CN-121989699-A - Electric vehicle mileage anxiety management

CN121989699ACN 121989699 ACN121989699 ACN 121989699ACN-121989699-A

Abstract

A robust mileage prediction system is presented that uses a mileage prediction model trained on data related to energy usage of an Electric Vehicle (EV) to estimate the mileage of the vehicle during operation. The mileage predictive model may require a greater number of inputs than the OEM mileage estimator of the EV setting may consider. The predicted mileage generated by the mileage prediction system may then be compared with the estimated mileage of the OEM mileage estimator and/or combined into an integrated display to provide the driver with confirmation of the estimated mileage, which may reduce the driver's mileage anxiety. In addition, the proposed mileage prediction system may generate a recommendation on how to maximize (e.g., maintain or increase) the predicted mileage by adjusting the operation of the vehicle or coordinating the operation of the vehicle with other vehicles, traffic signals, etc.

Inventors

S. A. Saihara
Y.H.Li
S. Deyi
M. P.K. Yatajiri

Assignees

哈曼国际工业有限公司

Dates

Publication Date: 20260508
Application Date: 20251103
Priority Date: 20241108

Claims (15)

1. A method for a controller of an Electric Vehicle (EV), the method comprising: collecting data from sensors and systems of the EV during operation of the EV; Predicting a mileage of the EV based on the collected data using a mileage prediction model, and further predicting a plurality of mileage gains of the EV associated with performing one or more mileage maximization actions of the EV based on the collected data, each mileage gain being a predicted increase in the mileage of the EV due to performing a corresponding mileage maximization action of the one or more mileage maximization actions; Comparing the predicted mileage with an estimated mileage of the EV generated by a mileage estimator included in the EV, and In response to determining that a difference between the predicted mileage and the estimated mileage is greater than a threshold difference, displaying the predicted mileage on a display of the EV, and One or more recommendations for the one or more mileage maximization actions to be performed at the EV to maintain or increase the mileage of the EV are displayed on the display, the one or more mileage maximization actions being recommended based on predicted mileage gains of the one or more mileage maximization actions output by the mileage prediction model.
2. The method of claim 1, wherein the data collected from the sensors and systems during operation of the EV comprises: operating data of the EV from on-load sensors including battery state of charge (SOC), energy consumption data, vehicle speed, load, braking and route data, and Static data of the surrounding environment of the EV, including route and geographic data, EV charging infrastructure data, and Dynamic data, including weather, road conditions, and traffic data.
3. The method of claim 1, wherein the one or more mileage maximization actions include a vehicle maneuver recommendation and a co-drive recommendation.
4. The method of claim 3, wherein the vehicle maneuver recommendation comprises one or more of: recommended adjustment of the speed of the EV; Recommended lane change to the EV, and Recommended application of brakes to the EV.
5. The method of claim 3, wherein the co-driving recommendation comprises one or more of: Engaging in a platoon drive, wherein operation of the EV is coordinated with one or more nearby vehicles; The traffic signal assist operation of the EV, wherein the operation of the EV is adjusted based on one or more upcoming traffic signals or the timing of the one or more upcoming traffic signals is adjusted based on the operation of the EV, and The EV is redirected based on traffic, road conditions, and/or weather conditions.
6. The method of claim 5, wherein the co-driving recommendation is generated based on data acquired at an edge device located at an infrastructure element along a route of the EV, and displaying the one or more mileage maximization actions output by the mileage prediction model on the display further comprises receiving data or operation instructions from the edge device.
7. The method of claim 6, wherein the mileage prediction model is stored at a cloud-based mileage prediction system, and predicting the mileage of the EV based on the collected data using the mileage prediction model further comprises transmitting the collected data to the cloud-based mileage prediction system and receiving the predicted mileage of the EV from the cloud-based mileage prediction system.
8. The method of claim 7, wherein a copy of the mileage prediction model is stored in a memory of one of the edge device and the EV, and predicting the mileage of the EV using the mileage prediction model further comprises predicting the mileage of the EV at one of the edge device and the EV.
9. The method of claim 7, wherein the mileage prediction model is a Machine Learning (ML) or Deep Learning (DL) model trained at the cloud-based mileage prediction system using data collected from a plurality of EVs communicatively coupled with the cloud-based mileage prediction system.
10. The method of claim 9, further comprising further training the ML or DL model at the EV or at the edge device after training the ML or DL model at the cloud-based mileage prediction system, and updating weights of the ML or DL model at the EV or at the edge device based on data acquired at the EV or at the edge device, respectively.
11. The method of claim 7, wherein the mileage prediction model is a rule-based system generated by a human expert.
12. The method of claim 1, wherein the EV is configured to operate in an autonomous or semi-autonomous mode, and the method further comprises performing the one or more mileage maximization actions without human intervention, the method further comprising displaying the predicted mileage and the estimated mileage in a single integrated display element.
13. A mileage prediction system for an Electric Vehicle (EV), the mileage prediction system comprising: A processor and a memory storing instructions that, when executed, cause the processor to: In a first stage, training a Machine Learning (ML) model based on data collected from sensors and systems of a plurality of EVs during operation of the plurality of EVs to output a predicted mileage for each of the plurality of EVs and additionally output a predicted mileage increase achievable by performing one or more of a plurality of predetermined mileage maximization actions at the EVs, and In the second stage: receiving data collected from sensors and systems of the EV during operation of the EV; Predicting mileage of the EV based on the received data using a trained ML model, and The predicted mileage and the predicted mileage increase are transmitted to the EV.
14. The mileage prediction system according to claim 13, wherein the data received from the EV in the second phase includes: operating data of the EV including energy consumption, speed, load, braking and route data; Weather, road conditions and traffic data collected by external sensors and/or cameras of the EV, and Weather, road conditions, and traffic data for the EV are transmitted by edge devices installed in infrastructure elements located on the route of the vehicle.
15. The mileage prediction system of claim 14, wherein the predetermined mileage maximization action includes at least one of a vehicle maneuver recommendation to change a speed, lane, or route of the vehicle, and a co-drive recommendation to coordinate operation of the EV with other EVs traveling on the route of the EV.

Description

Electric vehicle mileage anxiety management Technical Field Embodiments of the subject matter disclosed herein relate to reducing driver anxiety related to the mileage an electric vehicle can travel before recharging. Background As an alternative to conventional vehicles operating on fossil fuels, electric Vehicles (EVs) are becoming increasingly popular and cheaper. However, one of the major challenges faced by EV drivers is uncertainty and anxiety about the remaining battery charge and driving range of their vehicles, especially during long distance trips or on unfamiliar routes. This is called mileage anxiety, and it may affect the driving behavior, comfort, and satisfaction of EV drivers. Further, mileage anxiety may limit adoption and use of EVs because drivers may prefer to adhere to using conventional vehicles with more reliable and more available fuel replenishment options. EVs are typically equipped with a mileage estimator functionality that displays an estimated mileage of the EV based on a state of charge (SOC) of a battery of the EV. However, the estimated mileage may be inaccurate because road conditions, traffic conditions, weather conditions, and other driving conditions may change during operation of the EV. Disclosure of Invention The present disclosure solves the above identified problems, at least in part, by a method for a controller of an Electric Vehicle (EV), the method comprising collecting data from sensors and systems of the EV during operation of the EV, predicting a mileage of the EV based on the collected data using a mileage prediction model, and further predicting, based on the collected data, a plurality of mileage gains of the EV associated with performing one or more mileage maximization actions of the EV, each mileage gain being a predicted increase in mileage of the EV resulting from performing a corresponding one of the one or more mileage maximization actions, comparing the predicted mileage with an estimated mileage of the EV generated by a mileage estimator included in the EV, and displaying, on a display of the EV, the predicted mileage in response to determining that a difference between the predicted mileage and the estimated mileage is greater than a threshold difference, one or more mileage maximization actions for maintaining or increasing the mileage to be performed at the EV, the one or more recommended actions being the predicted mileage maximization actions based on the one or more mileage maximization models. The above advantages and other advantages and features of the present description will be readily apparent from the following detailed description, taken alone or in conjunction with the accompanying drawings. It should be understood that the above summary is provided to introduce in simplified form some concepts that are further described in the detailed description. It is not meant to identify key or essential features of the claimed subject matter, the scope of which is defined uniquely by the claims that follow the detailed description. Furthermore, the claimed subject matter is not limited to implementations that solve any disadvantages noted above or in any part of this disclosure. Drawings Various aspects of the disclosure may be better understood upon reading the following detailed description and upon reference to the drawings in which: FIG. 1 illustrates an exemplary EV charging ecosystem; FIG. 2 illustrates a schematic diagram of components of an exemplary electric vehicle and an exemplary mileage prediction system including the electric vehicle charging ecosystem of FIG. 1; FIG. 3 illustrates a schematic diagram of an exemplary mileage prediction model used by the mileage prediction system; FIG. 4 is a flow chart illustrating an exemplary method for predicting the mileage of an EV and providing an option to the driver of the EV for maximizing the mileage; FIG. 5 is a flow chart illustrating an exemplary method for increasing mileage of an EV using co-driving, and FIG. 6 illustrates an exemplary graphical user interface for displaying predicted mileage of an EV. The drawings illustrate specific aspects of the described systems and methods. The accompanying drawings illustrate and explain the structures, methods and principles described herein in connection with the following description. In the drawings, the size of the elements may be exaggerated or otherwise modified for clarity. Well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the described components, systems, and methods. Detailed Description A plug-in Electric Vehicle (EV) operates on power stored in one or more batteries of the EV. When the stored power decreases below the threshold, the one or more batteries may be recharged at the charging station. The current amount of battery power available to the EV may be displayed to the driver so that the driver may determine when to recharge the EV. In addition, current syste