Search

CN-121995365-A - Vehicle surrounding environment sensing method based on sensor fusion

CN121995365ACN 121995365 ACN121995365 ACN 121995365ACN-121995365-A

Abstract

The application relates to a sensing method of a surrounding environment of a vehicle, the vehicle comprising an ultrasonic sensor and a millimeter wave radar configured to detect the same environmental zone, the method comprising at least the steps of converting obstacle data based on detection of the ultrasonic sensor and point cloud data based on detection of the millimeter wave radar into the same coordinate system, and data filtering the obstacle data with the point cloud data to obtain first real obstacle data representing a relative position of a real obstacle and the vehicle. A computer program product and a related vehicle electronic control unit are also provided that can implement the method.

Inventors

  • LI YUNTAO

Assignees

  • 罗伯特·博世有限公司

Dates

Publication Date
20260508
Application Date
20241101

Claims (11)

  1. 1. A method of sensing an environment surrounding a vehicle, the vehicle including an ultrasonic sensor and a millimeter wave radar configured to detect the same environmental zone, the method comprising at least the steps of: S1, converting obstacle data based on detection of an ultrasonic sensor and point cloud data based on detection of a millimeter wave radar into the same coordinate system, and S2, performing data filtering on the obstacle data by utilizing the point cloud data to obtain first real obstacle data representing the relative positions of the real obstacle and the vehicle.
  2. 2. The method according to claim 1, wherein step S2 comprises the substep of S21, identifying the first real obstacle data from the obstacle data based on position information of the detection point mapped by the point cloud data.
  3. 3. The method according to claim 2, wherein step S2 comprises the substep of determining that the obstacle data is the first real obstacle data when the position information of the obstacle mapped by the obstacle data coincides with the position information of the detection point mapped by the point cloud data S22.
  4. 4. A method according to claim 3, wherein it is determined whether the position information of the obstacle mapped by the obstacle data coincides with the position information of the detection point mapped by the point cloud data by any one of: i) Comparing the coordinate information of the obstacle mapped by the obstacle data along the transverse direction and/or the vertical direction of the vehicle with the coordinate range of the detection point mapped by the point cloud data along the transverse direction and/or the vertical direction of the vehicle; ii) detecting whether an extended diameter range defined around the detection point mapped by the point cloud data contains or intersects an obstacle mapped by the obstacle data, optionally the extended diameter range having a radius of more than 10 cm and less than 20 cm, and Iii) A neighborhood of the obstacle mapped by the obstacle data is searched to determine whether there is a detection point mapped by the point cloud data, optionally the neighborhood is defined as a range more than 10 cm and less than 20 cm from the obstacle mapped by the obstacle data.
  5. 5. The method according to claim 4, wherein it is determined that the position information of the obstacle mapped by the obstacle data coincides with the position information of the detection point mapped by the point cloud data when at least one of: i) Coordinates of the obstacle mapped by the obstacle data along the vehicle transverse and/or vertical directions fall within a coordinate range of the detection point mapped by the point cloud data along the vehicle transverse and/or vertical directions; ii) the obstacle mapped by the obstacle data is contained within or intersects the extended diameter range of the at least one point cloud data, and Iii) At least one detection point mapped by the point cloud data exists in the neighborhood of the obstacle mapped by the obstacle data.
  6. 6. The method according to any one of claims 1-5, wherein step S2 comprises the substep of S23 obtaining first real obstacle data by filtering out obstacle data from the obstacle data, which do not correspond to the position information of the detection point to which the point cloud data is mapped, using the point cloud data.
  7. 7. The method of claim 6, further comprising the step of: s3, providing a target detection result based on the first real obstacle data and/or S0, determining installation position information of an ultrasonic sensor and a millimeter wave radar in the vehicle in advance to allow creation of the obstacle data and the point cloud data in a vehicle coordinate system.
  8. 8. The method of claim 7, wherein the method is allowed to be used when the speed of the vehicle is below a predetermined speed threshold and/or the method is enabled in a scenario where an ultrasonic sensor is applicable.
  9. 9. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the method according to any of claims 1-8.
  10. 10. An electronic control unit of a vehicle configured to implement the method of any one of claims 1-8 and obtain first real obstacle data to implement any one of a park assist, a reverse assist, a front cross target brake, a front cross target cue, a blind spot detection, a low speed emergency brake, and a rear automatic emergency brake.
  11. 11. The electronic control unit of claim 10, wherein the electronic control unit is a domain controller.

Description

Vehicle surrounding environment sensing method based on sensor fusion Technical Field The present application relates generally to the field of intelligent assisted driving of vehicles, and more particularly to a sensor fusion-based vehicle ambient environment awareness method and related computer program products and vehicle electronic control units. Background Object detection (object detection) is an important aspect of enabling vehicle assisted driving, intelligent driving, or even unmanned driving, which helps to perceive the vehicle surroundings and provide assistance and/or critical decision information for vehicle maneuvers in a specific scenario. Vehicles may typically be equipped with a variety of sensors to detect the surrounding environment of the vehicle and accordingly allow specific targets (e.g., motor vehicles, pedestrians, obstacles, etc.) to be detected, identified, and tracked based on the detection information. Conventionally, a plurality of ultrasonic sensors may be provided on front and rear bumpers of a vehicle for detecting obstacles in a short distance of the vehicle in a scene of parking, running at a low speed (e.g., 2-12 km/h), or stationary parking of the vehicle, etc. (generally, the ultrasonic sensors are intended to detect obstacles stationary or having a low relative speed to the vehicle) and thereby to realize intelligent auxiliary control (e.g., auxiliary parking, emergency braking, target prompt, etc.) in these scenes. Further, a plurality of millimeter wave radars may be further arranged around the body of the vehicle (e.g., at front and rear sides of the body (e.g., at front and rear bumpers) and at four corners) for detecting objects around the vehicle and recognizing and tracking the objects accordingly during running of the vehicle and thereby realizing intelligent assist control (e.g., constant speed auto cruise, navigation assist driving, lane keeping and lane change assist functions, etc.) in these scenes. According to the respective working characteristics of the ultrasonic sensor and the millimeter wave radar, the vehicle can use different sensing devices to sense environmental information based on different scenes in the use process. For example, when the vehicle speed detection indicates that the vehicle is jogging below a certain threshold or that the vehicle is in a stationary state, and/or a user command from the human-machine interaction interface indicates that the park or reverse assist function of the vehicle is enabled, the millimeter wave radar in the vehicle perception system may not be activated (e.g., because the millimeter wave radar cannot accurately recognize static and quasi-static (low speed movement) obstacles, in these scenarios, even though the millimeter wave radar is activated, the acquired information would not be employed by the corresponding functional module) and the ultrasonic sensor may be activated for detecting a static or quasi-static target around the vehicle and constructing the obstacle based on the detected information accordingly, thereby making a corresponding decision and control. Alternatively, if the vehicle speed detection indicates that the vehicle is traveling at a speed above a certain threshold, and/or the user command from the human-machine interaction interface indicates that the constant-speed-cruise function or the navigation-assisted driving function of the vehicle is enabled, the ultrasonic sensor of the vehicle perception system may not be activated and the millimeter-wave radar may be activated for providing detection of dynamic targets around the vehicle and generating a point cloud indicative of the detection target position based on the detection information accordingly, thereby making a corresponding decision and control. Thus, although many different types of sensing devices are loaded in vehicles, the sensing patterns used by vehicles in static and low speed dynamic scenarios are often fixed and unitary, e.g., relying on ultrasonic sensors alone to detect targets. It is therefore desirable to provide an improved target detection method that fully utilizes different sensing patterns of vehicles, including ultrasonic sensors, to provide real-time, efficient, accurate target detection in static and low-speed dynamic scenarios. Disclosure of Invention The present application proposes an obstacle recognition method suitable for use in a stationary or low-speed state of a vehicle, which allows a real target in a close range around the vehicle to be determined quickly, accurately, and efficiently by fusing detection information from an ultrasonic sensor and a millimeter wave radar. According to one aspect of the present application, there is provided a sensing method of a surrounding environment of a vehicle including an ultrasonic sensor and a millimeter wave radar configured to detect the same environmental zone, the method including at least the steps of S1 converting obstacle data based on detection of t