A Decision-Making Method for Autonomous Driving Based on Driving Intensity

Abstract

This invention discloses an autonomous driving decision-making method based on driving intensity, comprising: calculating the reachable space of the current vehicle based on the vehicle's motion state and driving intensity; reducing the reachable space to obtain the drivable space; constructing a vehicle operability evaluation model, an energy consumption level evaluation model, and a following performance evaluation model respectively; solving the evaluation models using a hierarchical binary optimization method; synthesizing the evaluation results; selecting the optimal pre-aiming point from the drivable space; and determining the driving intensity of the optimal pre-aiming point. This invention improves the stability of multi-objective decision-making and ensures vehicle stability.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and more particularly to an autonomous driving decision-making method based on driving intensity. Background Technology

[0002] Since the beginning of the 21st century, autonomous vehicles have gradually moved from imagination to reality. Mature autonomous driving technology can significantly reduce traffic accident rates, ensure the safety of drivers and pedestrians, and optimize traffic flow. In the closed-loop system of people, vehicles, and roads, the driver is the most unreliable factor; therefore, research on driver models is of great significance. Most existing driver models analyze decision-making and control in the vehicle coordinate system, and their calculation results are not directly related to driving operations. They cannot accurately describe the driver's steering and speed control operations, and their fit with the vehicle chassis is not high, exhibiting certain limitations.

[0003] Therefore, a new anti-aiming control method is needed that can better match the vehicle chassis structure and human driving habits while ensuring handling stability. Summary of the Invention

[0004] To address the issue that traditional driver models using lateral and longitudinal acceleration as decision variables are not well-suited to vehicle chassis structure and driving habits, an autonomous driving decision-making method based on driving intensity is proposed. This method simplifies the control model, improves comfort, and better aligns with driving habits while ensuring safety.

[0005] To achieve the above objectives, the present invention provides an autonomous driving decision-making method based on driving intensity, comprising:

[0006] Based on the vehicle's motion state and driving intensity, the current reachable space of the vehicle is calculated, and the reachable space is reduced to obtain the drivable space;

[0007] Vehicle operability evaluation model, energy consumption level evaluation model and followability evaluation model are constructed respectively. The hierarchical binary optimization method is used to solve the evaluation models respectively. Based on the comprehensive evaluation results, the optimal aiming point is selected from the drivable space and the driving intensity of the optimal aiming point is determined.

[0008] Preferably, calculating the reachable space of the current vehicle includes:

[0009] The driving intensity of the vehicle is calculated, which is represented by the rate of change of the heading angle in space and the rate of change of the vehicle speed over time. The rate of change of the heading angle in space is represented by the vehicle curvature, and the rate of change of the vehicle speed over time is represented by the tangential acceleration.

[0010] The curvature range of the current vehicle is analyzed based on the steering wheel angle range, wheelbase, and the ratio of the steering wheel to the steering wheel. The range of tangential acceleration variation is also analyzed based on the current vehicle's power specifications.

[0011] Excluding the case of vehicle sideslip, the curvature range is reduced, the driving intensity variation range is uniformly discretized, and each driving intensity is combined as the future motion state of the vehicle to form the reachable space.

[0012] Preferably, the calculation methods for the vehicle curvature and the tangential acceleration are as follows:

[0013]

[0014] In the formula, θ is the heading angle. Let yaw angle be L, wheelbase be R, turning radius be k, curvature be k, speed be v, time be t, and acceleration be a.

[0015] The method for calculating the curvature range is as follows:

[0016]

[0017] In the formula, θ is the maximum steering wheel angle, n is the transmission ratio between the steering wheel and the steering wheel, and k max This represents the maximum curvature of the vehicle.

[0018] Preferably, the method for calculating the reachable space is as follows:

[0019]

[0020] In the formula, a is the magnitude of tangential acceleration, h is the heading angle, x and y are the horizontal and vertical coordinates respectively, v is the vehicle speed, the subscripts i and i-1 represent any consecutive current time and previous time, and Δt represents the time interval between the current time and the previous time.

[0021] Preferably, obtaining the drivable space includes:

[0022] Based on the legality of the vehicle's current driving, remove the solid lines of the opposite lane and the adjacent lane of the vehicle in the accessible space, and remove the space outside the stop line when the light is red;

[0023] Considering the driving safety of the current vehicle, the intersection of the bounding box corresponding to the current vehicle's pre-aimed position with the bounding boxes of other traffic participants is removed.

[0024] Preferably, the vehicle operability evaluation model is constructed based on the vehicle's speed adjustment operability and steering operability, specifically as follows:

[0025] J h =wa *J a +w k *J k

[0026] In the formula, J a J is an evaluation index for speed regulation in terms of ease of operation. k J is an evaluation index for the ease of operation of steering. h As the overall ease of operation evaluation index, w a As the weight of the speed regulation evaluation index, w k The weights of the evaluation indicators for the shift.

[0027] Preferably, the energy consumption level evaluation model is constructed based on the vehicle's efficiency and ease of operation, specifically as follows:

[0028] J v =w e *J e +w h *J h

[0029] In the formula, J e J is an efficiency evaluation index. h As the overall evaluation index for ease of operation, J v As an overall energy consumption level evaluation index, w e As the weight of the efficiency evaluation index, w h The weights of the manipulability evaluation indicators.

[0030] Preferably, the following performance evaluation model is constructed based on the vehicle's longitudinal and lateral following performance, specifically as follows:

[0031] J s =w c *J c +w l *J l

[0032] In the formula, J c J is a horizontal following evaluation index. l J is a longitudinal tracking evaluation index. s As the overall path following performance evaluation index, w c To determine the weights of the horizontal followability evaluation indicators, w l The weights of the longitudinal tracking evaluation indicators.

[0033] Preferably, the method for synthesizing the evaluation results is as follows:

[0034] J = w s *J s +w v *J v

[0035] In the formula, J s J is a path-following performance evaluation index. v J is the energy consumption level evaluation index, and w is the overall evaluation index. s w is the weight of the path following line evaluation index. v The weights of the energy consumption level evaluation indicators.

[0036] Preferably, selecting the optimal aiming point includes:

[0037] An adaptive mesh optimization algorithm is used to find the point with the minimum cost, i.e., the optimal pre-aiming point, and the optimal pre-aiming driving intensity is determined.

[0038] Compared with the prior art, the present invention has the following advantages and technical effects:

[0039] (1) The present invention uses driving intensity as a decision variable to decouple the vehicle speed adjustment and steering, making the pre-aiming process more in line with human driving habits and more in line with the vehicle chassis structure, thus simplifying the vehicle motion prediction model.

[0040] (2) The present invention uses driving intensity as a decision quantity, which is a more intuitive and direct control variable. It can reduce the vibration and impact of the vehicle during turning and acceleration and deceleration, and improve the smoothness and comfort of driving.

[0041] (3) The present invention uses an adaptive mesh optimization algorithm to solve the problem, which improves the stability of multi-objective decision-making and ensures the stability of the vehicle. Attached Figure Description

[0042] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0043] Figure 1 This is an Ackermann steering diagram of a vehicle in an embodiment of the present invention;

[0044] Figure 2 This is a flowchart of the pre-aiming decision method in an embodiment of the present invention;

[0045] Figure 3 This is a schematic diagram of the reachable space in an embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram of the aiming path in an embodiment of the present invention. Detailed Implementation

[0047] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0048] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0049] This invention proposes an autonomous driving decision-making method based on driving intensity, such as... Figure 2 ,include:

[0050] Based on the vehicle's motion state and driving intensity, the reachable space of the current vehicle is calculated. Taking into account the legality and safety of the vehicle and other traffic participants, the reachable space is reduced to obtain the drivable space.

[0051] Vehicle operability evaluation model, energy consumption level evaluation model and followability evaluation model are constructed respectively. The hierarchical binary optimization method is used to solve the evaluation models respectively. Based on the comprehensive evaluation results, the optimal aiming point is selected from the drivable space and the driving intensity of the optimal aiming point is determined.

[0052] This invention improves the stability of multi-objective decision-making solutions and ensures vehicle stability.

[0053] Further, the reachable space of the current vehicle is calculated, including:

[0054] The driving intensity of the vehicle is calculated. The driving intensity is represented by the rate of change of the heading angle in space and the rate of change of the vehicle speed over time. The rate of change of the heading angle in space is represented by the vehicle curvature, and the rate of change of the vehicle speed over time is represented by the tangential acceleration.

[0055] The curvature range of the current vehicle is analyzed based on the steering wheel angle range, wheelbase, and the ratio of the steering wheel to the steering wheel. The range of tangential acceleration variation is also analyzed based on the current vehicle's power specifications.

[0056] Excluding the case of vehicle sideslip, the curvature range is reduced, the driving intensity variation range is uniformly discretized, and each driving intensity is combined as the future motion state of the vehicle to form the reachable space.

[0057] Specifically, the calculation methods for vehicle curvature and tangential acceleration are as follows:

[0058]

[0059] In the formula, θ is the heading angle. Let yaw angle be L, wheelbase be R, turning radius be k, curvature be k, speed be v, time be t, and acceleration be a.

[0060] The method for calculating the curvature range is as follows:

[0061]

[0062] In the formula, θ is the maximum steering wheel angle, n is the transmission ratio between the steering wheel and the steering wheel, and k max This represents the maximum curvature of the vehicle.

[0063] Furthermore, the method for calculating the reachable space is as follows:

[0064]

[0065] In the formula, a is the magnitude of tangential acceleration, h is the heading angle, x and y are the horizontal and vertical coordinates respectively, v is the vehicle speed, the subscripts i and i-1 represent any consecutive current time and previous time, and Δt represents the time interval between the current time and the previous time.

[0066] Furthermore, obtaining drivable space includes:

[0067] Based on the legality of the vehicle's driving, the solid lines of the opposite lane and the adjacent lane of the vehicle's own lane in the accessible space are removed, and the space outside the stop line is removed when the light is red.

[0068] Considering the driving safety of the vehicle, the intersection of the bounding box corresponding to the current vehicle's aiming position with the bounding boxes of other traffic participants is removed.

[0069] Specifically, regarding legality, this mainly includes oncoming lanes, solid line lane changes, and stop lines at traffic lights. Oncoming lanes and adjacent solid line lanes of the vehicle's own lane are removed from the accessible space based on environmental road information. Simultaneously, space outside the stop line is removed when the light is red. Regarding safety, collisions with other traffic participants are primarily considered. A polygon intersection detection method is used for judgment. When the bounding box corresponding to the vehicle's forward-aiming position intersects with the bounding box of another traffic participant, the position is considered unsafe, and that position is removed from the drivable space.

[0070] Furthermore, a vehicle operability evaluation model is constructed based on the vehicle's ease of speed adjustment and steering, specifically as follows:

[0071] J h =w a *J a +w k *J k

[0072] In the formula, J aJ is an evaluation index for speed regulation in terms of ease of operation. k As an evaluation metric for ease of operation, w i J represents the weight of each evaluation indicator. h As the overall ease of operation evaluation index, w a As the weight of the speed regulation evaluation index, w k The weights of the evaluation indicators for the shift.

[0073] Specifically, all evaluation indicators are normalized using the sigmoid function:

[0074]

[0075] In the formula, x is the normalization objective, J is the normalization result, and A and B are constants determined by the maximum and minimum values ​​of the normalization objective, respectively.

[0076] The ease of vehicle handling is evaluated based on changes in vehicle acceleration and curvature, where A and B are calculated as follows:

[0077]

[0078]

[0079] In the formula, a max a is the maximum achievable tangential acceleration of the vehicle. min For the minimum tangential acceleration, k max k is the maximum curvature at which the vehicle will not sideslip. min It represents the minimum curvature.

[0080] Furthermore, based on the vehicle's efficiency and ease of operation, the energy consumption level evaluation model is constructed as follows:

[0081] J v =w e *J e +w h *J h

[0082] In the formula, J e J is an efficiency evaluation index. h As the overall evaluation index for ease of operation, w i J represents the weight of each evaluation indicator. v As an overall energy consumption level evaluation index, w e As the weight of the efficiency evaluation index, w h The weights of the manipulability evaluation indicators.

[0083] Specifically, the vehicle's efficiency is evaluated based on its speed, where A and B are calculated using the following formulas:

[0084]

[0085] In the formula, v max To comply with the maximum speed currently achievable by the vehicle under traffic regulations, v min To comply with the minimum speed that a vehicle can currently achieve under traffic regulations.

[0086] Furthermore, the following performance evaluation model is constructed based on the vehicle's longitudinal and lateral following performance, specifically as follows:

[0087] J s =w c *J c +w l *J l

[0088] In the formula, J c J is a horizontal following evaluation index. l J is a longitudinal tracking evaluation index. s As the overall path following performance evaluation index, w c To determine the weights of the horizontal followability evaluation indicators, w l The weights of the longitudinal tracking evaluation indicators.

[0089] Specifically, the longitudinal following performance of a vehicle is evaluated based on the angle between the vehicle and the centerline of the reference lane, where A and B are calculated as follows:

[0090]

[0091] In the formula, θ max For the maximum angle, θ min Minimum angle;

[0092] The lateral following ability of a vehicle is evaluated based on its distance from the center line of the reference lane, where A and B are calculated as follows:

[0093]

[0094] In the formula, d max For the maximum lateral distance, d min Minimum lateral distance;

[0095] Furthermore, the method for comprehensively evaluating the results is as follows:

[0096] J = w s *J s +w v *J v

[0097] In the formula, J s J is a path-following performance evaluation index. vJ is the energy consumption level evaluation index, and w is the overall evaluation index. s w is the weight of the path following line evaluation index. v The weights of the energy consumption level evaluation indicators.

[0098] An adaptive mesh optimization algorithm is used to find the point with the minimum cost, i.e., the optimal pre-aiming point, and the optimal pre-aiming driving intensity is determined.

[0099] Since multi-valued optimization is prone to divergence, while optimizing two values ​​with opposite effects makes it easier to find the optimal solution, a hierarchical binary optimization method is adopted. Because using larger motion variations often improves efficiency but reduces operability, efficiency and operability are optimized together to improve solution stability. Finally, considering the optimization results along with path following performance, the optimal pre-aiming driving intensity is determined.

[0100] To more clearly illustrate the technical solution of the present invention, specific embodiments are provided below for description:

[0101] This embodiment provides an autonomous driving decision-making method based on driving intensity. The inputs in this embodiment are the dynamic driving environment around the vehicle and the vehicle's motion state, and the output is the target driving intensity. The specific process includes:

[0102] Step 1: Calculate the reachable space of the current vehicle based on its motion state and driving intensity.

[0103] Driving intensity refers to steering intensity and shifting intensity, which are expressed as the rate of change of heading angle over space and the rate of change of vehicle speed over time, respectively. Figure 1 The calculation is as follows:

[0104]

[0105] In the formula, θ is the heading angle. Let yaw angle be L, wheelbase be R, turning radius be k, curvature be v, speed be t, time be a, and acceleration be a.

[0106] Vehicle curvature is used to represent the rate of change of the heading angle in space, which reflects the steering intensity of the steering wheel rotation.

[0107] Tangential acceleration is used to represent the rate of change of vehicle speed over time, which reflects the intensity of gear shifts controlled by the accelerator and brake pedals.

[0108] First, based on the steering wheel angle range, wheelbase, and the ratio of the steering wheel to the steering wheel, the curvature range of this vehicle is analyzed. Then, based on the power specifications of this vehicle, the range of tangential acceleration variation is analyzed.

[0109] The formula for calculating the curvature range based on the vehicle structure is as follows:

[0110]

[0111] In the formula, θ is the maximum steering wheel angle, n is the transmission ratio between the steering wheel and the steering wheel, L is the vehicle wheelbase, and k max This represents the maximum curvature of the vehicle.

[0112] Secondly, to rule out vehicle sideslip, the curvature range needs to be reduced. The final curvature is taken as the minimum of the two values ​​as the range boundary. The calculation formula is as follows:

[0113]

[0114] In the formula, denoted as the road surface adhesion coefficient, g as the acceleration due to gravity, v as the vehicle speed, and 0.9 as the safety factor.

[0115] Finally, the above driving intensity variation ranges are uniformly discretized, and each driving intensity is combined as the vehicle's future motion state to form an reachable space, such as... Figure 3 The calculation formula is as follows:

[0116]

[0117] In the formula, a is the magnitude of tangential acceleration, k is the vehicle curvature, h is the heading angle, x and y are the horizontal and vertical coordinates respectively, v is the magnitude of vehicle velocity, the subscripts i and i-1 represent any consecutive current time and previous time, and Δt represents the time interval between the current time and the previous time.

[0118] Step 2: Based on the legality and safety of the vehicle, consider traffic participants and reduce the accessible space.

[0119] Regarding legality, this mainly includes oncoming lanes, solid line lane changes, and stop lines at traffic lights. Oncoming lanes and adjacent solid line lanes of the vehicle's own lane are removed from the accessible space based on environmental road information. Simultaneously, space outside the stop line is removed when the light is red. Regarding safety, collisions with other traffic participants are primarily considered. A polygon intersection detection method is used for judgment. When the bounding box corresponding to the vehicle's forward-aimed position intersects with the bounding box of another traffic participant, the position is considered unsafe and removed from the accessible space.

[0120] Step 3: Establish an operability evaluation model based on the vehicle's speed adjustment operability and steering operability.

[0121] All evaluation metrics were normalized using the sigmoid function:

[0122]

[0123] In the formula, x is the normalization objective, J is the normalization result, and A and B are constants determined by the maximum and minimum values ​​of the normalization objective, respectively.

[0124] The ease of vehicle handling is evaluated based on changes in vehicle acceleration and curvature, where A and B are calculated as follows:

[0125]

[0126] In the formula, a max a is the maximum achievable tangential acceleration of the vehicle. min k is the minimum tangential acceleration that the vehicle can currently achieve. max k is the maximum curvature at which the vehicle will not sideslip. min This is the minimum curvature at which the vehicle will not sideslip.

[0127] The operability evaluation index is as follows:

[0128] J h =w a *J a +w k *J k

[0129] In the formula, J a J is an evaluation index for speed regulation in terms of ease of operation. k J is an evaluation index for the ease of operation of steering. h As the overall ease of operation evaluation index, w a As the weight of the speed regulation evaluation index, w k The weights of the evaluation indicators for the shift.

[0130] Step 4: Establish an energy consumption level evaluation model based on the vehicle's efficiency and ease of operation.

[0131] The efficiency of a vehicle is evaluated based on its speed, which reflects the time it takes for the vehicle to travel a certain distance. The calculations for A and B are as follows:

[0132]

[0133] In the formula, v max To comply with the maximum speed currently achievable by the vehicle under traffic regulations, v min To comply with the minimum speed currently allowed by traffic regulations;

[0134] The energy consumption level evaluation index is as follows:

[0135] J v =w e *J e +w h *Jh

[0136] In the formula, J e J is an efficiency evaluation index. h As the overall evaluation index for ease of operation, J v As an overall energy consumption level evaluation index, w e As the weight of the efficiency evaluation index, w h The weights of the manipulability evaluation indicators.

[0137] Step 5: Establish a following performance evaluation model based on the vehicle's longitudinal and lateral following performance.

[0138] The longitudinal following performance of a vehicle is evaluated based on the angle between the vehicle and the centerline of the reference lane, where A and B are calculated as follows:

[0139]

[0140] In the formula, θ max For the maximum angle, θ min Minimum angle;

[0141] The lateral following ability of a vehicle is evaluated based on its distance from the center line of the reference lane, where A and B are calculated as follows:

[0142]

[0143] In the formula, d max For the maximum lateral distance, d min Minimum lateral distance;

[0144] The path following performance evaluation index is as follows:

[0145] J s =w c *J c +w l *J l

[0146] In the formula, J s J is a path-following performance evaluation index. v J is the energy consumption level evaluation index, and w is the overall evaluation index. s w is the weight of the path following line evaluation index. v The weights of the energy consumption level evaluation indicators.

[0147] Step 6: Based on the evaluation model, select the point with the lowest replacement cost from the reachable space as the driving target.

[0148] Since multi-valued optimization is prone to divergence, while optimizing two values ​​with opposite effects makes it easier to find the optimal solution, a hierarchical binary optimization method is adopted. Because using larger motion variations often improves efficiency but reduces operability, efficiency and operability are optimized together to improve solution stability. Finally, considering the optimization results along with path following performance, the optimal pre-aiming driving intensity is determined.

[0149] The total cost for each point is calculated based on all evaluation indicators, as follows:

[0150] J = w s *J s +w v *J v

[0151] In the formula, J s J is a path-following performance evaluation index. v J is the energy consumption level evaluation index, and w is the overall evaluation index. s w is the weight of the path following line evaluation index. v The weights of the energy consumption level evaluation indicators;

[0152] An adaptive mesh optimization algorithm is used to find the point with the minimum cost as the pre-aiming point, and the optimal pre-aiming driving intensity is determined, such as... Figure 4 .

[0153] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An autonomous driving decision-making method based on driving intensity, characterized in that, include: Based on the vehicle's motion state and driving intensity, the current reachable space of the vehicle is calculated, and the reachable space is reduced to obtain the drivable space; Vehicle operability evaluation model, energy consumption level evaluation model and followability evaluation model are constructed respectively. The hierarchical binary optimization method is used to solve the evaluation models respectively. Based on the comprehensive evaluation results, the optimal aiming point is selected from the drivable space and the driving intensity of the optimal aiming point is determined. Calculating the reachable space of the current vehicle includes: The driving intensity of the vehicle is calculated, which is represented by the rate of change of the heading angle in space and the rate of change of the vehicle speed over time. The rate of change of the heading angle in space is represented by the vehicle curvature, and the rate of change of the vehicle speed over time is represented by the tangential acceleration. The curvature range of the current vehicle is analyzed based on the steering wheel angle range, wheelbase, and transmission ratio between the steering wheel and the steering wheel; and the tangential acceleration variation range is analyzed based on the current vehicle power specifications. Excluding the case of vehicle sideslip, the curvature range is reduced, the driving intensity variation range is uniformly discretized, and each driving intensity is combined as the future motion state of the vehicle to form the reachable space. Obtaining the drivable space includes: Based on the legality of the vehicle's current driving, remove the solid lines of the opposite lane and the adjacent lane of the vehicle in the accessible space, and remove the space outside the stop line when the light is red; Considering the driving safety of the current vehicle, the intersection of the bounding box corresponding to the current vehicle's pre-aimed position with the bounding boxes of other traffic participants is removed.

2. The autonomous driving decision-making method based on driving intensity according to claim 1, characterized in that, The calculation methods for the vehicle curvature and the tangential acceleration are as follows: In the formula, For heading angle, For the horizontal swing angle, L This refers to the vehicle's wheelbase. R The turning radius of the vehicle. k For vehicle curvature, v For the speed of the vehicle, t For time, a It is tangential acceleration; The method for calculating the curvature range is as follows: In the formula, This is the maximum steering wheel angle. This refers to the transmission ratio between the steering wheel and the steering wheels. This represents the maximum curvature of the vehicle.

3. The autonomous driving decision-making method based on driving intensity according to claim 2, characterized in that, The method for calculating the reachable space is as follows: In the formula, a The magnitude of tangential acceleration, h For heading angle, x , y These are the horizontal and vertical coordinates, respectively. For the vehicle's speed, subscript , Represents any consecutive current and previous moments. It represents the time interval between the current moment and the previous moment.

4. The autonomous driving decision-making method based on driving intensity according to claim 1, characterized in that, The vehicle's operability evaluation model is constructed based on the vehicle's ease of speed adjustment and steering, specifically as follows: In the formula, The speed regulation is evaluated based on ease of operation. As an evaluation metric for ease of operation, The overall operability evaluation index is... As the weight of the speed regulation evaluation index, The weights of the evaluation indicators for the shift.

5. The autonomous driving decision-making method based on driving intensity according to claim 1, characterized in that, The energy consumption level evaluation model is constructed based on the vehicle's efficiency and ease of operation, specifically as follows: In the formula, As an efficiency evaluation indicator, The overall evaluation index for ease of operation is... As an indicator for evaluating the overall energy consumption level, The weights of the efficiency evaluation indicators, The weights of the manipulability evaluation indicators.

6. The autonomous driving decision-making method based on driving intensity according to claim 1, characterized in that, The following performance evaluation model is constructed based on the vehicle's longitudinal and lateral following performance, specifically as follows: In the formula, It serves as a horizontal tracking evaluation indicator. As a longitudinal follow-up evaluation indicator, As the overall evaluation index for path following performance, The weights of the horizontal follow-up performance evaluation indicators are determined. The weights of the longitudinal tracking evaluation indicators.

7. The autonomous driving decision-making method based on driving intensity according to claim 1, characterized in that, The method for synthesizing the evaluation results is as follows: In the formula, As a path-following performance evaluation index, As an indicator for evaluating energy consumption levels, As the overall evaluation indicator, The weights of the path following evaluation metrics, The weights of the energy consumption level evaluation indicators.

8. The autonomous driving decision-making method based on driving intensity according to claim 1, characterized in that, Selecting the optimal aiming point includes: An adaptive mesh optimization algorithm is used to find the point with the minimum cost, namely the optimal aiming point, and the driving intensity of the optimal aiming point is determined.

Images