Search

EP-4620765-B1 - METHOD AND APPARATUS FOR AUTOMATICALLY GENERATING A SPEED PROFILE OF A VEHICLE

EP4620765B1EP 4620765 B1EP4620765 B1EP 4620765B1EP-4620765-B1

Inventors

  • BERNES-LASSERRE, Thomas
  • PAPADOMICHELAKIS, Georgios
  • De Smet, Jeroen

Dates

Publication Date
20260513
Application Date
20240320

Claims (13)

  1. A computer-implemented method (20) for automatically generating a speed profile of a vehicle (1) to be driven on a predetermined path, the method comprising the following steps: - collecting a first set of data representative of environmental conditions at waypoints along the predetermined path (21), each distinct environmental condition being associated with alternative speed fluctuation values and each alternative speed fluctuation value being associated with a probability value; - collecting a second set of data representative of at least one vehicle attribute (22); - adjusting said alternative speed fluctuation values based on the at least one vehicle attribute (23); the computer-implemented method being characterized in that it comprises: - selecting for each waypoint an adjusted speed fluctuation value among the associated alternative speed fluctuation values according to the associated probability values (24); - generating the speed profile of the vehicle according to the selected speed fluctuation values and their waypoints (25); and - determining the vehicle's energy consumption along the predetermined path based on the generated speed profile of the vehicle.
  2. The computer-implemented method according to claim 1, wherein each speed fluctuation value of a speed profile to be generated is also selected according to a driver profile.
  3. The computer-implemented method according to claim 2, wherein the driver profile is selected from among a plurality of alternative driver profiles, wherein each alternative driver profile is associated to a distinct range of speed fluctuation values.
  4. The computer-implemented method according to claim 3, wherein the distinct ranges of speed fluctuation values are selected according to a statistical distribution of speed fluctuation values.
  5. The computer-implemented method according to claim 4, wherein the statistical distribution of speed fluctuation values is calculated from prior statistical study of driving records.
  6. The computer-implemented method according to any one of claims 1 to 5, wherein the at least one vehicle attribute comprises weight of the vehicle and/or the type of the vehicle.
  7. The computer-implemented method according to any one of claims 1 to 5, wherein the environmental condition comprises traffic condition and/or geometry condition of the path to be travelled by the vehicle.
  8. The computer-implemented method according to claim 6, wherein the traffic condition comprises traffic light and/or an accident and/or traffic signs.
  9. The computer-implemented method according to claim 7 or 8, wherein the speed fluctuations values due to geometry condition are calculated according to regression models.
  10. A computer program set including instructions for executing the steps of the method of any one of claims 1 to 9 when said program set is executed by at least one computer.
  11. An apparatus (10) for automatically generating a speed profile of a vehicle (1) to be driven on a predetermined path, the apparatus (10) comprising: - a first collecting module (11) configured to collect a first set of data representative of environmental conditions at waypoints along the predetermined path, each distinct environmental condition being associated with alternative speed fluctuation values and each alternative speed fluctuation value being associated with a probability value; - a second collecting module (12) configured to collect a second set of data representative of at least one vehicle attribute; - an adjusting module (13) configured to adjust said alternative speed fluctuation values based on the at least one vehicle attribute; the apparatus (10) being characterized in that it comprises: - a selecting module (14) configured to select for each waypoint an adjusted speed fluctuation value among the associated alternative speed fluctuation values according to the associated probability values; and - a generating module (15) configured to generate the speed profile of the vehicle according to the selected speed fluctuation values and their waypoints, and the apparatus determines the vehicle's energy consumption along the predetermined path based on the generated speed profile of the vehicle.
  12. The apparatus (10) according to claim 11, wherein at least one of said modules is located on a cloud.
  13. A vehicle (1) comprising an apparatus (10) according to claim 12.

Description

1. Field of the invention The present disclosure relates to the field of vehicle control systems and, more particularly, to a computer-implemented method for automatically generating a speed profile of a vehicle to be driven on a predetermined path. 2. Description of Related Art Document US 2020/172081 A1 relates to a control device of a vehicle. The automation of vehicles represents a major challenge for automotive safety and driving optimization. In an effort to eliminate human error while driving a vehicle, Advanced Driver Assistance Systems (ADAS), also known as "driver assistance systems" have been designed to guide the driver and assist him in risk anticipation by automating, improving, or adapting some or all of the tasks related to driving a vehicle. These driver assistance systems rely generally on sensors to assist the driver throughout his journey and often communicate with a server to receive real-time information along the vehicle's route. Modem assistance driver systems also provide additional information related to the route, such as weather conditions, traffic congestion, duration, and disruptions on the road (diversions or lane closures, for example). The driver assistance systems can also be configured to provide information, including regulatory indications, such as speed limits or the presence of checkpoints. By analysing speed variations, the driver assistance system can provide more targeted assistance. For instance, if a driver frequently accelerates aggressively, adaptive cruise control systems can adjust the speed to maintain safer following distances or suggest driving behaviour modifications. Further, by continuously monitoring the speed of the vehicle, the driver assistance system can detect sudden deviations that might indicate driver fatigue, prompting the system to intervene or alert the driver. Also, excessive speed changes, abrupt accelerations, or frequent and sudden decelerations may indicate erratic or unsafe driving habits. Identifying such patterns allows for interventions or alerts to promote safer driving practices, reducing the risk of accidents. These speed variations form "a speed profile" of the driver which refers to a depiction of the vehicle's speed variations over a specific duration or along a particular path. It typically includes information on how the vehicle's speed changes over time, encompassing acceleration, deceleration, and constant speed phases. This profile could be represented graphically, showcasing speed fluctuations at different points during a journey or specific driving periods. Generating a driver's speed profile is useful for various other applications as well. For example, the speed profile also significantly influences fuel consumption and emissions. Monitoring speed variations helps in optimizing driving habits for improved fuel efficiency. Consistent speeds and smooth accelerations/decelerations can contribute to reduced fuel consumption and environmental impact by minimizing unnecessary energy expenditure. Further, as extreme variations in speed can impact a vehicle's components and overall performances, identifying patterns in a driver's speed profile aids in understanding how driving, habits affect the vehicle's wear and tear. This information can contribute to more effective maintenance schedules and the longevity of vehicle components. In addition, fluctuations in vehicle speed have also an impact on energy consumption as frequent accelerations and decelerations increase mechanical losses in the drivetrain of the vehicle leading to higher energy usage. Thus, it is advantageous to determine the vehicle's energy consumption based on the generated speed profile to serve as an indicator of the vehicle's performance efficiency. The generation of a driver's speed profile is based on a modular framework but lacks a defined procedure for calibrating the model based on actual driving data that takes into account driver intentions. It only relies on a physical vehicle model which encompasses equations and principles governing vehicle dynamics, such as physic-based laws of motion, aerodynamics, and friction. However, without considering actual driving behaviours and intentions of the driver, the generated speed profiles do not accurately reflect real-world scenarios which lead to unrealistic or impractical outcomes. Understanding how drivers typically behave on specific routes or in certain conditions is crucial for creating speed profiles that align with expected real-world behaviours. An alternative approach would be the generation of the driver speed profile by using machine learning techniques, particularly classification or regression algorithms. These algorithms analyse and categorize road conditions based on recorded driving scenes by training on datasets that pair road conditions (e.g., curves, traffic density, weather) with corresponding driving behaviours. However, using machine learning techniques to train a model in order to gener