A high-risk road section longitudinal decision control method based on V2I, a vehicle, a computer and a storage medium

Abstract

The present application relates to the technical field of automatic driving, in particular to a high-risk section longitudinal decision control method based on V2I, a vehicle, a computer and a storage medium, the present application realizes the fusion perception of roadside sensors and vehicle-mounted sensors based on V2I technology, obtains the early perception ability of the vehicle SV to the high-risk section environment, obtains the safety boundary of the high-risk section, and forms an autonomous decision control system, so that the vehicle can travel in the safety range, and once the safety boundary is exceeded, the vehicle can be controlled and stopped to the maximum extent; the present application realizes the functions that the traditional ADAS based on vehicle-mounted perception cannot realize or enhances the performance and reliability of the existing ADAS functions.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, specifically to a longitudinal decision-making and control method for high-risk road sections based on V2I, a vehicle, a computer, and a storage medium. Background Technology

[0002] Safe driving is the primary and essential requirement for car owners. Driving off-course in high-risk areas can easily lead to traffic accidents. Especially on high-risk road scenarios such as bridges spanning rivers, mountain roads, and sections near rivers, most traffic accidents are caused by exceeding safe driving boundaries, often resulting in falls into rivers, cliffs, or other dangerous situations, leading to serious injuries and losses. The causes are often driver inattention or malicious behavior by passengers.

[0003] Despite existing technologies attempting to address this issue, such as Driver Fatigue Monitor Systems (DMS) and Autonomous Emergency Braking (AEB), physical limitations and delayed system responses often prevent accidents from occurring. For example, consider this SV vehicle traveling on a high-risk mountain road with a mountainside on one side and a cliff on the other. If the driver is not paying attention or encounters other unforeseen circumstances, the vehicle could easily veer off the road and fall. In this scenario, the AEB system might be ineffective due to the low road boundary, and the DMS might not detect brief moments of driver inattention or unforeseen circumstances. Even if it does, it might only issue a warning, leaving the driver with the final decision-making power. Considering driver delays, an accident is almost inevitable.

[0004] In summary, achieving intelligent driving faces numerous core technological bottlenecks, with environmental perception technology being the most critical and a major constraint on the practical application of intelligent driving systems. The integrated development of autonomous vehicles, roads, and smart city networks is a current cross-industry trend. The development and maturity of intelligent + connected + big data + cloud platform technologies are the technological foundation and guarantee for realizing "intelligent vehicle+".

[0005] Intelligent driving technology is one of the core technology areas of intelligent connected vehicles. Among these, environmental perception and control decision-making are the core technological bottlenecks of intelligent driving systems. Currently, in the field of intelligent driving technology, the system's environmental perception capability is far from mature, representing a bottleneck within a bottleneck and a key constraint on achieving intelligent driving. Single-vehicle perception (onboard sensors) and vehicle-to-everything (V2X) communication each have their limitations; only by combining the two can breakthroughs and leaps in intelligent perception technology be achieved. This represents the most feasible system solution, technical route, and direction for intelligent driving at present. In other words, realizing the environmental perception capability that empowers intelligent driving requires the integration of onboard sensors and V2X information technology, thereby greatly enhancing the vehicle's perception capabilities and ultimately significantly improving the functionality, performance, and safety reliability of intelligent driving. Simultaneously, the widespread application of V2X can significantly reduce the cost of single-vehicle intelligent perception.

[0006] Developing intelligent connected vehicles based on vehicle-to-infrastructure (V2I) communication to achieve intelligent driving technology and solve the problems of extremely complex and ever-changing scenarios is a long road and a long process. Although achieving fully autonomous driving is the direction of intelligent connected vehicle technology development, this is a long-term goal, and widespread commercial application still has a long way to go. Market demand is the decisive factor driving technological progress and implementation. Recently, the industry has begun to reach a consensus that using V2I technology to solve problems such as driving safety in key dangerous scenarios, traffic congestion, and improving traffic efficiency is the most important market demand and the biggest pain point in safe driving in transportation. This is a problem that needs to be gradually solved over the next few decades. In other words, solving driving safety problems in key dangerous scenarios is the current key objective and promoting the industrialization of the technology.

[0007] ADAS (Advanced Driver Assistance Systems) is a typical driver assistance system for solving driving safety issues and a technological foundation for achieving autonomous driving. It is currently developing rapidly and has a huge market. However, although ADAS systems have been on the market for many years, their technology is still far from mature, and their functionality and performance are severely limited by the system's perception capabilities. Especially in some particularly dangerous scenarios, ADAS cannot effectively avoid collisions. Through V2I (Vehicle-to-Infrastructure) technology, the onboard system and roadside perception information are fused, which can overcome the technical bottlenecks in perception and decision-making algorithms in some high-risk scenarios, developing an ADAS+ system with expanded functionality and enhanced performance. This invention aims to solve one of the high-risk scenarios that traditional ADAS systems cannot address.

[0008] Existing ADAS (Advanced Driver Assistance Systems) technologies rely on their onboard perception equipment. Due to limitations in their environmental perception range and capabilities, they cannot function effectively in many critical and dangerous scenarios. These include situations such as when the view of merging vehicles is obstructed at intersections, when the view of the vehicle in front is obstructed, when traffic lights are obstructed, and when running a red light at an intersection. In these scenarios, physical conditions dictate that ADAS systems based on their own onboard perception cannot effectively avoid collisions in sudden situations.

[0009] V2I technology can help overcome environmental perception obstacles in the above scenarios and systematically improve the vehicle's environmental perception capabilities. However, the current application of V2I technology mainly focuses on helping to realize autonomous driving technology, and the widespread commercial application of autonomous driving technology is still a long way off.

[0010] Therefore, the combination of V2I and ADAS systems has vast potential and room for development in both technology and commercial application. Thus, the purpose of this invention is to develop enhanced and more reliable ADAS+ system functional decision-making and control algorithms based on the systematic and deep integration of V2I and vehicle perception, addressing technical problems that vehicle perception cannot solve in key hazardous scenarios. Summary of the Invention

[0011] The technical problem to be solved by the present invention is to provide a V2I-based longitudinal decision control method, vehicle, computer and storage medium for solving the scenario of vehicles driving on high-risk road sections by integrating vehicle-mounted perception and roadside perception technologies through the application of V2I technology.

[0012] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0013] A longitudinal decision-making and control method for high-risk road sections based on V2I, including

[0014] Scene recognition determines whether the vehicle has entered a high-risk road segment; if so, it continues; otherwise, it does not interfere.

[0015] The decision-making process involves the vehicle communicating with the roadside RSU (Roadside Unit) via V2I (Vehicle-to-Infrastructure) communication to obtain information. Based on this information, relevant parameters are calculated to determine whether the distance *d* between the vehicle's front and the safety boundary is less than or equal to the danger distance *d* between the vehicle's front and the safety boundary. danger If so, activate AEB to stop the vehicle; otherwise, determine if the vehicle meets condition d. danger <d≤d warn d warn The warning distance between the front of the vehicle and the safety boundary; if so, then determine the front wheel deflection angle δ of the vehicle. f Safety threshold δ less than this range fth 1 And the rate of change of steering wheel angle wsteer The safety threshold w is less than this range th 1 , i.e. δ f <δ fth 1 and w steer <w th 1 Otherwise, the braking deceleration is calculated based on the perceived information, and gentle braking is initiated based on the braking deceleration to bring the vehicle to a stop before the safety boundary. If this is achieved, a warning is activated to alert the driver to drive safely and move to a safe area as soon as possible; if the condition d is not met... danger <d≤d warn If the front wheel deflection angle of the vehicle is not less than the safety threshold δ within this range, then it is determined that the vehicle's front wheel deflection angle is not less than the safety threshold δ within this range. fth 2 Or, the rate of change of steering wheel angle is not less than the safety threshold w within this range. th 2 , i.e. δ f ≥δ fth 2 or w steer ≥w th 2 If not, do not interfere; if yes, calculate the braking deceleration based on the perceived information and initiate gentle braking based on the braking deceleration to bring the vehicle to a stop before the safety boundary.

[0016] Preferably, the vehicle detects its own behavioral information through its own perception system;

[0017] By obtaining electronic maps from roadside RSU devices via V2I, vehicles are matched to the electronic maps in real time to determine their location; and the acquired behavioral information is combined to determine the vehicle's movement status in real time.

[0018] Preferably, the decision-making includes prediction and judgment, and the prediction and judgment include...

[0019] Based on the rate of change of steering wheel angle, vehicle driving behavior is predicted and judged. For designated high-risk road sections, a maximum limit threshold for front wheel deflection angle is set. If the rate of change of steering wheel angle obtained at this time is w steer The initial angle of the front wheel deflection is δ. f0 Then, after time t, the front wheel deflection angle δ f for:

[0020] δ f =k*w steer *t+δ f0

[0021] The maximum threshold can be reached after time t.

[0022]

[0023] Where k is the ratio factor between the steering wheel angle variable and the front wheel steering variable.

[0024] Preferably, the driver's braking reaction time is delayed by t delay and vehicle protection time t protect Included in the time period t, at the warning time t warn Issue a warning and apply gentle braking;

[0025]

[0026] Preferably, the decision-making process further includes predicting and judging vehicle driving behavior based on the distance between the vehicle's front and the safety boundary; the judgment of vehicle driving behavior includes...

[0027] Given the vehicle's initial speed v0, acceleration a0, and heading angle α... orien Calculate the vehicle's lateral speed v y The accelerations are a and a, respectively. y :

[0028] v y =v0*sin(δ f )

[0029] a y =a0*sin(δ f )

[0030] After time t, the distance d between the front of the vehicle and the safety boundary is:

[0031]

[0032] Right now

[0033]

[0034] Where d0 is the distance between the vehicle's initial distance and the safety boundary.

[0035] Preferably, the gentle braking adopts a constant acceleration model, with the initial vehicle speed v0 preset, then the deceleration a during gentle braking is... mild The calculation formula is

[0036]

[0037] Preferably, when AEB is activated to stop the vehicle, the braking deceleration reaches its maximum value a. max a max Greater than or equal to 0.8g.

[0038] A vehicle comprising the aforementioned V2I-based longitudinal decision control method for high-risk road sections.

[0039] A computer, comprising a processor and memory;

[0040] The memory is used to store computer instructions, and the processor is used to run the computer instructions stored in the memory to implement the above-mentioned V2I-based longitudinal decision control method for high-risk road sections.

[0041] A computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the above-described V2I-based longitudinal decision control method for high-risk road sections.

[0042] The beneficial effects of this invention are as follows: The purpose of this invention is to achieve the fusion perception of roadside sensors and vehicle-mounted sensors based on V2I technology, obtain the vehicle's SV's ability to perceive the environment of high-risk road sections in advance, obtain the safety boundary of high-risk road sections, and form an autonomous decision-making control system to ensure that the vehicle travels within a safe range. Once the safety boundary is exceeded, the vehicle is controlled and stopped to the maximum extent. This achieves functions that traditional ADAS based on vehicle-mounted perception cannot achieve or enhances the performance and reliability of existing ADAS functions. Attached Figure Description

[0043] Figure 1 This is an application scenario of a V2I-based longitudinal decision control method for high-risk road sections, according to a specific embodiment of the present invention.

[0044] Figure 2 This is a schematic diagram of the perception information interaction of a longitudinal decision-making and control method for high-risk road sections based on V2I, which is a specific embodiment of the present invention.

[0045] Figure 3 A vehicle motion relationship diagram of a V2I-based longitudinal decision control method for high-risk road sections, as described in a specific embodiment of the present invention;

[0046] Figure 4 A flowchart illustrating the perception information processing and prediction process of a V2I-based longitudinal decision control method for high-risk road sections, as shown in a specific embodiment of the present invention.

[0047] Figure 5 This is a decision-making flowchart of a V2I-based longitudinal decision-making control method for high-risk road sections, which is a specific embodiment of the present invention. Detailed Implementation

[0048] To explain in detail the technical content, objectives, and effects of the present invention, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0049] Example 1

[0050] A longitudinal decision-making and control method for high-risk road sections based on V2I;

[0051] Regarding the explanation of terms

[0052] V2X: Vehicle to Everything, the information communication and interaction between a vehicle and the outside world (X represents all things in the outside world, including: V2V, V2I, V2N, V2P, etc.).

[0053] V2I: Vehicle to Infrastructure, refers to the communication and information exchange between vehicles and surrounding roadside facilities.

[0054] V2P: Vehicle to People, refers to the communication and information exchange between vehicles.

[0055] AEB: Automatic Emergency Braking.

[0056] RSU: Roadside Unit

[0057] OBU: On-Board Unit (Vehicle Communication Unit)

[0058] Application Scenario Description

[0059] like Figure 1 As shown, this vehicle (SV) is a bus or large passenger vehicle traveling on a road near a river or valley. The road is narrow, and the guardrails along the roadside near the river or valley are low. This vehicle (SV) is planning to pass through this high-risk section of road. If the driver becomes inattentive or a passenger grabs the steering wheel, or if other sudden dangerous actions occur, it is difficult to avoid the vehicle falling into the river or off a cliff.

[0060] This SV vehicle is equipped with an ADAS system with Automatic Emergency Braking (AEB), but in high-risk road sections where the road boundary guardrails are low or indistinct, AEB is difficult to activate. Furthermore, the AEB system is unlikely to be triggered when the vehicle experiences a sudden increase in steering wheel angle or lateral movement beyond the road boundary. If the SV vehicle could identify the safety boundaries of high-risk road sections in advance and monitor the rate of change of steering wheel angle and the vehicle's lateral and longitudinal speeds in real time, then the safety system could issue a warning when the steering wheel angle, rate of change, and lateral speed continuously reach certain thresholds. When the vehicle approaches the safety boundary within a certain distance, the safety system could actively take braking or even stop measures to prevent the vehicle from crossing the safety boundary and falling into the road.

[0061] Environmental perception and conditions, reference Figure 2 ,

[0062] This vehicle SV is equipped with sensing devices, such as a navigation system, to detect the vehicle's heading angle, lateral and longitudinal speeds in real time. It also features a steering wheel angle sensor to detect the steering wheel angle and its rate of change in real time.

[0063] This vehicle SV is equipped with an OBU (V2I on-board unit) for real-time V2I communication and information exchange with the roadside RSU (Roadside Unit).

[0064] Edge computing units and RSU devices enabling V2I communication are installed on the roadside. The edge computing units are configured with electronic maps of high-risk road sections and set safety boundaries for these sections. The roadside RSUs and vehicle SVs (Sales Vehicles) exchange information in real time via V2I, with the roadside electronic map information being sent to the vehicle SVs in real time.

[0065] In this invention, the vehicle's SV (Side Module) connects with the roadside RSU (Roadside Unit) via its onboard OBU (On-Board Unit) and V2I (Vehicle-to-Infrastructure) communication to collaboratively perceive road condition information in high-risk sections, which is then fused with the onboard sensing information. On one hand, the vehicle uses its own sensing system to detect its speed, heading angle, lateral and longitudinal speeds, lateral and longitudinal accelerations, steering wheel angle, and steering wheel angle change rate. Simultaneously, it obtains an electronic map provided by the roadside via V2I, matching the SV vehicle onto the map in real time to determine whether the vehicle is traveling within a safe area or approaching a safe boundary. By timely acquiring the SV vehicle's behavioral information, including steering wheel angle, steering wheel angle change rate, lateral speed, and lateral acceleration, the system continuously assesses the vehicle's motion status. When these values ​​exceed a certain threshold, the system immediately issues a warning. By integrating roadside electronic map information via V2I and fusing vehicle-mounted perception with electronic map information, the system determines the vehicle's location in high-risk road sections, detects the distance between the in-vehicle (SV) vehicle and the safety boundary, and measures its speed and acceleration as it approaches the safety boundary. The system calculates the vehicle's motion state in real time. When the distance between the vehicle and the safety boundary at a certain speed exceeds a certain threshold, the system initiates braking or even brings the vehicle to a complete stop to prevent it from crossing the safety boundary. To achieve these system technical goals, the following key technical aspects need to be addressed: real-time V2I communication, V2I-based collaborative perception fusion, prediction and judgment of the in-vehicle SV's behavior, and the SV's control decision algorithm.

[0066] The prediction and judgment of the driving behavior of this vehicle SV are based on... Figure 3

[0067] Assumption:

[0068] This vehicle is traveling at speed V. SV The velocity components in the longitudinal (x-axis direction) and transverse (y-axis direction) directions are V, respectively. x V y Similarly, the vehicle's SV acceleration a SV The velocity components in the longitudinal (x-axis direction) and transverse (y-axis direction) directions are a x a y ;

[0069] The distance between the front of the SV vehicle and the safety boundary is d, and the warning distance between the front of the SV vehicle and the safety boundary is d. warn The dangerous distance between the front of the SV vehicle and the safety boundary is d. danger ;

[0070] The steering wheel angle is θ steer Steering wheel angle change rate w steer Front wheel deflection angle δ f The scaling factor between the steering wheel angle variable and the front wheel steering variable is k, i.e., Δδ f =k*Δθ steer ;

[0071] Vehicle heading angle α orien .

[0072] The main focus of this invention is to address the situation where, during the passage of a vehicle-to-everything (SV) vehicle (V2X) through high-risk road sections, the vehicle's SV perception system, through V2I technology, obtains an electronic map from the roadside and acquires steering wheel angle, heading angle, vehicle longitudinal and lateral velocities, vehicle longitudinal and lateral accelerations, and high-precision vehicle position information to accurately locate the SV's position on the electronic map. The perception system determines the SV's distance from the safety boundary by a distance *d*. Once the steering wheel angle, the rate of change of steering wheel angle, and the distance relative to the safety boundary exceed a certain threshold, the intelligent system issues a warning. Based on the vehicle's lateral velocity, lateral acceleration, and distance relative to the safety boundary, the intelligent system makes a comprehensive judgment, issuing a warning, gentle braking, and automatic emergency braking (AEB) to ensure that the SV does not cross the safety boundary. The vehicle decision-making and control technology developed based on V2I-based vehicle-road cooperative perception information is within the scope of this invention.

[0073] SV prediction and judgment are completed by the perception system. The V2I-based perception fusion system includes roadside perception units, vehicle-mounted perception units, and collaborative perception fusion units. Roadside perception units mainly include edge computing, high-precision electronic maps, and roadside communication modules (RSUs). Vehicle-mounted perception includes high-precision integrated navigation equipment, steering wheel angle sensors, and vehicle-mounted communication modules (OBUs). The collaborative perception fusion unit mainly consists of vehicle-mounted computing units.

[0074] Prediction and judgment, process reference Figure 4 and Figure 5

[0075] (a) Based on the rate of change of steering wheel angle, predict and judge vehicle driving behavior, and set a maximum limit threshold for front wheel deflection angle for designated high-risk road sections. If the rate of change of steering wheel angle obtained at this time is w steer The initial angle of the front wheel deflection is δ. f0 Then, after time t, the front wheel deflection angle is:

[0076] δ f =k*w steer *t+δ f0

[0077] The maximum threshold can be reached after time t.

[0078]

[0079] Considering the driver's braking reaction time delay t delay and system protection time t protect Then the system should be at t warn It constantly issues warnings and performs gentle braking.

[0080]

[0081] (b) Predict and judge vehicle driving behavior based on the distance between the vehicle's front and the safety boundary. The initial speed of vehicle SV is v0, the acceleration is a0, and the heading angle is α. orien Then the vehicle's lateral speed and acceleration are v, respectively. y a y :

[0082] v y =v0*sin(δ f )

[0083] a y =a0*sin(δ f )

[0084] After time t, the distance d between the front of vehicle SV and the safety boundary is:

[0085]

[0086] Right now:

[0087]

[0088] Where d0 represents the distance between the vehicle's initial distance and the safety boundary. The warning distance between the front of the SV vehicle and the safety boundary is d. warn The dangerous distance between the front of the SV vehicle and the safety boundary is d. danger When d continues to approach d warn This should be noted. When d crosses d warn When the system anticipates that SV is at risk of colliding with the safety boundary, an alarm should be triggered. When d continues to approach d... danger When the system anticipates that SV will collide with the safety boundary, it should initiate gentle braking while considering the safety of the passengers to ensure the vehicle remains ahead of the safety boundary. When d crosses d...danger When the system predicts that the SV is about to crash into the safety boundary, it should brake urgently to ensure that the vehicle does not fall.

[0089] (2) Control and decision-making algorithm design:

[0090] (a) The distance d between the front of the SV vehicle and the safety boundary satisfies d ≤ d danger

[0091] At this point, SV activates AEB, and the braking deceleration reaches its maximum value a. max a max You can take 0.8g or even more to ensure that SV stops in a short time.

[0092] (b) The distance d between the front of the SV vehicle and the safety boundary satisfies d danger <d≤d warn

[0093] If the front wheel deflection angle of the vehicle is less than the safety threshold δ within this range... fth 1 And the rate of change of steering wheel angle is less than the safety threshold w within this range. th 1 , i.e. δ f <δ fth 1 and w steer <w th 1 In this case, the vehicle's SV intelligent control system will only issue a warning, alerting the driver to drive safely and move to a safe area as soon as possible.

[0094] If the front wheel deflection angle of the vehicle is not less than the safety threshold δ within this range... fth 1 Or, the rate of change of steering wheel angle is not less than the safety threshold w within this range. th 1 , i.e. δ f ≥δ fth 1 or w steer ≥w th 1 The vehicle's SV intelligent control system initiates gentle braking, with a braking deceleration of a. mild1 It is related to the distance d between the front of the SV vehicle and the safety boundary.

[0095] We choose the constant acceleration model, assuming the vehicle's initial speed is v0, then we can obtain:

[0096]

[0097] When SV is at a distance d from the safety boundary, the SV vehicle control system starts with a deceleration of a. mild The braking ensures that the vehicle stops before the SV reaches the safety boundary.

[0098] (c) The distance d between the front of the SV vehicle and the safety boundary satisfies d > d warn

[0099] If the front wheel deflection angle of the vehicle is less than the safety threshold δ within this range... fth 1 And the rate of change of steering wheel angle is less than the safety threshold w within this range. th 2 , i.e. δ f <δ fth 1 and w steer <w th 2 The intelligent system determines that the vehicle is driving normally and does not intervene.

[0100] If the front wheel deflection angle of the vehicle is not less than the safety threshold δ within this range... fth 2 Or, the rate of change of steering wheel angle is not less than the safety threshold w within this range. th 2 , i.e. δ f ≥δ fth 2 or w steer ≥w th 2 The vehicle's SV intelligent control system initiates gentle braking, with a braking deceleration of a. mild2 It is related to the distance d between the front of the SV vehicle and the safety boundary.

[0101] Similar to the above, choosing the constant acceleration model, assuming the vehicle's initial speed is v0, then we can obtain:

[0102]

[0103] Example 2

[0104] A vehicle employs the V2I-based longitudinal decision control method for high-risk road sections as described in Embodiment 1.

[0105] Example 3

[0106] A computer, comprising a processor and memory;

[0107] The memory is used to store computer instructions, and the processor is used to run the computer instructions stored in the memory to implement the V2I-based longitudinal decision control method for high-risk road sections as described in Embodiment 1.

[0108] Example 4

[0109] A computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the V2I-based longitudinal decision control method for high-risk road sections as described in Embodiment 1.

[0110] In summary, the V2I-based longitudinal decision-making and control method for high-risk road sections provided by this invention achieves the fusion of vehicle-mounted perception and roadside perception information through V2I technology, obtaining more accurate and reliable all-weather environmental perception information and solving perception obstacles in critical and dangerous scenarios. The V2I-based perception fusion technology is then applied to ADAS systems to form an ADAS+ system, thereby obtaining ADAS functional algorithm technology with enhanced functionality and performance.

[0111] Based on V2I perception information, potential dangerous driving behaviors are judged; for example, in this invention, based on the motion state of the SV vehicle and its motion information near the safety boundary, a prediction and intervention are made to determine whether it has run out of the safety boundary.

[0112] Control decision-making algorithms comprehensively consider comfort, safety, and collision avoidance requirements, and are applicable to ADAS and autonomous driving systems. For example, control decisions include warnings, gentle deceleration, and emergency braking.

[0113] Vehicle decision control algorithms, such as deceleration, speed, and relative distance control strategies, are dynamically calculated and optimized in real time based on the vehicle's motion trajectory.

[0114] By integrating sensor information and motion calculations, a braking pre-control strategy can be applied before emergency braking is initiated, if necessary, to improve system reaction speed, reduce braking delay, and enhance collision avoidance performance.

[0115] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent modifications made based on the content of the present invention specification and drawings, or direct or indirect applications in related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A longitudinal decision-making and control method for high-risk road sections based on V2I, characterized in that, include Scene recognition determines whether the vehicle has entered a high-risk road segment; if so, it continues; otherwise, it does not interfere. The decision-making process involves the vehicle communicating with the roadside RSU (Roadside Unit) via V2I (Vehicle-to-Infrastructure) communication to obtain information. Based on this information, relevant parameters are calculated to determine whether the distance *d* between the vehicle's front and the safety boundary is less than or equal to the danger distance *d* between the vehicle's front and the safety boundary. danger If so, activate AEB to stop the vehicle; otherwise, determine if the vehicle meets condition d. danger <d≤d warn d warn The warning distance between the front of the vehicle and the safety boundary; if so, then determine the front wheel deflection angle δ of the vehicle. f Safety threshold δ less than this range fth1 And the rate of change of steering wheel angle w steer The safety threshold w is less than this range th1 , i.e. δ f <δ fth1 and w steer <w th1 Otherwise, the braking deceleration is calculated based on the perceived information, and gentle braking is initiated based on the braking deceleration to bring the vehicle to a stop before the safety boundary. If this is achieved, a warning is activated to alert the driver to drive safely and move to a safe area as soon as possible; if the condition d is not met... danger <d≤d warn If the front wheel deflection angle of the vehicle is not less than the safety threshold δ within this range, then it is determined that the vehicle's front wheel deflection angle is not less than the safety threshold δ within this range. fth2 Or, the rate of change of steering wheel angle is not less than the safety threshold w within this range. th2 , i.e. δ f ≥δ fth2 or w steer ≥w th2 If not, do not interfere; if yes, calculate the braking deceleration based on the perceived information and initiate gentle braking based on the braking deceleration to bring the vehicle to a stop before the safety boundary.

2. The longitudinal decision-making and control method for high-risk road sections based on V2I according to claim 1, characterized in that, The vehicle detects its own behavioral information through its own sensing system; By obtaining electronic maps from roadside RSU devices via V2I, vehicles are matched to the electronic maps in real time to determine their location; and the acquired behavioral information is combined to determine the vehicle's movement status in real time.

3. The longitudinal decision-making and control method for high-risk road sections based on V2I according to claim 1, characterized in that, The decision-making process includes prediction and judgment, and the prediction and judgment include... Based on the rate of change of steering wheel angle, vehicle driving behavior is predicted and judged. For designated high-risk road sections, a maximum limit threshold for front wheel deflection angle is set. If the rate of change of steering wheel angle obtained at this time is w steer The initial angle of the front wheel deflection is δ. f0 Then, after time t, the front wheel deflection angle δ f for: d f =k*w steer *t+d f0 The maximum threshold can be reached after time t. Where k is the ratio factor between the steering wheel angle variable and the front wheel steering variable.

4. The longitudinal decision-making and control method for high-risk road sections based on V2I according to claim 3, characterized in that, Delay the driver's braking reaction time by t delay and vehicle protection time t protect Included in the time period t, at the warning time t warn Issue a warning and apply gentle braking; 5. The longitudinal decision-making and control method for high-risk road sections based on V2I according to claim 3, characterized in that, The decision-making process also includes predicting and judging vehicle driving behavior based on the distance between the vehicle's front and the safety boundary; the judgment of vehicle driving behavior includes... Given the vehicle's initial speed v0, acceleration a0, and heading angle α... orien Calculate the vehicle's lateral speed v y The accelerations are a and a, respectively. y : v y =v0*sin (δ f ) a y =a0*sin (δ f ) After time t, the distance d between the front of the vehicle and the safety boundary is: Right now Where d0 is the distance between the vehicle's initial distance and the safety boundary.

6. The longitudinal decision-making and control method for high-risk road sections based on V2I according to claim 3, characterized in that, The gentle braking employs a constant acceleration model. Given an initial vehicle speed of v0, the deceleration a during gentle braking is... mild The calculation formula is 7. The longitudinal decision-making and control method for high-risk road sections based on V2I according to claim 1, characterized in that, When AEB is activated to stop the vehicle, the braking deceleration reaches its maximum value a. max a max Greater than or equal to 0.8g.

8. A vehicle, characterized in that, The method includes the longitudinal decision control method for high-risk road sections based on V2I as described in any one of claims 1-7.

9. A computer, characterized in that, Including processor and memory; The memory is used to store computer instructions, and the processor is used to run the computer instructions stored in the memory to implement the V2I-based longitudinal decision control method for high-risk road sections as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the V2I-based longitudinal decision control method for high-risk road sections as described in any one of claims 1-7.

Images