Abstract: The invention relates to a control system for an autonomous vehicle, a method and an autonomous vehicle. The system comprises an image capturing means capable of capturing at least a first image of the environment of the vehicle and a second image of the environment, wherein the images are captured in a close time relationship but with different image capturing parameters. A processing means configured to obtain and process the images captured with different image capturing parameters separately and taking into consideration a first intensity threshold when processing the first image and a second, different intensity threshold when processing the second image. A control means for generating and outputting a control signal on the basis of a result of the at least one of the processed images.

Abstract: The invention relates to an autonomous lawn mower comprising a control unit in electrical connection with electrical connection means, and at least one replaceable part. The electrical connection means is located such that connection and disconnection of the electrical connection means and its counterpart of the replaceable part can be performed when replacing the replaceable part. The module for such autonomous lawn mower can replace the replaceable part of the lawn mower and comprises a signal generation unit and a counterpart for the electrical connection means of the lawn mower for transmitting electrical signals to a control unit of the autonomous lawn mower. The autonomous lawn mower forms an autonomous lawn mower system together with the module.

Abstract: The invention regards an autonomous working machine comprising drive means, current position estimation means, control means including a driving control unit and a camera. With aid of the current position estimation means the current position of the autonomous working machine is estimated. Furthermore, the driving control unit generates driving commands for the driving means on the basis of an intended movement of the autonomous working machine and the estimated current position. The camera is configured to capture images of the environment of the working machine. For estimating the current position, the current position estimation means is formed by the control means, which is configured to apply visual odometry on the captured images for estimating the current position of the working machine.

Abstract: A method for analyzing related images corresponding system and vehicle including such system as well as a computer program product for executing the method. The method comprises obtaining at least a first and a second image, defining a pixel patch in the first image for which a correlation shall be calculated, calculating matching cost values between each pixel of the pixel patch in the first image and its corresponding pixel in each of a plurality of pixel patches in the second image, wherein the pixel patches in the second image differ in position in the second image and include the pixel patch with a target position, aggregating the matching cost values of those corresponding pixels of all patches in the second image which match best to generate an aggregation window associated with the target position, and producing a signal including information on the target position.

Abstract: Embodiments of the invention address the area of predictive suspension control system for a vehicle, particularly a two-wheel vehicle such as a motor cycle or a scooter. The system includes a stereo sensor unit which for generating image data, a computing unit which extracts a relevant image portion from the image data based on future vehicle path data, and calculates road unevenness on a future vehicle path of the vehicle based on the generated image data. A suspension control unit generates an adaptation signal for adapting the suspension based on the calculated road unevenness. The computing unit adapts a search direction of a stereo algorithm or a correlation area of the stereo algorithm based on a lean angle of the vehicle to generate the three-dimensional partial image data from the relevant image portion, and fits a road model to the three-dimensional partial image data to calculate the road unevenness.

Abstract: An autonomous vehicle comprises an environment sensing means for sensing an environment of the autonomous vehicle, and a computing unit configured to perform a mapping function and a localization function. The mapping function is based upon signals supplied from the environment sensing means to build a map. The localization function localizes the autonomous vehicle within the map and generates localization information. The autonomous vehicle further comprises boundary distance sensing means configured to generate a distance signal correlated to a distance between the autonomous vehicle and boundary indication means. The computing unit is configured to receive the distance signal and to perform the mapping function or the localization function based upon a signal from the environment sensing means and the distance signal from the boundary distance sensing means. The system also comprises a boundary wire indicating a border of an area in which autonomous driving of the vehicle can be performed.

Abstract: The inventive system comprises an autonomous robot device, a base station and a method operating the same. The autonomous robot device includes a sensor means, e.g. an optical sensor, and a propulsion means. The base station includes a cleaning means specifically adapted for cleaning the sensor means of the autonomous robot device. In a preferred embodiment the propulsion means of the autonomous robot device is configured to move the autonomous robot device in a manner suitable to generate a relative movement of the autonomous robot device with respect to the passive cleaning means arranged at the stationary base station to effect the cleaning of the sensor means of the autonomous robot device.

Abstract: The present invention presents a sensing system 1 and a corresponding method for detecting moving objects 11 in the surroundings of a vehicle 10. The sensing system 1 comprises an imaging unit 2 for obtaining an image stream 2a, a computing unit 3 for analyzing the image stream 2a, and a control unit 4 for controlling the vehicle 10 based on the analysis result of the computing unit 3. The sensing system 1 particularly employs a background-model-free estimation. The sensing system 1 is configured to perform a local analysis of two neighboring motion vectors 6, which are computed from points 7a in images 5a, 5b of the image stream 2a, and to determine, whether the points 7a corresponding to these motion vectors 6 belong to a particularly moving object.

Abstract: A distance measurement method determines the distance of a sensor system to a physical object. The method includes obtaining at least a pair of stereoscopic images including the physical object, and applying to each element of at least a portion of a first image of the pair of stereoscopic images and to each element of at least a portion of a second image of the pair of stereoscopic images at least two differently shaped or sized filters, respectively. Correlation values for each filter applied to the first and second image are determined, and, combined correlation values are determined for the applied filters by combining the determined correlation values for each applied filter. The combined correlation values are evaluated for different disparities for an extremum value of the combined correlation values. A distance value to the physical object is calculated and output based on a disparity value at which the extremum occurs.

Abstract: The invention relates to an autonomous lawn mower comprising a control unit in electrical connection with electrical connection means, and at least one replaceable part. The electrical connection means is located such that connection and disconnection of the electrical connection means and its counterpart of the replaceable part can be performed when replacing the replaceable part. The module for such autonomous lawn mower can replace the replaceable part of the lawn mower and comprises a signal generation unit and a counterpart for the electrical connection means of the lawn mower for transmitting electrical signals to a control unit of the autonomous lawn mower. The autonomous lawn mower forms an autonomous lawn mower system together with the module.

Abstract: The invention relates to a method for determining a static element in images captured by an imaging means mounted on a movable device. The method comprises steps of acquiring a first image and a second image captured by the imaging means. The first image and the second image are captured at capture times separated by a time difference and the method is characterized by the time difference being selected depending on motion parameters of the movable device. A determination measure for corresponding regions of the first and the second image for representing a similarity of the corresponding regions is calculated and a static element of the first and the second image is determined based on the calculated determination measure. An output signal comprising information on the determined static element is generated.

Abstract: The invention relates to a control system for an autonomous vehicle, a method and an autonomous vehicle. The system comprises an image capturing means capable of capturing at least a first image of the environment of the vehicle and a second image of the environment, wherein the images are captured in a close time relationship but with different image capturing parameters. A processing means configured to obtain and process the images captured with different image capturing parameters separately and taking into consideration a first intensity threshold when processing the first image and a second, different intensity threshold when processing the second image. A control means for generating and outputting a control signal on the basis of a result of the at least one of the processed images.

Abstract: A computer-implemented method for generating a depth map including, generating an initial depth map for a first image, the first image being one of a pair of stereo images received from an imaging device, the pair of stereo images including the first image and a second image and generating an estimated depth map based on the initial depth map by hypothesizing depth values for missing regions in the initial depth map. The method including warping the second image based on the estimated depth map, generating a warped depth map based on the first image and the warped second image, and generating a new depth map for the first image relative to the second image based on the warped depth map and the estimated depth map.

Abstract: The invention provides an image processing method for processing a sequence of images, comprising the steps of: obtaining, from a visual sensor, at least two images of the sequence of images, detecting whether the images include a distortion, determining an image warping function at least partially compensating the distortion, applying the determined warping function to the image(s) including the distortion, and calculating by a processing unit, and outputting, an optical flow as a displacement vector field form the images.

Abstract: A method for detecting the position of a target object in the environment of a host vehicle. The method may include receiving a first position of the target object as detected by an object position sensor which emits waves and receives the waves that are reflected back by the target object, and receiving an image containing the target object as detected by an image sensor. The method may also include projecting the first position on the image, and refining the first position by computing a second refined position of the target object on the basis of a symmetry search within the image.

Abstract: A distance measurement method determines the distance of a sensor system to a physical object. The method includes obtaining at least a pair of stereoscopic images including the physical object, and applying to each element of at least a portion of a first image of the pair of stereoscopic images and to each element of at least a portion of a second image of the pair of stereoscopic images at least two differently shaped or sized filters, respectively. Correlation values for each filter applied to the first and second image are determined, and, combined correlation values are determined for the applied filters by combining the determined correlation values for each applied filter. The combined correlation values are evaluated for different disparities for an extremum value of the combined correlation values. A distance value to the physical object is calculated and output based on a disparity value at which the extremum occurs.

Abstract: The invention presents a method for comparing the similarity between image patches comprising the steps of receiving form at least two sources at least two image patches, wherein each source supplies an image patch, comparing the received image patches by extracting a number of corresponding subpart pairs from each image patch, calculating a normalized local similarity score between all corresponding subpart pairs, calculating a total matching score by integrating the local similarity scores of all corresponding subpart pairs, and using the total matching score as an indicator for an image patch similarity, determining corresponding similar image patches based on the total matching score.

Abstract: The present invention proposes a profound user-mower interaction, which enables the user to teach a robotic lawn mower for improving its visual obstacle detection. The main idea of the invention is that the user can show some typical obstacles from his garden to the mower. This will increases the performance of the visual obstacle detection. In the simplest scenario the user just places the mower in front of an obstacle, and activates the learning mechanism of the classification means (module) of the mower. The increasing use of smart devices such as smart phones or tablets enables also more elaborated learning. For example, the mower can send the input image to the smart device, and the user can provide a detailed annotation of the image. This will drastically improve the learning, because the mower is provided with ground truth information.

Abstract: A technique for assigning lanes on a road to objects moving in a vicinity of a vehicle on the road is proposed. A method embodiment of the invention comprises the steps of providing trajectories, wherein the or each trajectory represents a time sequence of positions of a moving object; selecting first and second objects and determining a distance between a current position of the first object and the trajectory of the second object; comparing the distance with a predefined threshold; and providing, based on a result of the comparison, a lane assignment indicating a lane to which the second object is assigned.

Abstract: A computer-implemented method for generating a depth map including, generating an initial depth map for a first image, the first image being one of a pair of stereo images received from an imaging device, the pair of stereo images including the first image and a second image and generating an estimated depth map based on the initial depth map by hypothesizing depth values for missing regions in the initial depth map. The method including warping the second image based on the estimated depth map, generating a warped depth map based on the first image and the warped second image, and generating a new depth map for the first image relative to the second image based on the warped depth map and the estimated depth map.