Method for starting up an autonomous vehicle
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-02-29
- Publication Date
- 2026-03-04
AI Technical Summary
Inaccurate or incomplete maps in technical systems, such as industrial applications, hinder the effective commissioning of autonomous vehicles, as they rely on precise object detection and positioning for route determination.
A method for commissioning autonomous vehicles that allows real-time route determination and map updating using a SLAM algorithm, where the vehicle is controlled through the system to save and calculate route points, utilizing sensors and odometric data to enhance position accuracy without requiring pre-defined accurate maps.
Simplifies the commissioning process by enabling accurate route determination and map updates, ensuring precise positioning and integration of transfer stations into the route, even with initial map inaccuracies, thus improving operational efficiency.
Smart Images

Figure EP2024055286_31102024_PF_FP_ABST
Abstract
Description
[0001] Procedure for commissioning an autonomous vehicle
[0002] Description:
[0003] The invention relates to a method for commissioning an autonomous vehicle in a technical installation, wherein the autonomous vehicle has at least one sensor for detecting objects and a detection unit for detecting objects from detected objects, and wherein the autonomous vehicle has a map of the technical installation.
[0004] The technical facility is primarily an industrial application, such as a production plant, an industrial hall, or a logistics center. Autonomous vehicles are used, for example, to transport materials within the technical facility. The technical facility also contains other objects, such as walls, pillars, production machines, pallets, transfer stations, as well as people and other autonomous vehicles.
[0005] The autonomous vehicles have sensors for detecting such objects and a detection unit for detecting objects from the detected objects. The autonomous vehicles each have a map of the technical system in which such objects are recorded. If an object is detected, the location of the autonomous vehicle within the technical system can be determined by comparing the detected object with an object recorded on the map.
[0006] Document DE 102019 001 253 A1 discloses a method for operating a technical installation comprising at least one mobile system that can be moved along a traffic area of the technical installation. The mobile system detects objects in the technical installation using appropriate sensors. The positions of the detected objects are compared with presumed positions of objects based on a map of the technical installation.
[0007] DE 102013211414 A1 discloses an automated guided vehicle and a method for operating an automated guided vehicle. The automated guided vehicle is controlled from a starting point to a destination, and at the destination, the surroundings are detected and compared with a target position. JP 2022-180938 A discloses a device for determining a movement route for a vehicle.
[0008] During operation, an autonomous vehicle regularly travels a specific route within the technical facility. To commission an autonomous vehicle, for example, several route points are determined on the map that lie along the route. The route thus determined is inserted into the map, and the map containing the route is loaded into the autonomous vehicle. This can be problematic if the map of the technical facility is inaccurate or incomplete.
[0009] The invention is based on the object of developing a method for commissioning an autonomous vehicle in a technical system.
[0010] The object is achieved by a method for commissioning an autonomous vehicle in a technical system having the features specified in claim 1. Advantageous embodiments and further developments are the subject of the subclaims.
[0011] A method for commissioning an autonomous vehicle in a technical installation is proposed, wherein the autonomous vehicle has at least one sensor for detecting objects and a detection unit for detecting objects from detected objects, and wherein the autonomous vehicle has a map of the technical installation.
[0012] According to the invention, the autonomous vehicle is controlled by a user starting from a first route point through the technical system, with further route points being traveled to. The position of the first route point is stored in the map of the technical system. The positions of the further route points reached are calculated and stored in the map. Objects are detected by the sensor while the further route points are being traveled to. Objects are detected by the detection unit from the detected objects. The positions of the detected objects are calculated and stored in the map. Starting at the position of the first route point, a route to be traveled is determined by inserting the positions of the further route points into the route to be traveled. The method according to the invention simplifies the commissioning of an autonomous vehicle in the technical system.The method uses a teach mode to determine the route to be traveled and simultaneously update the map of the technical system using a SLAM algorithm. Preliminary route determination using an inaccurate or incomplete map is not required.
[0013] According to a preferred embodiment of the invention, the autonomous vehicle is stopped upon reaching a further route point, and the autonomous vehicle is further controlled after calculating the position of the further route point. This increases the accuracy of calculating the position of the further route point.
[0014] According to an advantageous development of the invention, the autonomous vehicle has an odometric system for determining odometry data, in particular for determining a distance between two approached route points and for determining a direction between two approached route points. The odometric system enables the use of a SLAM algorithm to calculate the positions of the additional route points.
[0015] According to an advantageous embodiment of the invention, the autonomous vehicle calculates the position of a further route point from the position of the previous route point and odometry data determined by the odometric system.
[0016] According to an advantageous embodiment of the invention, the autonomous vehicle calculates the position of another route point by detecting objects using the sensor, detecting objects from the detected objects using the detection unit and comparing the detected objects with objects stored in the map.
[0017] According to an advantageous development of the invention, the autonomous vehicle calculates and stores a respective orientation of the autonomous vehicle at the further route points. The respective orientation of the autonomous vehicle specifies the direction of travel of the autonomous vehicle upon reaching the respective route point.
[0018] According to a preferred development of the invention, if a detected object is a transfer station, a point in the transfer station is defined as an additional route point, a position of the additional route point is calculated and stored in the map, and the position of the additional route point is inserted into the route to be traveled. The transfer station is thus integrated into the route to be traveled. Driving the autonomous vehicle into the transfer station is not required.
[0019] According to an advantageous embodiment of the invention, when an object is detected by the at least one sensor, a distance to the object is detected, and a direction in which the object is located is detected, and the position of an object detected from the detected object is calculated from a location of the autonomous vehicle, the distance to the object and the direction in which the object is located.
[0020] According to an advantageous embodiment of the invention, the at least one sensor is designed as a laser scanner or a 3D camera. A laser scanner emits a laser beam, detects a reflected laser beam, and uses this to calculate the distance to an object reflecting the laser beam. A laser scanner is already present in known autonomous vehicles, thus no additional costs are incurred for installing a laser scanner. A 3D camera calculates the distance to an object detected by the 3D camera.
[0021] According to a preferred embodiment of the invention, the autonomous vehicle comprises a drive device, an electrical energy storage device for supplying the drive device, and a control unit for controlling the drive device. Furthermore, the autonomous vehicle comprises a communication unit for wireless communication, in particular with other autonomous vehicles and with a higher-level server in the technical system, via a network. The communication unit of the autonomous vehicle is designed, for example, for data transmission via WLAN, Bluetooth, or light.
[0022] The invention is not limited to the combination of features in the claims. Further possible combinations of claims and / or individual claim features and / or features of the description and / or the figures will become apparent to those skilled in the art, particularly from the task and / or the problem posed by comparison with the prior art. The invention will now be explained in more detail with reference to figures. The invention is not limited to the exemplary embodiments shown in the figures. The figures represent the subject matter of the invention only schematically. It shows:
[0023] Figure 1 : a schematic representation of a map of a technical installation with a route to be traveled and
[0024] Figure 2: a schematic representation of a route to be traveled with transfer stations.
[0025] Figure 1 shows a schematic representation of a map of a technical facility with a route 10 to be traveled. The technical facility is an industrial application, for example, a production plant, an industrial hall, or a logistics center. The technical facility comprises several autonomous vehicles 1. The autonomous vehicles 1 are used primarily for transporting material within the technical facility. In this example, only one autonomous vehicle 1 is shown, which is moving along route 10.
[0026] The autonomous vehicle 1 has a drive system, an electrical energy storage device for supplying the drive system, and a control unit for controlling the drive system. Furthermore, the autonomous vehicle 1 has a communication unit for wireless communication via a network. The communication unit enables communication with other autonomous vehicles 1 and with a higher-level server in the technical system. The communication unit of the autonomous vehicle is designed, for example, for data transmission via WLAN, Bluetooth, or light.
[0027] The technical facility contains objects, such as walls, pillars, production machines, pallets, and transfer stations 20. The autonomous vehicle 1 has a map of the technical facility. These objects are stored as objects in the map of the technical facility. The positions of the objects are also stored as object positions in the map.
[0028] It is conceivable, particularly when commissioning a new autonomous vehicle 1, that the map of the technical system available to the autonomous vehicle 1 at that time is inaccurate or incomplete. In particular, objects may be missing or stored in the wrong positions on the map. The autonomous vehicle 1 further comprises two sensors 2. The sensors 2 are embodied as laser scanners. The sensors 2 serve to detect objects in the technical system. The autonomous vehicle 1 also has a detection unit. The detection unit serves to detect objects from among the objects detected by the sensors 2.
[0029] Each sensor 2 has a detection range 5. Objects located within the detection range 5 are detected by the sensor 2. When an object is detected by a sensor 2, a distance to the object and a direction in which the object is located are detected. A position of an object detected from the detected object is calculated from a location of the autonomous vehicle 1, the distance to the object, and the direction in which the object is located.
[0030] To commission the autonomous vehicle 1 in the technical system, the autonomous vehicle 1 is first controlled by a user to a first route point 11. A position of the first route point 11 is stored in the map of the technical system when the autonomous vehicle 1 is located at the first route point 11. The first route point 11 corresponds to the location of the autonomous vehicle 1.
[0031] Starting from the first route point 11, the autonomous vehicle 1 is controlled by the user through the technical system. Several additional route points 12 are then approached. The positions of the additional route points 12 are also calculated and stored on the map. The additional route points 12 each correspond to the location of the autonomous vehicle 1.
[0032] At each of the additional route points 12, the autonomous vehicle 1 has a respective orientation, each of which is represented by an arrow. The autonomous vehicle 1 calculates the respective orientation of the autonomous vehicle 1 at the additional route points 12 and stores the calculated orientation.
[0033] The autonomous vehicle 1 is stopped when it reaches another route point 12.
[0034] After calculating the position of the further route point 12 and saving the calculated position of the further route point 12 in the map, the autonomous vehicle 1 is further controlled.
[0035] While the vehicle approaches the remaining route points 12, the sensors 2 detect objects. The detection unit then selects objects from the detected objects. The positions of the detected objects are calculated and stored on the map.
[0036] For example, one of the sensors 2 detects a transfer station 20 located within the detection range 5 of the sensor 2. The sensor 2 detects a distance to the transfer station 20 and a direction in which the transfer station 20 is located. The detection unit detects the transfer station 20. A position of the transfer station 20 is calculated from the location of the autonomous vehicle 1, the distance to the transfer station 20, and the direction in which the transfer station 20 is located.
[0037] The autonomous vehicle 1 has an odometric system for determining odometry data. The odometric system serves in particular to determine a distance between two approached route points 11, 12 and to determine a direction between two approached route points 11, 12.
[0038] The autonomous vehicle 1 calculates the position of a further route point 12 from the position of the previous route point 11, 12 and odometry data determined by the odometric system.
[0039] Alternatively or additionally, the autonomous vehicle 1 calculates the position of a further route point 12 by detecting objects using the sensor 2, detecting objects from the detected objects using the detection unit and comparing the detected objects with objects stored in the map.
[0040] Starting at the position of the first route point 11, a route 10 to be traveled is determined by inserting the positions of the additional route points 12 into the route 10 to be traveled. The route 10 begins at the first route point 11. The route 10 has several sub-routes. The first sub-route extends from the first route point 11 to the next additional route point 12. The subsequent sub-routes each extend from one additional route point 12 to the next additional route point 12.
[0041] Figure 2 shows a schematic representation of a route 10 to be driven with several transfer stations 20. The commissioning of the autonomous vehicle 1, which is not shown here, takes place as shown in Figure 1.
[0042] If an object detected by the detection unit is a transfer station 20, a point in the transfer station 20 is defined as an additional route point 13. The transfer station 20 is configured such that the autonomous vehicle 1 can enter the transfer station 20. The additional route point 13 then corresponds to the location of the autonomous vehicle 1.
[0043] The position of the additional route point 13 is calculated and saved on the map. The position of the additional route point 13 is also inserted into the route 10 to be traveled.
[0044] List of reference symbols
[0045] I autonomous vehicle 2 sensor
[0046] 5 Detection range
[0047] 10 route
[0048] II first route point
[0049] 12 additional route point 13 additional route point
[0050] 20 transfer station
Claims
Patent claims:
1. A method for commissioning an autonomous vehicle (1) in a technical installation, wherein the autonomous vehicle (1) has at least one sensor (2) for detecting objects and a detection unit for detecting objects from detected objects, and wherein the autonomous vehicle (1) has a map of the technical installation, characterized in that the autonomous vehicle (1) is controlled by a user starting from a first route point (11) through the technical installation, wherein further route points (12) are approached; a position of the first route point (11) is stored in the map of the technical installation; Positions of the further route points (12) approached are calculated and stored in the map; objects are detected by the sensor (2) while the further route points (12) are approached; objects are detected from the detected objects by the detection unit; Positions of the detected objects are calculated and stored in the map; and starting at the position of the first route point (11), a route (10) to be traveled is determined by inserting the positions of the further route points (12) into the route (10) to be traveled.
2. Method according to one of the preceding claims, characterized in that the autonomous vehicle (1) is stopped when a further route point (12) is reached, and in that the autonomous vehicle (1) is further controlled after calculating the position of the further route point (12).
3. Method according to one of the preceding claims, characterized in that the autonomous vehicle (1) has an odometric system for determining odometry data, in particular for determining a distance between two approached route points (11, 12) and for determining a direction between two approached route points (11, 12).
4. Method according to claim 3, characterized in that the autonomous vehicle (1) calculates the position of a further route point (12) from the position of the previous route point (11, 12) and odometry data determined by the odometric system.
5. Method according to one of the preceding claims, characterized in that the autonomous vehicle (1) determines the position of a further route point (12) by detecting objects by means of the sensor (2), Detection of objects from the recorded items using the detection unit and comparison of the detected objects with objects stored in the map.
6. Method according to one of the preceding claims, characterized in that the autonomous vehicle (1) calculates and stores a respective orientation of the autonomous vehicle (1) at the further route points (12).
7. Method according to one of the preceding claims, characterized in that if a detected object is a transfer station (20), a point in the transfer station (20) is defined as an additional route point (13), and that a position of the additional route point (13) is calculated and stored in the map, and that the position of the additional route point (13) is inserted into the route (10) to be traveled.
8. Method according to one of the preceding claims, characterized in that when an object is detected by the at least one sensor (2), a distance to the object is detected, and a direction in which the object is located is detected, and in that the position of an object detected from the detected object is calculated from a location of the autonomous vehicle (1), the distance to the object and the direction in which the object is located.
9. Method according to one of the preceding claims, characterized in that the at least one sensor (2) is designed as a laser scanner or as a 3D camera.
10. Method according to one of the preceding claims, characterized in that the autonomous vehicle (1) has a drive device, an electrical energy storage device for supplying the drive device, a control unit for controlling the drive device and a communication unit for wireless communication via a network.