Method for the autonomous localization of a driverless, motorized vehicle

• US 9,134,734 B2
• Filed: 02/06/2012
• Issued: 09/15/2015
• Est. Priority Date: 02/16/2011
• Status: Active Grant

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Lipkowski, Merten, Wsch, Thomas
• Primary Examiner(s): Badii, Behrang
• Assistant Examiner(s): TESTARDI, DAVID A
• Application Number:
  US13/985,883
• Publication Number:
  US 20130325243A1
• Time in Patent Office: 1,317 Days
• Field of Search: 701/25
• US Class Current: 1/1
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

A range-measuring sensor is arranged on a vehicle. The direction of measurement or plane of measurement of the sensor can be altered by driving a sensor motor. A map of the environment is produced by using natural landmarks. A predetermined route along which the vehicle is intended to move is stipulated. Landmarks which can serve as a localization aid along the predetermined route are determined. The environment is scanned at different times by using the sensor in order to detect the previously determined landmarks while the vehicle is moving along the predetermined route. The vehicle is localized by comparing the detected landmarks with the landmarks recorded on the map. The sensor motor is actively controlled, at least in areas of the environment with only a few previously determined landmarks, such that the sensor is oriented to these landmarks in order to ensure that they are detected.

Claims

1. A method for the autonomous localization of a driverless motorized vehicle within a known environment, comprising:

using a sensor arranged on the vehicle for range-measuring;

changing at least one of a measurement direction and a measurement plane of the sensor by controlling a sensor motor;

obtaining a map of the environment, the map having natural landmarks recorded thereon, the natural landmarks being landmarks that are not placed in the environment for the purpose of localization;

stipulating a pre-determined route along which the vehicle is to move;

identifying landmarks along the pre-determined route, to serve as localization aids, and identifying one or more critical regions in the environment along the pre-determined route, the one or more critical regions being regions which contain a number of landmarks that is below a threshold value;

scanning the environment at different points in time, while the vehicle is moving along the pre-determined route, the environment being scanned using the sensor to detect the landmarks along the pre-determined route; and

localizing the vehicle by comparing the landmarks identified along the pre-determined route with the landmarks recorded on the map;

actively controlling a speed and/or a rotation direction of the sensor motor at least while the vehicle is moving in the one or more critical regions such that the sensor is oriented toward the landmarks in the one or more critical regions, in order to ensure detection of the landmarks in the one or more critical regions.

2. The method as claimed in claim 1, wherein

the sensor is a laser scanner which measures in one measurement plane, and

the measurement plane is pivoted by controlling the sensor motor.

3. The method as claimed in claim 1, wherein

the sensor is a single-beam laser, and

the single-beam laser is mounted on the sensor motor to be rotatable about two pivot axes.

4. The method as claimed in claim 1, wherein

during localization of the vehicle, a vehicle speed is detected by a speed detector, and

the vehicle speed is taken into account in controlling the speed and/or the rotation direction of the sensor motor.

5. The method as claimed in claim 1, wherein

the sensor motor is controlled such that the sensor rotates faster in the one or more critical regions than in regions other than the one or more critical regions.

6. The method as claimed in claim 1, wherein

the sensor rotates at a predetermined rotational speed in regions other than the one or more critical regions, and

the sensor rotates a rotational speed greater than the predetermined rotational speed in the one or more critical regions.

7. The method as claimed in claim 1, wherein

the map has a non-populated area with no natural landmarks,

the method further comprises actively controlling the speed and/or the rotation direction of the sensor motor such that the sensor does not scan for landmarks in the non-populated area.