Abstract: Control commands in a system and method for autonomously driving a vehicle or partially autonomously driving a vehicle are generated on the basis of an environment representation, which is generated from sensor signal of a sensing means. The environment representation where ambiguous objects are identified is such that information obtained from the driver of the vehicle are added. The system generates an information request. Additional information is extracted and accumulated in the environment representation map. Traffic is then determined and suitable control signals for the vehicles are generated. In case no ambiguous objects are included in the environment representation but the system is not capable of deciding on traffic, the driver is asked to disambiguate the situation or to instruct on dealing with the traffic.

Abstract: The method for assisting a person in operating in a dynamic environment may form part of a mobility assistance system. The method comprises a step of acquiring sensor data comprising a time sequence of at least two consecutive images of the dynamic environment from at least one sensor, for example a camera. Optical flows are calculated based on the at least two consecutive images. Feature scores associated to spatial positions for selected regions in an image space are determined in order to generate a feature score field. An output signal including directional stimulus information is generated based on the generated feature score field, wherein the directional stimulus information comprises information on relative spatial relations between the selected regions. The generated output signal is provided to at least one actuator, which signals the directional stimulus information to the person.

Abstract: The invention relates to a system and method for assisting a driver in driving a vehicle. First information on an environment of the vehicle is obtained and an instruction from the vehicle driver is received. An evaluation task defining an aspect of a current traffic situation encountered by the vehicle and to be evaluated is defined from the received instruction. An evaluation of the obtained information according to the evaluation task is performed, and an evaluation result is generated. Other aspects of the traffic situation and their relation to the aspect defined in the task are then evaluated additionally. Finally an information on the basis of the evaluation result and the other determined aspects is generated and output.

Abstract: The method for assisting a person in operating in a dynamic environment may form part of a mobility assistance system. The method comprises a step of acquiring sensor data comprising a time sequence of at least two consecutive images of the dynamic environment from at least one sensor, for example a camera. Optical flows are calculated based on the at least two consecutive images. Feature scores associated to spatial positions for selected regions in an image space are determined in order to generate a feature score field. An output signal including directional stimulus information is generated based on the generated feature score field, wherein the directional stimulus information comprises information on relative spatial relations between the selected regions. The generated output signal is provided to at least one actuator, which signals the directional stimulus information to the person.

Abstract: The invention relates to a system and method for assisting a driver in driving a vehicle. First information on an environment of the vehicle is obtained and an instruction from the vehicle driver is received. An evaluation task defining an aspect of a current traffic situation encountered by the vehicle and to be evaluated is defined from the received instruction. An evaluation of the obtained information according to the evaluation task is performed, and an evaluation result is generated. Other aspects of the traffic situation and their relation to the aspect defined in the task are then evaluated additionally. Finally an information on the basis of the evaluation result and the other determined aspects is generated and output.

Abstract: The invention relates to a method for controlling a driver assistance system comprising the steps of providing information on an environment of a host vehicle, receiving a spoken instruction from a host vehicle driver, generating an attention delegation task for evaluation of the provided information from the spoken instruction, performing evaluation of provided information in accordance with said attention delegation task and outputting a result of the evaluation.

Abstract: Control commands in a system and method for autonomously driving a vehicle or partially autonomously driving a vehicle are generated on the basis of an environment representation, which is generated from sensor signal of a sensing means. The environment representation where ambiguous objects are identified is such that information obtained from the driver of the vehicle are added. The system generates an information request. Additional information is extracted and accumulated in the environment representation map. Traffic is then determined and suitable control signals for the vehicles are generated. In case no ambiguous objects are included in the environment representation but the system is not capable of deciding on traffic, the driver is asked to disambiguate the situation or to instruct on dealing with the traffic.

Abstract: The invention relates to a method for controlling a driver assistance system comprising the steps of providing information on an environment of a host vehicle, receiving a spoken instruction from a host vehicle driver, generating an attention delegation task for evaluation of the provided information from the spoken instruction, performing evaluation of provided information in accordance with said attention delegation task and outputting a result of the evaluation.

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: The invention relates to a method for processing video signals from a video sensor, in order to extract 3d shape information about objects represented in the video signals, the method comprising the following steps: providing a memory in which objects are stored in a 3d shape space, the shape space being an abstract feature space encoding the objects' 3d shape properties, and mapping a 2d video signal representation of an object in the shape space, the coordinates of the object in the shape space indicating the object's 3d shape.

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 method and a system for determining an object segment in an electronic image. Preferably the method or system is sufficiently fast to allow real-time processing. A method for determining an object segment in an electronic image may comprise the steps of unsupervised learning of a multi-feature segmentation and of forming a relevance map. The method may further comprise the step of estimating the probability of a segment belonging to an object by the overlap of the segment and the relevance map in the electronic image.

Abstract: A method for generating a saliency map for a robot device having sensor means, the saliency map indicating to the robot device patterns in the input space of the sensor means which are important for carrying out a task; wherein the saliency map comprises a weighted contribution from a disparity saliency selection carried out on the basis of depth information gathered from the sensor means, such that a weighted priority is allocated to patterns being within a defined peripersonal space in the environment of the sensor means.

Abstract: The invention relates to a method for processing video signals from a video sensor, in order to extract 3d shape information about objects represented in the video signals, the method comprising the following steps: providing a memory in which objects are stored in a 3d shape space, the shape space being an abstract feature space encoding the objects' 3d shape properties, and mapping a 2d video signal representation of an object in the shape space, the coordinates of the object in the shape space indicating the object's 3d shape.

Abstract: A robot controller including a multitude of simultaneously functioning robot controller units. Each robot controller unit is adapted to receive an input signal, receive top-down information, execute an internal process or dynamics, store at least one representation, send top-down information, issue motor commands wherein each motor command has a priority. The robot controller selects one or several motor commands issued by one or several units based on their priority. Each robot controller unit may read representations stored in other robot controller units.

Abstract: Within the frameworks of hierarchical neural feed-forward architectures for performing real-world 3D invariant object recognition a technique is proposed that shares components like weight-sharing (2), and pooling stages (3, 5) with earlier approaches, but focuses on new methods for determining optimal feature-detecting units in intermediate stages (4) of the hierarchical network. A new approach for training the hierarchical network is proposed which uses statistical means for (incrementally) learning new feature detection stages and significantly reduces the training effort for complex pattern recognition tasks, compared to the prior art. The incremental learning is based on detecting increasingly statistically independent features in higher stages of the processing hierarchy. Since this learning is unsupervised, no teacher signal is necessary and the recognition architecture can be pre-structured for a certain recognition scenario.

Abstract: A method and a system for determining an object segment in an electronic image. Preferably the method or system is sufficiently fast to allow real-time processing. A method for determining an object segment in an electronic image may comprise the steps of unsupervised learning of a multi-feature segmentation and of forming a relevance map. The method may further comprise the step of estimating the probability of a segment belonging to an object by the overlap of the segment and the relevance map in the electronic image.

Abstract: A method for generating a saliency map for a robot device having sensor means, the saliency map indicating to the robot device patterns in the input space of the sensor means which are important for carrying out a task; wherein the saliency map comprises a weighted contribution from a disparity saliency selection carried out on the basis of depth information gathered from the sensor means, such that a weighted priority is allocated to patterns being within a defined peripersonal space in the environment of the sensor means.

Abstract: Within the frameworks of hierarchical neural feed-forward architectures for performing real-world 3D invariant object recognition a technique is proposed that shares components like weight-sharing (2), and pooling stages (3, 5) with earlier approaches, but focuses on new methods for determining optimal feature-detecting units in intermediate stages (4) of the hierarchical network. A new approach for training the hierarchical network is proposed which uses statistical means for (incrementally) learning new feature detection stages and significantly reduces the training effort for complex pattern recognition tasks, compared to the prior art. The incremental learning is based on detecting increasingly statistically independent features in higher stages of the processing hierarchy. Since this learning is unsupervised, no teacher signal is necessary and the recognition architecture can be pre-structured for a certain recognition scenario.