Robert Boschgmbh

Peter Biber

Klaus Marx

Thilo Koeder

Jan Sparbert

Uwe Zimmermann

Benjamin Visel

Amos Albert

Steffen Petereit

Ralf Becker

Christoph Koch

Markus Koehler

Anke Svensson

Stefan Lang

Stefan Hensel

Robert Schirmer

Hannes Becker

Paul Abbott

Florian Belser

Ulrich-Lorenz Benzler

Stefan Laible

Cyrill Stachniss

Chris Coote

Ulrich Weiss

Melita Beti

Maximilian Wenger

A computer-implemented method for operating a mobile agent in an environment on the basis of a pose of the mobile agent. The location of the mobile agent is determined by way of the following steps in order to operate the mobile agent: capturing sensor data regarding walls and/or objects located in an environment, wherein the sensor data indicate the orientation and distance of the walls and/or objects in an agent-based agent coordinate system; establishing the pose of the mobile agent in the environment using a SLAM algorithm while taking account of a Manhattan orientation.

Computer-implemented method for creating an environment map for operating a mobile agent

The disclosure relates to a method for determining the orientation of a robot and comprises at least one method step in which expected orientation data (I) pertaining to an expected orientation of the robot are provided and a method step in which actual orientation data (II) pertaining to an actual orientation of the robot are provided. According to the disclosure, one method step involves the expected orientation data (I) and the actual orientation data (II) being used to ascertain outlier-free orientation data that are used for determining the orientation of the robot. The disclosure further relates to a robot and to an orientation determination apparatus.

Method for determining the orientation of a robot, orientation determination apparatus of a robot, and robot

A method for the simultaneous localization and mapping in 2D using a 3D scanner. An environment is scanned with the aid of the 3D scanner in order to generate a three-dimensional representation of the environment in the form of a 3D pixel cloud made up of a multitude of scanned pixels. A two-dimensional representation of the environment in the form of a 2D pixel cloud is subsequently generated from the 3D pixel cloud. The 2D pixel cloud is conveyed to a 2D SLAM algorithm for the generation of a map of the environment and for the simultaneous ascertainment of the current position of the 3D scanner within the map.

Simultaneous localization and mapping in 2D using a 3D-scanner

The disclosure relates to a method for mapping a processing area, in particular for determining a processing area, as part of a navigation method for autonomous robot vehicles. According to the disclosure, said method is characterized in that boundary lines between adjoining mapped and unmapped subareas of the processing area that is to be mapped are identified by comparing distances traveled by the robot vehicle during an initial mapping trip within the processing area, mapping of an unmapped subarea adjoining a boundary line is initiated from a point on one of those identified boundary lines during another mapping trip of the robot vehicle into the unmapped subarea, and a map of the processing area is created on the basis of the subareas mapped by the robot vehicle.

Method for mapping a processing area for autonomous robot vehicles

An autonomous implement includes at least one orientation device configured to provide an orientation within a processing zone. The at least one orientation device is different from a perimeter-wire orientation device. The autonomous implement further includes at least one control and/or regulating unit configured to ascertain a travel strategy. The at least one control and/or regulating unit is configured at least to ascertain an alignment relative to a base station for a targeted docking onto an interface of the base station based on at least one orientation parameter captured using the at least one orientation device.

Autonomous work device

An autonomous working device, in particular an autonomous lawn mower, is configured to travel across a surface that is to be worked. The working device includes a processing unit configured to divide the surface that is to be worked into at least two dynamic partial surfaces to be traveled across separately by the working device.

Autonomous working device for generating and working dynamic partial surfaces

An autonomous implement, in particular an autonomous lawnmower, includes at least one computing unit configured to travel over an area to be worked. The computing unit is configured at least partly to automatically initialize relocalization in at least one operating state.

Autonomous implement

An autonomous working device, in particular an autonomous lawn mower, comprising a computing unit. The autonomous working device is configured to cover a surface to be treated in strips. The computing unit is configured to adjust an overlap of the strips according to at least one parameter.

Autonomous working device

An autonomous implement comprising at least one drive unit including at least one drive wheel, at least one sensor unit configured to detect at least one characteristic value, at least one location-determining unit configured to detect at least one characteristic value, and at least one evaluating unit. The at least one evaluating unit is configured to determine a slip of the at least one drive wheel from the at least one characteristic value detected by the at least one sensor unit and the at least one characteristic value detected by the at least one location-determining unit.

The disclosure relates to a method for processing a surface by means of a robotic vehicle, wherein the robotic vehicle has a control system in which data concerning the outline of the surface to be processed are stored, wherein locating means are present, which determine the position of the robotic vehicle, in particular in relation to the surface to be processed, and wherein the method comprises the following steps: dividing the surface to be processed into individual segments; classifying each individual segment into a property class; and moving to and processing each individual segment in succession, each individual segment being processed with a processing strategy corresponding to its property class.

Method for processing a surface by means of a robotic vehicle

A self-controlling vehicle, designed for the autonomous movement in an area, is disclosed. The self-controlling vehicle includes driving means for movement and navigation means, wherein the navigation means are designed for the position determination along a closed path surrounding an operating space of the area. The navigation means are designed for creating successive path sectional data, the path sectional data for route sections of the path has assigned orientation information, in particular angle information, and the navigation means are assigned with autocorrelation means, which are designed such that they determine from a sequence of path sectional data corresponding to a movement along the path by determining auto correlation data whether and/or that the vehicle has driven completely along the surrounding path and/or a sequence of route sections already driven is driven again.

Self-steering vehicle

The invention relates to a robotic vehicle (), in particular a robotic vehicle () designed for self-contained operations, with drive means () for the movement of the vehicle () on the subsurface (), and with control means () for the activation of the drive means () in accordance with the measured intensity of the infrared radiation. According to the invention, a light sensor () is provided to detect the intensity of light radiation from the visible spectrum reflected from the subsurface (), and in addition the control means () are designed to activate the drive means () in accordance with the measured intensity of the light radiation. The invention further relates to a method of activation.

Robotic vehicle with drive means and method for activating drive means

A method and apparatus for controlling driving means which are designed to steer and move a robot vehicle () that is designed as a lawn mowing vehicle. The driving means are controlled so that the robot vehicle () travels through several sections () of a working area () in a specific movement pattern according to a section travel strategy with the help of dead reckoning such that two adjoining course sections () overlap with a predefined probability transversely to the direction of travel of the robot vehicle ().

Growing community of inventors

Poltringen, Germany

Peter Biber