exist), B (the main vehicle arrives at the collision point later and has maintained a certain safe distance from the target vehicle), or C (the main vehicle arrives at the collision point first and has maintained a certain safe distance from the target vehicle), the system will exit the alarm or brake. If the main vehicle is already in a braked state, the driver will be reminded to enter the main lane in time through the instrument or sound.

[0117] In addition, when there are multiple target vehicles, each target vehicle must be judged for safety, and the safety risks of each target must be considered at the same time. When there is a risk of collision with at least one target, the safety risk level must be judged and the corresponding strategy must be implemented, such as emergency braking, gentle braking, or sound and light reminders.

[0118] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A driving assistance method based on V2X perception fusion technology, characterized in that: The method comprises the following steps: after the main vehicle enters the ramp merging scene, it is determined whether there is a target vehicle on the far right side of the main road. If not, it is recorded as event A and the vehicle is driven normally. If yes, it is determined whether the main vehicle reaches the collision point first. If yes, it is determined whether the main vehicle satisfies the condition that TTC is greater than a first preset value and THW is greater than a first set threshold value after entering the main road. If yes, it is recorded as event C and the vehicle is driven normally. If not, step 2 is executed. If the main vehicle fails to reach the collision point first, it is predicted whether the main vehicle meets the TTC greater than the first preset value and the THW greater than the second preset threshold after entering the main road; If yes, record it as event B and drive normally, if no, proceed to step 2; Step 2: Determine whether the distance between the safety line and the main vehicle is less than the third set threshold value of emergency braking. If so, emergency braking is performed and step 3 is executed. If not, determine whether the distance between the safety line and the main vehicle is less than the fourth set threshold value of gentle braking. If so, gentle braking is performed and step 3 is executed. If not, determine whether the distance between the safety line and the main vehicle is less than the fifth set threshold value of early warning. If not, normal driving is performed. If so, early warning is performed and step 3 is executed. Step 3: When at least one of event A, event B, and event C is satisfied, the system exits the alarm or brakes. If the main vehicle has stopped, the driver is reminded to drive into the main road in time. The TTC is the time between the main vehicle and the target vehicle. If the main vehicle reaches the collision point first, the calculation formula of TTC is: THW is the headway time, and the calculation formula is: If the main vehicle fails to reach the collision point first, the TTC calculation formula is: THW is the headway time, and the calculation formula is: Among them, v SV is the driving speed of the main vehicle; v T is the speed of the target vehicle; a SV is the acceleration of the main vehicle; a T is the acceleration of the target vehicle; d R The distance between the main vehicle and the target vehicle after it enters the main road.

2. The driving assistance method based on V2X perception fusion technology according to claim 1 is characterized in that: The calculation formula of the third set threshold value Dstop is: Among them, t RBR Braking system response time.

3. The driving assistance method based on V2X perception fusion technology according to claim 2 is characterized in that: The fourth set threshold d stop The calculation formula is: Among them, t SVD The driver's reaction time.

4. The driving assistance method based on V2X perception fusion technology according to claim 1, characterized in that: The method of determining whether the host vehicle reaches the collision point first further includes first determining the time T1 when the target vehicle reaches the collision point, and the calculation formula is: Among them, d T is the distance from the target vehicle to the collision point; Determine the time T2 when the main vehicle reaches the collision point, and the calculation formula is: Among them, d S is the distance from the main vehicle to the collision point; If T1 is greater than or equal to T2, the host vehicle reaches the collision point first, otherwise the target vehicle reaches the collision point first.

5. The driving assistance method based on V2X perception fusion technology according to claim 1, characterized in that: The first set threshold is 4.4s.

6. The driving assistance method based on V2X perception fusion technology according to claim 1, characterized in that: The second set threshold is 1.2s.

7. The driving assistance method based on V2X perception fusion technology according to claim 1, characterized in that: If there are multiple target vehicles, each target vehicle is judged.

8. A vehicle, characterized in that: It includes a controller, which executes the driving assistance method based on V2X perception fusion technology as described in any one of claims 1-7.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the driving assistance method based on V2X perception fusion technology as described in any one of claims 1 to 7 is implemented.

10. A storage medium, which is computer-readable and stores a computer program, characterized in that: When the computer program is executed by a processor, the driving assistance method based on V2X perception fusion technology as described in any one of claims 1 to 7 is implemented.

Images