Vehicle speed and neutral gear sliding collaborative planning method and device

Abstract

The invention provides a vehicle speed and neutral gear sliding collaborative planning method and device, and relates to the technical field of vehicles. The method comprises the steps of planning a discretized multi-dimensional different-density state space of a vehicle based on three-dimensional road information; when the speed state transition of the neutral gear state layer is determined, the corresponding state point of the neutral gear in the vehicle speed state in each stage of the stage state is determined through approximation of the speed discrete state, and the corresponding vehicle speed state transition cost is calculated; when the speed state transition of the in-gear state layer is determined, traversing speed state points based on the determined discrete state, and calculating the cost of state point transition based on a state transition cost function; determining a state point with the minimum transfer cost in each stage based on a cost model, and obtaining a corresponding control quantity and a corresponding state quantity; the control quantity comprises gear and torque, and the state quantity comprises vehicle speed; and the control quantity and the state quantity sequence are sent to a vehicle controller to dynamically adjust the vehicle speed and the gear of the vehicle, and the energy-saving economical efficiency of vehicle driving can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method and device for coordinated planning of vehicle speed and neutral coasting. Background Art

[0002] With the continuous development and accelerated construction of intelligent network cloud control systems, intelligent network assisted driving applications based on cloud control have become a hot research direction. In the cloud control network environment, intelligent network vehicles can obtain rich road traffic information, which provides more space for optimizing the vehicle's energy-saving cruise control strategy, especially in terms of how to optimize the vehicle's power output and driving status.

[0003] At present, the coordinated control of vehicle speed and gear is one of the key technologies to achieve this goal. In the related research on the coordinated control of vehicle speed and gear, the focus is on the control strategy based on fixed rules to achieve the matching of gear and speed through preset gear switching points and vehicle speed thresholds. Or use machine learning methods to train models through historical driving data to achieve intelligent adjustment of gear and speed. However, these related studies mostly focus on the matching of gear and speed, while ignoring the energy-saving advantages of neutral gliding under specific working conditions, resulting in the failure to maximize energy-saving economy. Therefore, how to achieve coordinated planning of vehicle speed and neutral gliding to improve energy-saving economy is an important issue that the industry needs to solve urgently. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a method and device for coordinated planning of vehicle speed and neutral coasting.

[0005] The present invention provides a vehicle speed and neutral coasting coordinated planning method, comprising: In the constructed discretized multi-dimensional heterogeneous density state space, the speed and gear sequence of the vehicle's future travel is planned based on the three-dimensional road information; the discretized multi-dimensional heterogeneous density state space includes a phase state, a speed state and a gear state, the gear state includes a neutral gear and an in-gear gear, and the speed discrete interval of the neutral gear is smaller than the speed discrete interval of the in-gear gear; According to the discretized multi-dimensional heterogeneous density state space, the state transition of the neutral gear layer determines the vehicle speed state corresponding to each stage state transition through the coasting vehicle speed; the gear layer determines the state point corresponding to the vehicle speed state in each stage of the stage state according to the discrete interval of the vehicle speed in the gear, and establishes a cost model based on the transfer cost of the state point; Determine the state point with the minimum transfer cost in each stage based on the cost model, and obtain the corresponding control quantity and state quantity; the control quantity includes gear position and torque, and the state quantity includes vehicle speed; Based on the discretized multi-dimensional heterogeneous density state space, the optimal control quantity is solved to dynamically adjust the vehicle speed and gear position of the vehicle.

[0006] According to a vehicle speed and neutral coasting coordinated planning method provided by the present invention, the state point with the minimum transfer cost in each stage is determined based on the cost model, specifically including: Calculate the first transfer cost of each stage of the state point in the neutral state based on the cost model; calculate the second transfer cost of each stage of the state point in the gear state based on the cost model; Determine a neutral pre-selected state point at which the first transfer cost is the smallest in neutral state at each stage, and determine a gear pre-selected state point at which the second transfer cost is the smallest in gear state at each stage; When the first transfer cost of the neutral pre-selected state point in the target phase is less than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the neutral pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; or when the first transfer cost of the neutral pre-selected state point in the target phase is greater than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the in-gear pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; Repeat the step of determining the state point with the minimum transfer cost in the target stage to determine the state point with the minimum transfer cost in each stage.

[0007] According to a vehicle speed and neutral coasting coordinated planning method provided by the present invention, before calculating the first transfer cost of the state point in the neutral state in each stage based on the cost model, the method further includes: Determining a state transfer equation based on a preset vehicle power system model; the state transfer equation includes a gear variable and a torque variable; Determine the glide speed of the target stage based on the current state point and the state transfer equation when the gear variable is in neutral; the glide speed is the actual speed calculated and determined by the state transfer equation at the current state point; The speed deviation between the taxiing speed and the speed corresponding to each discrete state point in the target stage in the neutral state in the discretized multi-dimensional heterodensity state space is determined to determine the target state point.

[0008] According to a vehicle speed and neutral coasting coordinated planning method provided by the present invention, determining the state point with the minimum transfer cost in each stage based on the cost model specifically includes: The cost model is reversely calculated to determine the state point with the minimum transfer cost in each stage.

[0009] The control sequence of the vehicle is obtained based on the control quantity, and the state sequence of the vehicle is obtained based on the state quantity, specifically including: A forward search is performed from the starting stage to the final stage of the stage state, and the control sequence of the vehicle is obtained based on the control amount of the state point with the minimum transfer cost in each stage, and the state sequence of the vehicle is obtained based on the state amount of the state point with the minimum transfer cost in each stage.

[0010] According to a vehicle speed and neutral coasting coordinated planning method provided by the present invention, a cost model is established according to the transfer cost of the state point in each stage under the stage state, specifically including: Determine the transfer energy consumption, driving time and speed deviation between the state point speed and the cruising speed at each stage based on a preset vehicle power system model; A cost model is established by weighting the transfer energy consumption, the travel time and the speed deviation.

[0011] According to a vehicle speed and neutral coasting coordinated planning method provided by the present invention, a vehicle discretized multi-dimensional heterogeneous density state space is planned based on three-dimensional road information, specifically including: Traversing the original waypoints of the three-dimensional road information, marking the original waypoints corresponding to preset key road features as key segmentation waypoints, and marking the original waypoints corresponding to preset geometric features as non-key segmentation waypoints; Obtaining discrete waypoints of the three-dimensional road information based on the key segmentation waypoints and the non-key segmentation waypoints; The stage state of the vehicle is planned according to the discrete waypoints, and the vehicle speed state and gear state of each stage under the stage state are planned to obtain a discretized multi-dimensional heterodensity state space of the vehicle.

[0012] According to a vehicle speed and neutral coasting coordinated planning method provided by the present invention, after solving the optimal control quantity based on the discretized multi-dimensional heterogeneous density state space, the method further includes: The original waypoints are used for interpolation processing to be sent to the vehicle for control and for rolling trigger updates; Based on the fact that the angle between the line connecting the real-time GNSS position of the vehicle at the adjacent original waypoint and the line connecting the subsequent waypoints adjacent to the original waypoints is within a preset angle range, determine the vehicle position corresponding to the subsequent waypoint adjacent to the original waypoint, and set the vehicle speed and gear position at the position as the control command at the next moment for vehicle control; In the case where the subsequent waypoints in the adjacent original waypoints are the corresponding discrete waypoints in the second stage, the step of planning the vehicle in a discretized multi-dimensional heterogeneous density state space based on the three-dimensional road information is repeated.

[0013] The present invention also provides a vehicle speed and neutral coasting coordinated planning device, comprising: A state space planning module is used to plan the speed and gear sequence of the vehicle's future travel based on the three-dimensional road information in the constructed discretized multi-dimensional heterogeneous density state space; the discretized multi-dimensional heterogeneous density state space includes a phase state, a speed state and a gear state, the gear state includes a neutral gear and an in-gear gear, and the speed discrete interval of the neutral gear is smaller than the speed discrete interval of the in-gear gear; A cost model building module is used to determine the vehicle speed state corresponding to each stage state transfer according to the discretized multi-dimensional heterogeneous density state space, the state transfer of the neutral layer by the coasting vehicle speed; determine the state point corresponding to the vehicle speed state in each stage of the stage state according to the discrete interval of the vehicle speed in the gear at the gear layer, and establish a cost model based on the transfer cost of the state point; A local cost determination module, used to determine the state point with the minimum transfer cost in each stage based on the cost model, and obtain the corresponding control quantity and state quantity; the control quantity includes gear position and torque, and the state quantity includes vehicle speed; The overall cost determination module is used to solve the optimal control quantity based on the discretized multi-dimensional heterogeneous density state space to dynamically adjust the vehicle speed and gear position of the vehicle.

[0014] The present invention also provides a vehicle, 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 vehicle speed and neutral coasting coordinated planning method as described in any one of the above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the vehicle speed and neutral coasting coordinated planning method as described in any one of the above is implemented.

[0016] The vehicle speed and neutral gear coasting coordinated planning method and device provided by the present invention plan a vehicle including a discrete multi-dimensional heterogeneous density state space of a stage state, a vehicle speed state and a gear state based on three-dimensional road information, establish a cost model according to the transfer cost of the state point in each stage under the stage state, so as to determine the state point with the minimum transfer cost in each stage and the corresponding control quantity and state quantity, and solve the optimal control quantity based on the discretized multi-dimensional heterogeneous density state space to dynamically adjust the vehicle speed and gear, increase the number of neutral gear state points under the speed state by planning the neutral gear discrete interval to be smaller than the in-gear speed discrete interval, improve the probability that the vehicle can reach the determined state point when coasting in the neutral gear, and realize the vehicle speed and neutral gear coasting coordinated planning to improve energy saving and economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow charts of the vehicle speed and neutral coasting coordinated planning method provided by the present invention.

[0019] Figure 2 It is a schematic diagram of the discretized multi-dimensional heterogeneous density state space of the vehicle speed and neutral-gear coasting collaborative planning method provided by the present invention.

[0020] Figure 3 It is a schematic diagram of the expansion processing of discrete state points in neutral gear of the vehicle speed and neutral gear coasting collaborative planning method provided by the present invention.

[0021] Figure 4 It is a schematic diagram of waypoint annotation of the vehicle speed and neutral gear coasting coordinated planning method provided by the present invention.

[0022] Figure 5 It is a schematic diagram of the architecture of the cloud control system used in the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0023] Figure 6 It is one of the schematic diagrams of the module principles in the cloud control system used in the vehicle speed and neutral coasting coordinated planning method provided by the present invention.

[0024] Figure 7 This is the second schematic diagram of the module principle in the cloud control system used in the vehicle speed and neutral coasting coordinated planning method provided by the present invention.

[0025] Figure 8 It is one of the schematic diagrams of the motor model parameters in the module in the cloud control system applied to the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0026] Fig. 9 This is the second schematic diagram of the motor model parameters in the module in the cloud control system used in the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0027] Fig.10 This is the third schematic diagram of the motor model parameters in the module in the cloud control system used in the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0028] Fig.11 This is the fourth schematic diagram of the motor model parameters in the module in the cloud control system used in the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0029] Fig.12 This is the fifth schematic diagram of the motor model parameters in the module in the cloud control system used in the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0030] Fig.13 This is the sixth schematic diagram of the motor model parameters in the module in the cloud control system used in the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0031] Fig.14 It is a schematic diagram of the principle of the battery model in the cloud control system applied to the vehicle speed and neutral coasting coordinated planning method provided by the present invention.

[0032] Fig.15 It is a schematic diagram of battery model parameters in a module in a cloud control system used in the vehicle speed and neutral coasting collaborative planning method provided by the present invention.

[0033] Fig.16 This is the second flow chart of the vehicle speed and neutral coasting coordinated planning method provided by the present invention.

[0034] Fig.17 It is a structural schematic diagram of the vehicle speed and neutral coasting coordinated planning device provided by the present invention.

[0035] Fig.18 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Combine the following Figure 1-Figure 17 The vehicle speed and neutral coasting coordinated planning method and device of the present invention are described.

[0038] Figure 1 is one of the flow charts of the vehicle speed and neutral coasting coordinated planning method provided by the present invention, such as Figure 1 As shown, the method includes: Step 101: In the constructed discrete multi-dimensional heterogeneous density state space, plan the vehicle speed and gear sequence for future driving based on the three-dimensional road information; the discrete multi-dimensional heterogeneous density state space includes a phase state, a speed state and a gear state, the gear state includes a neutral gear and an in-gear gear, and the discrete interval of the neutral gear speed is smaller than the discrete interval of the in-gear gear speed.

[0039] Three-dimensional road information refers to information describing the road status in three-dimensional space. The road status may include road width, curves and other road shapes, intersections, tunnels and other road connection relationships and road elevations. The three-dimensional road information may be obtained from a remote end or may be preset in the execution subject of this method.

[0040] The state space refers to the set of all possible states. When the discretized multidimensional heterogeneous density state space includes the stage state, the vehicle speed state and the gear state, the possible state can be the first speed of the neutral gear in the first stage, or the first speed of the gear in the first stage, etc. The discretized multidimensional heterogeneous density state space refers to the state space that divides the continuous discretized multidimensional heterogeneous density state space into a finite number of discrete regions. The discretized multidimensional heterogeneous density state space includes multiple discrete state points.

[0041] Exemplarily, original waypoints can be obtained based on three-dimensional road information, and the original waypoints can be traversed to perform dimensionality reduction processing to obtain discrete waypoints of the three-dimensional road information. The stage state of the vehicle is determined according to the discrete waypoints, and the speed state of the vehicle in gear at each stage in the stage state is planned based on the vehicle speed threshold range and the first vehicle speed discrete interval. The speed state of the vehicle in neutral gear at each stage in the stage state is planned based on the vehicle speed threshold range and the first vehicle speed discrete interval, thereby obtaining a discretized multi-dimensional heterogeneous density state space including the stage state, speed state and gear state.

[0042] Step 102: According to the discretized multi-dimensional heterodensity state space, the state transfer of the neutral layer determines the vehicle speed state corresponding to each stage state transfer through the coasting vehicle speed; in the gear layer, the state point corresponding to the vehicle speed state in each stage of the stage state is determined according to the discrete intervals of the vehicle speed in the gear, and a cost model is established based on the transfer cost of the state point.

[0043] For the vehicle speed in neutral gear, since the engine does not provide power and it relies entirely on coasting, the speed state point of the neutral gear position density preset in advance may not be reached, so it can only be reached approximately, which is an approximation.

[0044] The stage state includes multiple stages: stage 1, stage 2, ..., stage k, stage k+1, ..., stage N. Each stage may correspond to a road section. For example, the starting waypoint of the road section may be used to represent the stage. On this basis, the state point may be used to describe the state quantities such as the waypoint position, gear position and speed state of the vehicle. It is understandable that each stage may include multiple state points. The transfer cost of the state point may refer to the transfer cost from a state point in stage 1 to a state point in stage 2.

[0045] For example, the state point of each stage in the discretized multi-dimensional heterogeneous density state space may correspond to the state of its distance domain terminal waypoint. For example, the state point of stage 1 may describe the speed of the vehicle when the vehicle is in a neutral state at the distance domain terminal waypoint position.

[0046] Exemplarily, the transfer cost of a vehicle from one state point to another can be determined based on a preset cost calculation method. For example, the power consumption of the vehicle from one state point to another can be determined as the transfer cost, so as to establish a cost model that can characterize the transfer cost of each stage based on the transfer cost of each possible state transfer.

[0047] Step 103: Determine the state point with the minimum transfer cost in each stage based on the cost model, and obtain the corresponding control quantity and state quantity; the control quantity includes gear and torque, and the state quantity includes vehicle speed.

[0048] The state quantity may refer to the stage and vehicle speed of the state point in the discretized multi-dimensional heterodensity state space, and the control quantity may refer to the gear position of the state point in the discretized multi-dimensional heterodensity state space, and may also include the motor torque, etc.

[0049] Step 104: Based on the discretized multi-dimensional heterogeneous density state space, solve the optimal control variable to dynamically adjust the speed and gear of the vehicle.

[0050] For example, according to the state point with the minimum transfer cost in each stage determined in step 103, the corresponding control quantity can be extracted and the control quantity can be arranged in stage order to generate a control sequence, and the corresponding state quantity can be extracted and the state quantity can be arranged in stage order to generate a state sequence. The control sequence may include changes in gear and motor torque, and the state sequence may include changes in vehicle speed.

[0051] The vehicle speed and neutral coasting collaborative planning method provided by the embodiment of the present invention plans a discrete multi-dimensional heterogeneous density state space of the vehicle including a stage state, a vehicle speed state and a gear state based on three-dimensional road information, establishes a cost model according to the transfer cost of the state point in each stage under the stage state, so as to determine the state point with the minimum transfer cost in each stage and the corresponding control quantity and state quantity, and solves the optimal control quantity based on the discretized multi-dimensional heterogeneous density state space to dynamically adjust the vehicle speed and gear, increases the number of state points of the neutral gear under the speed state by planning the vehicle speed discrete interval of the neutral gear to be smaller than the vehicle speed discrete interval of the gear, and improves the probability that the vehicle can reach the determined state point when coasting in the neutral gear, so as to realize the coordinated planning of the vehicle speed and neutral coasting to improve energy saving and economy.

[0052] In one embodiment, the vehicle speed state space under different gears can be constructed based on the following formula: in, The gear state is neutral. is the gear position state of being in gear, is the discrete interval of vehicle speed in neutral gear, is the discrete interval of vehicle speed in gear, is the maximum vehicle speed, is the minimum vehicle speed.

[0053] In addition, it is understandable that the gear level may be a common gear level of the vehicle in the target scenario. For example, in a scenario where a truck is traveling on a highway, since the driving speed of the truck is generally above 80 kilometers per hour, based on the fact that the truck includes 4 gears, the gear level refers to the 4th gear.

[0054] The maximum vehicle speed, the minimum vehicle speed, the discrete interval of the neutral speed and the discrete interval of the in-gear speed can be set according to actual needs, and this embodiment does not make any further restrictions on this. For example, in the case of a one-time forward planning distance of 2000m, it can be obtained Figure 2 The discretized multidimensional heterodensity state space is shown.

[0055] Based on the above embodiment, determining the state point with the minimum transfer cost in each stage based on the cost model specifically includes: Calculate the first transfer cost of each stage of the state point in the neutral state based on the cost model; calculate the second transfer cost of each stage of the state point in the gear state based on the cost model; Determine a neutral pre-selected state point at which the first transfer cost is the smallest in neutral state at each stage, and determine a gear pre-selected state point at which the second transfer cost is the smallest in gear state at each stage; When the first transfer cost of the neutral pre-selected state point in the target phase is less than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the neutral pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; or when the first transfer cost of the neutral pre-selected state point in the target phase is greater than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the in-gear pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; Repeat the step of determining the state point with the minimum transfer cost in the target stage to determine the state point with the minimum transfer cost in each stage.

[0056] Exemplarily, the first transfer cost of all state points in the gear state during the k-stage is calculated, and the in-gear pre-selected state point with the minimum second transfer cost in the gear state during the k-stage is determined by traversal sorting; the second transfer cost of all state points in the neutral state during the k-stage is calculated, and the neutral pre-selected state point with the minimum first transfer cost in the gear state during the k-stage is determined by traversal sorting. Here, the in-gear pre-selected state point refers to the state point in the gear state that may have the minimum transfer cost in the k-stage, and the neutral pre-selected state point refers to the state point in the neutral state that may have the minimum transfer cost in the k-stage. If the first transfer cost of the neutral pre-selected state point in the neutral state is less than the second transfer cost of the in-gear pre-selected state point in the gear state, the neutral pre-selected state point is stored in the optimal state transfer amount for the k-stage.

[0057] like Figure 3 As shown, based on any of the above embodiments, before calculating the first transfer cost of the state point in the neutral state in each stage based on the cost model, the method further includes: Determining a state transfer equation based on a preset vehicle power system model; the state transfer equation includes a gear variable and a torque variable; Determine the glide speed of the target stage based on the current state point and the state transfer equation when the gear variable is in neutral; the glide speed is the actual speed calculated and determined by the state transfer equation at the current state point; The speed deviation between the taxiing speed and the speed corresponding to each discrete state point in the target stage in the neutral state in the discretized multi-dimensional heterodensity state space is determined to determine the target state point.

[0058] Among them, infeasible points whose sliding points exceed the boundary can be removed. The state transfer equation refers to the equation that describes the law of change of the state point. The sliding speed of the vehicle actually reaches the target stage from the current state point under the control of the state transfer equation. The target stage refers to the next stage or subsequent stage of the current stage in the process of vehicle state transfer. The speed deviation can be the speed difference between the sliding speed and the speed corresponding to the discrete state point, or the speed ratio between the sliding speed and the speed corresponding to the discrete state point, etc. The discrete state point is the state point in the planned discretized multi-dimensional heterodensity state space.

[0059] Exemplarily, the state transfer equation determined by performing term-shifting discretization processing on the preset vehicle power system model is as follows: in, is the vehicle speed in the k+1 state, is the vehicle speed in state k, The gear position in the k state is in gear, The gear state in the k state is neutral. is the motor output torque in state k.

[0060] The speed change of the vehicle when gliding in neutral gear state has great randomness and uncertainty, so the gliding speed of the target stage actually determined according to the state transfer equation may not fall on the discrete state point in the discretized multi-dimensional heterogeneous density state space. To solve this problem, in this embodiment, the speed deviation between the gliding speed and each discrete state point in the neutral gear state of the target stage is determined, and the discrete state point closest to the gliding speed can be obtained based on the speed deviation. The closest discrete state point is expanded, and the state quantity of the state transfer point is approximately obtained by the closest discrete state point, so as to calculate the first transfer cost of the target state point in the neutral gear state of each stage, and coordinate the vehicle speed and neutral gliding.

[0061] In one embodiment, the state transfer equation and the cost model can be used to obtain a cloud-controlled predictive energy-saving cruise control model, and the constraints are set as follows to coordinate the planning of vehicle speed and neutral coasting.

[0062] in, is the minimum value of vehicle acceleration, is the vehicle acceleration at stage k, is the maximum value of vehicle acceleration, is the minimum value of the driving motor torque, is the driving motor torque in stage k, is the maximum value of the driving motor torque, is the minimum vehicle speed, is the vehicle speed at stage k, is the maximum vehicle speed, is the minimum value of the motor speed, is the motor speed in stage k, is the maximum value of the motor speed.

[0063] Based on any of the above embodiments, determining the state point with the minimum transfer cost in each stage based on the cost model specifically includes: The cost model is reversely calculated to determine the state point with the minimum transfer cost in each stage.

[0064] The control sequence of the vehicle is obtained based on the control quantity, and the state sequence of the vehicle is obtained based on the state quantity, specifically including: A forward search is performed from the starting stage to the final stage of the stage state, and the control sequence of the vehicle is obtained based on the control amount of the state point with the minimum transfer cost in each stage, and the state sequence of the vehicle is obtained based on the state amount of the state point with the minimum transfer cost in each stage.

[0065] Exemplarily, based on the Bellman optimality principle, starting from the terminal stage, the minimum transfer cost of each possible state point is calculated, and then gradually moving forward, the minimum transfer cost of each state point in the previous stage is calculated, and the corresponding control quantity and state quantity are recorded, and the above steps are repeated until the starting stage, and the state point with the minimum transfer cost in each stage is determined.

[0066] Starting from the state point of the initial stage, the state point of the next stage can be selected according to the minimum transfer cost obtained by reverse calculation, the state quantity and control quantity of each stage can be recorded, and the above steps can be repeated for forward search until the final stage to form a state sequence and control sequence.

[0067] In this embodiment, the minimum transfer cost of each stage is determined by reverse calculation, which can reduce the risk of the local transfer cost being the lowest while the global transfer cost being high. The optimal control sequence and state sequence are gradually determined by forward search, which can improve the coherence of the control sequence and state sequence and increase the user experience of the coordinated planning of vehicle speed and neutral coasting.

[0068] Based on any of the above embodiments, a cost model is established according to the transfer cost of the state point in each stage under the stage state, specifically including: Determine the transfer energy consumption, driving time and speed deviation between the state point speed and the cruising speed at each stage based on a preset vehicle power system model; A cost model is established by weighting the transfer energy consumption, the travel time and the speed deviation.

[0069] Transfer energy consumption refers to the energy consumption from the previous stage to the current stage state point. Transfer energy consumption can be electricity consumption or fuel consumption, etc. Cruising speed refers to the target speed set by the vehicle during driving. Cruising speed can be determined based on the driver's input instructions or based on the planning of the autonomous driving system, etc.

[0070] The weights of the weighted processing and the specific weighting method can be adjusted according to actual needs, and this embodiment will not be further explained. For example, the cost model can be obtained by weighted summation based on the transfer energy consumption, driving time and speed deviation as shown below: in, is the weighted coefficient of transfer energy consumption, is the weighting coefficient of travel time, is the weighting coefficient of speed deviation, is the state point velocity of state point i in stage k, is the cruising speed.

[0071] This embodiment achieves multi-objective collaborative optimization by building a cost model that integrates transfer energy consumption, driving time, and speed deviation, and incorporates driving time and the deviation between the state point speed and the cruising speed into the cost function. Compared with the traditional method of optimizing energy consumption alone, this embodiment can reduce energy consumption while taking into account driving efficiency and speed stability to improve user experience.

[0072] Specifically, the cost model in this embodiment can shorten the driving time by optimizing the driving time, and can make the vehicle as close to the set cruising speed as possible by controlling the speed deviation, thereby reducing the acceleration or deceleration of the vehicle to improve driving smoothness and comfort.

[0073] like Figure 4 As shown, based on any of the above embodiments, planning a discretized multi-dimensional heterogeneous density state space of a vehicle based on three-dimensional road information specifically includes: Traversing the original waypoints of the three-dimensional road information, marking the original waypoints corresponding to preset key road features as key segmentation waypoints, and marking the original waypoints corresponding to preset geometric features as non-key segmentation waypoints; Obtaining discrete waypoints of the three-dimensional road information based on the key segmentation waypoints and the non-key segmentation waypoints; The stage state of the vehicle is planned according to the discrete waypoints, and the vehicle speed state and gear state of each stage under the stage state are planned to obtain a discretized multi-dimensional heterodensity state space of the vehicle.

[0074] Among them, the preset key road features refer to road features that have a significant impact on the vehicle's transfer energy consumption, travel time and speed control, such as closed scenes such as tunnels, speed limit scenes, road slope tops and road slope valleys, etc. The preset geometric features refer to road features that have an impact on the vehicle's transfer energy consumption, travel time and speed control, such as the change rate of the road slope and the cumulative length of the road segment corresponding to the stage.

[0075] Exemplarily, when planning the first stage of the vehicle according to the starting waypoint in the discrete waypoints, the starting waypoint position is defined as the first stage, and the gear state and vehicle speed state of state point 1 in the first stage are determined by collaborative planning of the vehicle's driving state on the road segment between the starting waypoint and the next waypoint, thereby generating state point 1 of the first stage.

[0076] Specifically, if a discrete waypoint is a key segmentation waypoint corresponding to the entrance of a tunnel, the road segment between the discrete waypoint and the key segmentation waypoint corresponding to the exit of the tunnel is incorporated into the stage corresponding to the position of the previous discrete waypoint for unified planning. In this way, when there is no recommended speed and positioning information in closed scenes such as tunnels, the recommended information cached from the cloud can be used to continuously control in the tunnel, thereby increasing the proportion of energy-saving control throughout the entire process.

[0077] If a discrete waypoint is a key segmentation waypoint corresponding to the tunnel entrance, the road segment between the discrete waypoint and the key segmentation waypoint corresponding to the tunnel exit is merged into the stage to which the previous discrete waypoint belongs for unified planning. This embodiment uses this segmentation strategy. In closed scenes such as tunnels, when the vehicle cannot obtain the recommended speed and positioning information in real time, it can use the recommended speed, slope data and other information pre-cached in the cloud to continuously perform energy-saving control in the tunnel, thereby avoiding control failure caused by information interruption, improving the applicability of coordinated planning of vehicle speed and neutral gliding in closed scenes such as tunnels, and can also increase the proportion of full-process energy-saving control, and improve the energy consumption optimization effect of vehicles under complex road conditions.

[0078] For example, the original waypoints corresponding to the speed limit and the tunnel can be marked by the following formula to obtain the tunnel division point and the speed limit division point: in, Change the flag for speed limit, It is the mark for entering and exiting the tunnel.

[0079] The original road points corresponding to the road top and road valley can be marked by the following formula to obtain the top segmentation point and valley segmentation point: in, is the road elevation, s is the distance from the road to the starting point, and i is the waypoint sequence number.

[0080] Road elevation can also be called road surface elevation, which refers to the vertical height change of the road surface relative to a certain reference horizontal plane, and is used to describe the longitudinal undulating characteristics of the road.

[0081] In this embodiment, discrete waypoints of three-dimensional road information are obtained by using key segmentation waypoints and non-key segmentation waypoints, which can reduce the complexity of waypoint data while increasing the integrity of key information contained in the discrete waypoints. Therefore, when planning the discretized multi-dimensional heterogeneous density state space of the vehicle based on the discrete waypoints to perform coordinated planning of vehicle speed and neutral coasting, the risk of planning errors caused by losing key information at the stage determined based on the discrete waypoints due to frequent changes in speed limits, tunnel scenes and large fluctuations in roads is reduced.

[0082] Based on any of the above embodiments, after solving the optimal control amount based on the discretized multi-dimensional heterogeneous density state space, the method further includes: The original waypoints are used for interpolation processing to be sent to the vehicle for control and for rolling trigger updates; Based on the fact that the angle between the line connecting the real-time GNSS position of the vehicle at the adjacent original waypoint and the line connecting the subsequent waypoints adjacent to the original waypoints is within a preset angle range, determine the vehicle position corresponding to the subsequent waypoint adjacent to the original waypoint, and set the vehicle speed and gear position at the position as the control command at the next moment for vehicle control; In the case where the subsequent waypoints in the adjacent original waypoints are the corresponding discrete waypoints in the second stage, the step of planning the vehicle in a discretized multi-dimensional heterogeneous density state space based on the three-dimensional road information is repeated.

[0083] The preset angle range can be set according to actual needs, and this embodiment does not further limit this. For example, the preset angle range can be less than or equal to 90 degrees. The vehicle position point can be the real-time latitude and longitude of the vehicle.

[0084] Exemplarily, after the interpolation process is performed, a sequence of the inserted original waypoints may be obtained, and based on the sequence, it is determined once whether the connecting line angle is within a preset angle range.

[0085] In this embodiment, a high-precision waypoint sequence is generated by linear interpolation of the original waypoint densification. Combined with the real-time latitude and longitude information on the vehicle side, it is possible to quickly and accurately match the vehicle's current actual position with the recommended waypoint information sent from the cloud, so as to improve the matching degree of control instructions such as the recommended speed and gear position with the specific position of the vehicle and the real-time nature of collaborative planning.

[0086] The cloud control system is a standardized architecture with layered decoupling and cross-domain use. When implementing different cloud-controlled assisted driving applications, special design based on the cloud control system architecture is required to achieve unification and feasibility.

[0087] The cloud control system can connect vehicles, road infrastructure, cloud platforms, pedestrians, vehicles and other traffic participants to achieve real-time data collection, transmission, processing and analysis, so as to provide comprehensive information support and decision-making optimization for intelligent connected vehicles. Building a predictive cruise control system based on the cloud control system has significant advantages.

[0088] The cloud control application platform of the cloud control system can execute the vehicle speed and neutral coasting coordinated planning methods provided by the above methods.

[0089] like Figure 5As shown, the architecture of the cloud control system may include a cloud control basic platform and a cloud control application platform, and the cloud control application platform may be connected to the cloud control basic platform and the vehicle-side platform respectively.

[0090] The cloud control basic platform can provide three-dimensional road information or road map information such as slope, curvature, speed limit, etc., providing data support for optimizing the optimal decision-making planning of predictive cruise vehicles.

[0091] The vehicle-side platform may include an on-board intelligent terminal T-BOX and a vehicle-mounted communication unit (VehicularCommunication Unit, VCU). T-BOX can determine the vehicle's position through the Global Navigation Satellite System (GNSS), receive, collect and forward the collected vehicle motion-power system status information through the signal processing module, and also realize data communication between the signal processing module and the brake energy recovery controller, vehicle speed controller and automatic transmission control unit (Transmission Control Unit, TCU) in the on-board communication device through the controller area network bus technology (Controller Area Network-BUS, CANbus). Data communication can be used for T-BOX to receive the suggestion information from the cloud control application platform, parse it to obtain the real-time suggestion command, and then send the real-time suggestion command to the chassis controller for control, so as to realize cloud-controlled predictive energy-saving cruise control, etc.

[0092] The cloud control application platform can integrate vehicle information such as location, speed, gear, instantaneous energy consumption, and road map information uploaded by the vehicle platform to achieve predictive cruising, provide the vehicle with globally optimized driving suggestions and control strategies, and achieve energy-saving, safe, and efficient intelligent driving. For example, the cloud control application platform may include: Module 1, Module 1 may include a vehicle information library and a vehicle model. The vehicle information library may include system parameter information of different power systems and models such as pure electric trucks, fuel trucks and hybrid trucks. The vehicle model may include a vehicle dynamics model and an energy consumption model constructed based on parameters such as motors, batteries, internal combustion engines, and transmissions in the system parameter information.

[0093] For example, a pure electric heavy-duty truck can be driven by a central motor and equipped with a 4-speed automatic transmission. The power system transmission route is as follows: Figure 6 As shown. The battery system is a battery pack composed of four battery packs connected in series and parallel. The motor controller converts the DC voltage into the AC voltage required by the drive motor. The torque of the drive motor transmits the power to the wheels in the drive axle through the transmission-final reducer to drive the vehicle. In addition, when deceleration is required, the motor controller controls the current to make the motor generate reverse torque and perform regenerative braking, so that the drive motor can recover electric energy while decelerating.

[0094] It should be noted that, in this embodiment, a pure electric heavy-duty truck is used as an example for explanation, but the vehicle speed and neutral coasting coordinated planning method provided by the present invention is not limited to the scenario of heavy-duty trucks driving on highways.

[0095] When the road adhesion coefficient is greater than a specified threshold and the dynamic characteristics of vehicle power transmission have little or no effect on vehicle performance, refer to Figure 7 , we can get the following vehicle longitudinal driving equation and dynamic model: in, The driving force required for the vehicle; is the rolling resistance; is air resistance; is the slope resistance; For acceleration resistance; Output torque for the motor; is the transmission ratio; is the main reducer speed ratio; is the mechanical efficiency of the transmission system; is the wheel radius; is the total vehicle mass; is the acceleration due to gravity; is the rolling resistance coefficient; is the road slope; is the air resistance coefficient; is the windward area; is the air density, is the vehicle speed.

[0096] When the motor torque is negative, it is the conversion efficiency of the feed. The motor power is a function of the motor speed, motor torque and motor efficiency. The motor controller efficiency is measured based on the motor speed and motor torque. and motor efficiency Efficiency values ​​and motor controllers measured at motor speed and motor torque and motor efficiency The efficiency value can be obtained by the motor power model as shown below: in, is the power of the motor, The efficiency of the motor controller and motor efficiency The fitting coefficient of the efficiency value, For motor inverter and motor efficiency The fitting coefficient of the efficiency value, is the motor output torque, is the speed of the motor.

[0097] For example, Can be based on Figure 8 The motor efficiency measured at different motor speeds and positive motor torques is shown. Fig. 9 The motor controller efficiency shown is fitted from the measurements at the same motor speed and positive motor torque. Can be based on Fig.10 The motor efficiency measured at different motor speeds and negative motor torques is shown. Fig.11 The controller efficiency measured at different motor speeds and negative motor torques is fitted as shown. Among them, the controller efficiency under negative motor torque can also be called the motor inverter efficiency. It can be obtained from this Fig.12 The motor power model fitting diagram and Fig.13 The motor feed power model fitting diagram is shown.

[0098] like Fig.14 As shown, when the battery is modeled as an equivalent internal model, the relationship between the power demand of the drive motor and the power output of the battery is as follows: in, is the power consumption of the driving motor, is the battery output power, is the total battery power consumption, For other auxiliary power consumption of the vehicle, is the open circuit voltage, is the internal resistance of the battery.

[0099] For example, based on Fig.14 Shown and Get the total battery power consumption .

[0100] For example, based on Fig.15 The internal resistance data and battery output power of the battery at different remaining power (State Of Charge, SOC) and power are shown, and the total power value of the battery can be obtained and driving energy consumption The formula is as follows: Module 2 is used for waypoint preprocessing and adaptive planning in the distance domain. After obtaining the road map information sent by the cloud control basic platform, module 2 can preprocess the original waypoints in the road map information to reduce the dimension of the waypoint input, and adaptively plan the distance domain for tunnel scenarios, variable speed limit scenarios, etc. based on the preprocessed waypoints to provide useful key information for the predictive cruise algorithm.

[0101] Module 3 is used for rolling iterative control planning of vehicle status to reduce the risk of the vehicle deviating too much from the expected recommended driving due to uncertain environmental interference during driving.

[0102] Module 4 is used to obtain the real-time status of the vehicle so that modules 2 and 3 can perform vehicle-map matching, rolling iterative control, etc. based on vehicle information such as position, speed, gear position and instantaneous energy consumption.

[0103] like Fig.16 As shown, the vehicle-road cooperative control method based on vehicle-side positioning and map waypoints in module 5 triggers each other. After long-distance road prediction, the original waypoints corresponding to the road section are obtained, and then the waypoint segmentation processing can be performed in the predictive cruise control (PCC) planning layer based on waypoint segmentation to obtain discrete waypoints. Module 5 can obtain the road map based on the GNSS position of the vehicle in a rolling manner, so as to package the planning instruction information and control the state of the vehicle within the rolling control distance under the control instruction, and realize cloud-controlled predictive energy-saving cruise control.

[0104] By performing linear interpolation processing on the original waypoints, a sequence of inserted original waypoints can be obtained. The instruction parsing layer based on the real-time position of the vehicle can perform instruction parsing based on the real-time position, and judge that the connecting line angle is within the preset angle range, and when the dynamic rear waypoint is the discrete waypoint P1 corresponding to the second stage, module 5 performs a new round of planning based on the mutual triggering iterative control of the dynamic waypoint, or the response of the rolling iterative control module, and calculates in real time the optimal power system and motion state recommendations for future vehicle driving.

[0105] The vehicle speed and neutral coasting coordinated planning device provided by the present invention is described below. The vehicle speed and neutral coasting coordinated planning device described below and the vehicle speed and neutral coasting coordinated planning method described above can correspond to each other.

[0106] Fig.17 The structural schematic diagram of a vehicle speed and neutral coasting coordinated planning device is shown as an example. Fig.17 As shown, the device comprises: The state space planning module 1701 is used to plan the speed and gear sequence of the vehicle in the future based on the three-dimensional road information in the constructed discretized multi-dimensional heterogeneous density state space; the discretized multi-dimensional heterogeneous density state space includes a phase state, a speed state and a gear state, the gear state includes a neutral gear and an in-gear gear, and the speed discrete interval of the neutral gear is smaller than the speed discrete interval of the in-gear gear; The cost model building module 1702 is used to determine the vehicle speed state corresponding to each stage state transition according to the discretized multi-dimensional heterogeneous density state space, the state transition of the neutral layer by the coasting vehicle speed; determine the state point corresponding to the vehicle speed state in each stage of the stage state according to the discrete interval of the vehicle speed in the gear at the gear layer, and establish a cost model based on the transfer cost of the state point; A local cost determination module 1703 is used to determine the state point with the minimum transfer cost in each stage based on the cost model, and obtain the corresponding control quantity and state quantity; the control quantity includes the gear position and torque, and the state quantity includes the vehicle speed; The overall cost determination module 1704 is used to solve the optimal control quantity based on the discretized multi-dimensional heterogeneous density state space to dynamically adjust the vehicle speed and gear position of the vehicle.

[0107] Based on any of the above embodiments, the local cost determination module 1703 includes: A cost determination unit is used to calculate a first transfer cost of a state point in a neutral state at each stage based on the cost model; and calculate a second transfer cost of a state point in a gear state at each stage based on the cost model; Cost comparison unit for: Determine a neutral pre-selected state point at which the first transfer cost is the smallest in neutral state at each stage, and determine a gear pre-selected state point at which the second transfer cost is the smallest in gear state at each stage; When the first transfer cost of the neutral pre-selected state point in the target phase is less than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the neutral pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; or when the first transfer cost of the neutral pre-selected state point in the target phase is greater than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the in-gear pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; Repeat the step of determining the state point with the minimum transfer cost in the target stage to determine the state point with the minimum transfer cost in each stage.

[0108] Based on any of the above embodiments, the vehicle speed and neutral coasting coordinated planning device further includes a state point expansion unit, which is used to: Determining a state transfer equation based on a preset vehicle power system model; the state transfer equation includes a gear variable and a torque variable; Determine the glide speed of the target stage based on the current state point and the state transfer equation when the gear variable is in neutral; the glide speed is the actual speed calculated and determined by the state transfer equation at the current state point; The speed deviation between the taxiing speed and the speed corresponding to each discrete state point in the target stage in the neutral state in the discretized multi-dimensional heterodensity state space is determined to determine the target state point.

[0109] Based on any of the above embodiments, the local cost determination module 1703 is specifically configured to: The cost model is reversely calculated to determine the state point with the minimum transfer cost in each stage.

[0110] The control sequence of the vehicle is obtained based on the control quantity, and the state sequence of the vehicle is obtained based on the state quantity, specifically including: A forward search is performed from the starting stage to the final stage of the stage state, and the control sequence of the vehicle is obtained based on the control amount of the state point with the minimum transfer cost in each stage, and the state sequence of the vehicle is obtained based on the state amount of the state point with the minimum transfer cost in each stage.

[0111] Based on any of the above embodiments, the cost model building module 1702 is specifically used for: Determine the transfer energy consumption, driving time and speed deviation between the state point speed and the cruising speed at each stage based on a preset vehicle power system model; A cost model is established by weighting the transfer energy consumption, the travel time and the speed deviation.

[0112] Based on any of the above embodiments, the state space planning module 1701 is specifically used for: Traversing the original waypoints of the three-dimensional road information, marking the original waypoints corresponding to preset key road features as key segmentation waypoints, and marking the original waypoints corresponding to preset geometric features as non-key segmentation waypoints; Obtaining discrete waypoints of the three-dimensional road information based on the key segmentation waypoints and the non-key segmentation waypoints; The stage state of the vehicle is planned according to the discrete waypoints, and the vehicle speed state and gear state of each stage under the stage state are planned to obtain a discretized multi-dimensional heterodensity state space of the vehicle.

[0113] Based on any of the above embodiments, the vehicle speed and neutral coasting coordinated planning device further includes a rolling control module, which is used to: The original waypoints are used for interpolation processing to be sent to the vehicle for control and for rolling trigger updates; Based on the fact that the angle between the line connecting the real-time GNSS position of the vehicle at the adjacent original waypoint and the line connecting the subsequent waypoints adjacent to the original waypoints is within a preset angle range, determine the vehicle position corresponding to the subsequent waypoint adjacent to the original waypoint, and set the vehicle speed and gear position at the position as the control command at the next moment for vehicle control; In the case where the subsequent waypoints in the adjacent original waypoints are the corresponding discrete waypoints in the second stage, the step of planning the vehicle in a discretized multi-dimensional heterogeneous density state space based on the three-dimensional road information is repeated.

[0114] Fig.18 A schematic diagram of the structure of a vehicle is shown as an example. Fig.18 As shown, the electronic device may include: a processor 1810, a communication interface 1820, a memory 1830 and a communication bus 1840, wherein the processor 1810, the communication interface 1820 and the memory 1830 communicate with each other through the communication bus 1840. The processor 1810 may call the logic instructions in the memory 1830 to execute the vehicle speed and neutral coasting collaborative planning method, the method comprising: in a constructed discrete multi-dimensional heterogeneous density state space, planning the vehicle speed and gear sequence of the vehicle's future travel based on three-dimensional road information; the discrete multi-dimensional heterogeneous density state space includes a stage state, a vehicle speed state and a gear state, the gear state includes neutral and in gear, the vehicle speed discrete interval of the neutral gear is smaller than the vehicle speed discrete interval of the in gear; according to the discrete multi-dimensional heterogeneous density state space, the state transfer of the neutral layer is achieved through coasting The vehicle speed determines the vehicle speed state corresponding to the state transfer in each stage; at the gear layer, the state point corresponding to the vehicle speed state in each stage of the stage state is determined according to the discrete intervals of the vehicle speed in the gear, and a cost model is established based on the transfer cost of the state point; based on the cost model, the state point with the minimum transfer cost in each stage is determined, and the corresponding control quantity and state quantity are obtained; the control quantity includes gear position and torque, and the state quantity includes vehicle speed; based on the discretized multi-dimensional heterogeneous density state space, the optimal control quantity is solved to dynamically adjust the vehicle speed and gear position of the vehicle.

[0115] In addition, the logic instructions in the above-mentioned memory 1830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0116] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle speed and neutral coasting collaborative planning method provided by the above methods. The method includes: in a constructed discrete multi-dimensional heterogeneous density state space, planning the vehicle speed and gear sequence for future driving based on three-dimensional road information; the discretized multi-dimensional heterogeneous density state space includes a stage state, a vehicle speed state and a gear state, the gear state includes neutral and in gear, and the discrete interval of the vehicle speed in the neutral gear is smaller than the discrete interval of the vehicle speed in the in gear. interval; according to the discretized multi-dimensional heterogeneous density state space, the state transfer of the neutral layer determines the vehicle speed state corresponding to each stage state transfer through the coasting speed; in the gear layer, the state point corresponding to the vehicle speed state in each stage of the stage state is determined according to the discrete interval of the vehicle speed in the gear, and a cost model is established based on the transfer cost of the state point; based on the cost model, the state point with the minimum transfer cost in each stage is determined, and the corresponding control quantity and state quantity are obtained; the control quantity includes gear position and torque, and the state quantity includes vehicle speed; based on the discretized multi-dimensional heterogeneous density state space, the optimal control quantity is solved to dynamically adjust the vehicle speed and gear position of the vehicle.

[0117] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the vehicle speed and neutral gear coasting coordinated planning method provided by the above methods, the method comprising: in a constructed discrete multi-dimensional heterogeneous density state space, planning the vehicle speed and gear sequence of the vehicle's future travel based on three-dimensional road information; the discrete multi-dimensional heterogeneous density state space includes a stage state, a vehicle speed state and a gear state, the gear state includes neutral and in gear, the vehicle speed discrete interval of the neutral gear is smaller than the vehicle speed discrete interval of the in gear; according to the discrete multi-dimensional heterogeneous density state space, The state space is constructed, and the state transfer of the neutral layer determines the vehicle speed state corresponding to each stage state transfer through the coasting vehicle speed; in the gear layer, the state point corresponding to the vehicle speed state in each stage of the stage state is determined according to the discrete intervals of the vehicle speed in the gear, and a cost model is established based on the transfer cost of the state point; based on the cost model, the state point with the minimum transfer cost in each stage is determined, and the corresponding control quantity and state quantity are obtained; the control quantity includes gear position and torque, and the state quantity includes vehicle speed; based on the discretized multi-dimensional heterogeneous density state space, the optimal control quantity is solved to dynamically adjust the vehicle speed and gear position of the vehicle.

[0118] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0119] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle speed and neutral coasting coordinated planning method, characterized in that: include: In the constructed discretized multi-dimensional heterogeneous density state space, the speed and gear sequence of the vehicle's future travel is planned based on the three-dimensional road information; the discretized multi-dimensional heterogeneous density state space includes a phase state, a speed state and a gear state, the gear state includes a neutral gear and an in-gear gear, and the speed discrete interval of the neutral gear is smaller than the speed discrete interval of the in-gear gear; According to the discretized multi-dimensional heterogeneous density state space, the state transition of the neutral gear layer determines the vehicle speed state corresponding to each stage state transition through the coasting vehicle speed; the gear layer determines the state point corresponding to the vehicle speed state in each stage of the stage state according to the discrete interval of the vehicle speed in the gear, and establishes a cost model based on the transfer cost of the state point; Determine the state point with the minimum transfer cost in each stage based on the cost model, and obtain the corresponding control quantity and state quantity; the control quantity includes gear position and torque, and the state quantity includes vehicle speed; Based on the discretized multi-dimensional heterogeneous density state space, the optimal control quantity is solved to dynamically adjust the vehicle speed and gear position of the vehicle.

2. The vehicle speed and neutral coasting coordinated planning method according to claim 1 is characterized in that: Determine the state point with the minimum transfer cost in each stage based on the cost model, specifically including: Calculate the first transfer cost of each stage of the state point in the neutral state based on the cost model; calculate the second transfer cost of each stage of the state point in the gear state based on the cost model; Determine a neutral pre-selected state point at which the first transfer cost is the smallest in neutral state at each stage, and determine a gear pre-selected state point at which the second transfer cost is the smallest in gear state at each stage; When the first transfer cost of the neutral pre-selected state point in the target phase is less than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the neutral pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; or when the first transfer cost of the neutral pre-selected state point in the target phase is greater than the second transfer cost of the in-gear pre-selected state point in the corresponding phase, the in-gear pre-selected state point is determined to be the state point with the minimum transfer cost in the target phase; Repeat the step of determining the state point with the minimum transfer cost in the target stage to determine the state point with the minimum transfer cost in each stage.

3. The vehicle speed and neutral coasting coordinated planning method according to claim 2 is characterized in that: Before calculating the first transfer cost of the state point in the neutral state in each stage based on the cost model, the method further includes: Determining a state transfer equation based on a preset vehicle power system model; the state transfer equation includes a gear variable and a torque variable; Determine the glide speed of the target stage based on the current state point and the state transfer equation when the gear variable is in neutral; the glide speed is the actual speed calculated and determined by the state transfer equation at the current state point; The speed deviation between the taxiing speed and the speed corresponding to each discrete state point in the target stage in the neutral state in the discretized multi-dimensional heterodensity state space is determined to determine the target state point.

4. The vehicle speed and neutral coasting coordinated planning method according to claim 1, characterized in that: Determine the state point with the minimum transfer cost in each stage based on the cost model, specifically including: Reverse calculation is performed on the cost model to determine the state point with the minimum transfer cost in each stage; The control sequence of the vehicle is obtained based on the control quantity, and the state sequence of the vehicle is obtained based on the state quantity, specifically including: A forward search is performed from the starting stage to the final stage of the stage state, and the control sequence of the vehicle is obtained based on the control amount of the state point with the minimum transfer cost in each stage, and the state sequence of the vehicle is obtained based on the state amount of the state point with the minimum transfer cost in each stage.

5. The vehicle speed and neutral coasting coordinated planning method according to claim 1, characterized in that: A cost model is established based on the transfer cost of the state point in each stage under the stage state, specifically including: Determine the transfer energy consumption, driving time and speed deviation between the state point speed and the cruising speed at each stage based on a preset vehicle power system model; A cost model is established by weighting the transfer energy consumption, the travel time and the speed deviation.

6. The vehicle speed and neutral coasting coordinated planning method according to claim 1, characterized in that: Discrete multi-dimensional heterogeneous density state space for vehicle planning based on three-dimensional road information, including: Traversing the original waypoints of the three-dimensional road information, marking the original waypoints corresponding to preset key road features as key segmentation waypoints, and marking the original waypoints corresponding to preset geometric features as non-key segmentation waypoints; Obtaining discrete waypoints of the three-dimensional road information based on the key segmentation waypoints and the non-key segmentation waypoints; The stage state of the vehicle is planned according to the discrete waypoints, and the vehicle speed state and gear state of each stage under the stage state are planned to obtain a discretized multi-dimensional heterodensity state space of the vehicle.

7. The vehicle speed and neutral coasting coordinated planning method according to claim 6, characterized in that: After solving the optimal control quantity based on the discretized multi-dimensional heterogeneous density state space, the method further includes: The original waypoints are used for interpolation processing to be sent to the vehicle for control and for rolling trigger updates; Based on the fact that the angle between the line connecting the real-time GNSS position of the vehicle at the adjacent original waypoint and the line connecting the subsequent waypoints adjacent to the original waypoints is within a preset angle range, the vehicle position corresponding to the subsequent waypoint adjacent to the original waypoint is determined, and the vehicle speed and gear position at the position are used as the control command at the next moment for vehicle control; In the case where the subsequent waypoints in the adjacent original waypoints are the corresponding discrete waypoints in the second stage, the step of planning the vehicle in a discretized multi-dimensional heterogeneous density state space based on the three-dimensional road information is repeated.

8. A vehicle speed and neutral coasting coordinated planning device, characterized in that: include: A state space planning module is used to plan the speed and gear sequence of the vehicle's future travel based on the three-dimensional road information in the constructed discretized multi-dimensional heterogeneous density state space; the discretized multi-dimensional heterogeneous density state space includes a phase state, a speed state and a gear state, the gear state includes a neutral gear and an in-gear gear, and the speed discrete interval of the neutral gear is smaller than the speed discrete interval of the in-gear gear; A cost model building module is used to determine the vehicle speed state corresponding to each stage state transfer according to the discretized multi-dimensional heterogeneous density state space, the state transfer of the neutral layer by the coasting vehicle speed; determine the state point corresponding to the vehicle speed state in each stage of the stage state according to the discrete interval of the vehicle speed in the gear at the gear layer, and establish a cost model based on the transfer cost of the state point; A local cost determination module, used to determine the state point with the minimum transfer cost in each stage based on the cost model, and obtain the corresponding control quantity and state quantity; the control quantity includes gear position and torque, and the state quantity includes vehicle speed; The overall cost determination module is used to solve the optimal control quantity based on the discretized multi-dimensional heterogeneous density state space to dynamically adjust the vehicle speed and gear position.

9. A vehicle comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the vehicle speed and neutral coasting coordinated planning method as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle speed and neutral coasting coordinated planning method as described in any one of claims 1 to 7 is implemented.

Images