Search

CN-121986044-A - Method for predicting vehicle speed

CN121986044ACN 121986044 ACN121986044 ACN 121986044ACN-121986044-A

Abstract

The invention relates to a method (21) implemented in a computer (4) placed on a vehicle (2) for predicting the speed of the vehicle (2) on a route between a departure point and an arrival point, the computer (4) being connected to a system (8) for managing static and/or dynamic data related to road infrastructure and/or road traffic, the computer (4) being configured to calculate an optimal speed profile of the vehicle (2) according to a predefined calculation method, said calculation method minimizing the hamiltonian of a set of equations modeling the driving of the vehicle (2) and being configured to allow optimization of criteria taking into account the energy consumption of the vehicle (2) and the duration of the route, the computer (4) storing one or more records of past or recent driving phases of the vehicle (2).

Inventors

  • MARIANO SANS

Assignees

  • 舍弗勒技术股份两合公司

Dates

Publication Date
20260505
Application Date
20241210
Priority Date
20231215

Claims (10)

  1. 1. A method (21) implemented in a computer (4) placed on a vehicle (2) for predicting the speed of the vehicle (2) on a route between a departure point and an arrival point, the vehicle (2) being further provided with a navigation and positioning system (12) of the vehicle (2) connected to the computer (4), the computer (4) of the vehicle (2) being further connected to a system (8) for managing static and/or dynamic data related to road infrastructure and/or road traffic, said static and/or dynamic data related to the road infrastructure and/or road traffic being provided as input to the computer (4), the route of the vehicle (2) within a predetermined distance being predefined or predicted within the computer (4), the computer (4) being configured to calculate an optimal speed profile of the vehicle (2) according to a predefined calculation method, said calculation method minimizing the hamiltonian of a set of modeling the driving of the vehicle (2) and being configured to allow the optimization of the driving of the vehicle (2) in view of the past characteristics of the vehicle (2) and the past characteristics (21) of the method comprising the most recent step (21) of storing the most recent step(s): -determining (22) the driving style of the driver of the vehicle (2) from one or more recordings of past or recent driving phases of the vehicle (2); -defining (24) a series of notable points of the route, the points being characterized by a stop of the vehicle (2) or a reduction in speed of the vehicle (2), wherein the series of notable points divide the route into a series of parts; -calculating (26) an optimal speed profile of the vehicle (2) according to said predefined calculation method for each part of the route, the duration of the route being weighted using weighting coefficients in the hamiltonian volumes of said predefined calculation method; -adapting (28) said weighting coefficients according to the determined driving style of the driver of the vehicle (2), said adapting step (28) providing an adapted speed profile of the vehicle (2) for each part of the route; -providing (30) said adapted speed profile for each part of the route as a prediction of the speed of the vehicle (2) over said part of the route.
  2. 2. The method (21) as claimed in claim 1, characterized in that the predefined calculation method is a calculation method implementing the pointrisia maximum value principle.
  3. 3. The method (21) as claimed in claim 1 or 2, characterized in that the step (22) of determining the driving style of the driver of the vehicle (2) is performed by comparing the actual speed profile of the vehicle (2) with the optimal speed profile of the vehicle (2) calculated using the predefined calculation method in the one or more recordings of past or recent driving phases of the vehicle (2).
  4. 4. A method (21) as claimed in any one of claims 1 to 3, characterized in that the step (28) of adapting the weighting coefficient according to a driving style determined for the driver of the vehicle (2) is performed according to a scale of continuous or discrete values.
  5. 5. The method (21) as set forth in any of claims 1-4, characterized in that the step (28) of adapting the weighting coefficient according to a driving style determined for a driver of the vehicle (2) is performed via closed loop feedback correction.
  6. 6. A method (20) implemented in a computer (4) placed on a vehicle (2) for optimizing the energy consumption of the vehicle (2) on a route between a departure point and an arrival point, the vehicle (2) being further provided with a navigation and positioning system (12) of the vehicle (2) connected to the computer (4), the computer (4) of the vehicle (2) being further connected to a system (8) for managing static and/or dynamic data related to road infrastructure and/or road traffic, said static and/or dynamic data related to the road infrastructure and/or road traffic being provided as input to the computer (4), the route of the vehicle (2) within a predetermined distance being predefined or predicted within the computer (4), the computer (4) being configured to calculate an optimal speed profile of the vehicle (2) according to a predefined calculation method, said calculation method minimizing the Hamiltonian amount of a set modeling the driving of the vehicle (2) and being configured to allow the calculation of the most recent past characteristics of the vehicle (2) or the most recent characteristics of the vehicle (4) to be recorded, the method further comprises the sub-method (21) for predicting the speed of the vehicle (2) as claimed in any one of claims 1 to 5, and the step (32) of taking into account the predicted speed of the vehicle (2) on each part of the route, in order to apply or recommend said predicted speed on said part of the route to the vehicle.
  7. 7. A method implemented in a computer (4) placed on a vehicle (2) for controlling the speed of the vehicle (2), the vehicle (2) being further provided with a navigation and positioning system (12) and a powertrain of the vehicle (2) both connected to the computer (4), the computer (4) of the vehicle (2) being further connected to a system (8) for managing static and/or dynamic data related to road infrastructure and/or road traffic, said static and/or dynamic data related to the road infrastructure and/or road traffic being provided as input to the computer (4), the route of the vehicle (2) within a predetermined distance being predefined or predicted within the computer (4), the computer (4) being configured to calculate an optimal speed profile of the vehicle (2) according to a predefined calculation method, said calculation method minimizing the hamiltonian of a set of equations modeling the driving of the vehicle (2) and being configured to allow a further optimization of the driving duration of the vehicle (2) taking into account the vehicle (2) and the vehicle (2) consumption, said method comprising a more recent optimization step (21) of the vehicle (2) being recorded as a more recent method or as a function of the optimization step (4), and a step (34) of transmitting to the powertrain of the vehicle (2) a speed command established according to the predicted speed of the vehicle (2) under consideration.
  8. 8. A computer (4) intended to be placed on a vehicle (2), wherein a route of the vehicle (2) within a predetermined distance is predefined or predicted within the computer (4), the computer (4) being configured to calculate an optimal speed profile of the vehicle (2) according to a predefined calculation method, said calculation method minimizing the hamiltonian amount of a set of equations modeling the driving of the vehicle (2) and being configured to optimize a criterion taking into account the energy consumption of the vehicle (2) and the duration of the route, the computer (4) storing one or more records of past or recent driving phases of the vehicle (2), characterized in that the computer (4) comprises means for implementing the method (21) for predicting the speed of the vehicle (2) as claimed in any one of claims 1 to 5 and/or the method (20) for optimizing the energy consumption of the vehicle (2) and/or the method for controlling the speed of the vehicle (2) as claimed in claim 7.
  9. 9. Vehicle (2), in particular motor vehicle, characterized in that the vehicle (2) comprises a computer (4) as claimed in claim 8 and a navigation and positioning system (12) of the vehicle (2) connected to the computer (4), the computer (4) being connectable to a system (8) for managing static and/or dynamic data relating to road infrastructure and/or road traffic.
  10. 10. Computer program product downloadable from a communication network and/or stored on a computer-readable medium and/or executable by a processor, characterized in that it comprises program instructions configured to implement the method (21) for predicting the speed of a vehicle (2) according to any one of claims 1 to 5 and/or the method (20) for optimizing the energy consumption of the vehicle (2) according to claim 6 and/or the steps of the method for controlling the speed of the vehicle (2) according to claim 7 when said instructions are executed on the computer (4) according to claim 8.

Description

Method for predicting vehicle speed Technical Field The present invention relates to a method for predicting a speed of a vehicle. The method is implemented in a computer placed on the vehicle. The invention also relates to a method for optimizing the energy consumption of a vehicle implemented in a computer placed on the vehicle, the method comprising such a sub-method for predicting the speed of the vehicle. The invention also relates to a method for controlling the speed of a vehicle implemented in a computer placed on the vehicle, the method comprising such a sub-method for optimizing the energy consumption of the vehicle. The invention also relates to a computer intended to be placed on board a vehicle, comprising means for implementing the steps of such a method for predicting the speed of a vehicle, and to a vehicle, in particular a motor vehicle, on which such a computer is mounted. The vehicle is typically, but not limited to, an autonomous or semi-autonomous vehicle. Finally, the invention relates to a computer program product comprising program instructions configured to implement the steps of such a method for predicting the speed of a vehicle. Background In motor vehicles, it is known practice to optimise the energy consumption of the powertrain on a given or predicted route. Such optimization may be done for fuel, electrical energy, hydrogen consumption (in the case of a fuel cell equipped vehicle) or for two or three of these criteria simultaneously. It is well known that optimization can be performed using a principle known as the pointrisia maximum value principle (PMP). This approach involves minimizing the hamiltonian (or hamiltonian amount) based on criteria to be optimized (e.g., the amount of fuel or hydrogen or even the electrical energy consumed) and a description of the dynamics of the system. The dynamics of the system are defined based on the state of various variables of the vehicle (speed of the vehicle, state of charge of the battery and/or super capacitor, temperature, etc.) and various inputs or setpoints (torque setpoints to be applied by the internal combustion engine or by the one or more electric machines to the wheels of the vehicle, torque setpoints to be applied by the one or more motors of the generator, and/or power or current setpoints of the fuel cell, and/or even setpoints for heating the catalytic converter, and/or even setpoints for controlling the cooling circuit, etc.). The hamiltonian is minimized to determine a set point that enables minimal consumption of fuel or hydrogen and/or electrical energy. The hamiltonian amount determined in this way is then minimized. In other words, the values of these setpoints when the value of hamiltonian is the lowest are selected and applied to the vehicle. Thus, these setpoint values are determined in real time based on the current state of the system. The application of such a PMP model thus uses an internal model describing the dynamics of the system to be controlled (in this case the motor vehicle and its powertrain) via differential equations representing the system. Thus, such PMP models are mainly based on an optimal open-loop control strategy that computes an optimal control solution based on predictions of the internal model, with very little feedback from the current measurements on the system. In this context, it may be useful to predict the speed of a vehicle by means of the vehicle's computer and be performed in a given or planned driving scenario, which scenario may typically be provided by a navigation system (which destination may be provided by the driver when the destination is known, or may be inferred by the vehicle assistance system) or by a "electronic information horizon" (or "eHorizon") type of system (which is conventionally based on an ADASIS (advanced driver assistance system interface specification) data format standard for predictive driving assistance systems, or on any other type of device) which provides information about the predicted route characteristics "ahead of the vehicle" based on available data, the position of the vehicle and driving conditions, which information may be used for short-, medium-or long-term time predictions. When the criteria to be optimized take into account the energy consumption of the vehicle and the duration of the route, it is necessary to provide a method for predicting the speed of the vehicle on the route between the departure point and the arrival point, allowing a short-, medium-or long-term temporal prediction of the speed of the vehicle. To this end, several solutions are known, such as statistical analysis (based on speed recordings on observed road segments and regulated by traffic conditions, schedules, etc.), analytical modeling (based on certain behavioral models of the driver, vehicle performance capabilities, route characteristics, traffic conditions, etc.), fuzzy logic (based on recent driving phases modeling the driver's activities on the pedals