Abstract: A method and corresponding system for improving an interaction process in a social network for a user with at least one other person is provided. The method comprises a step of, in a training phase, acquiring sensor data on at least a user state and interaction data on a social interaction of a human person with the at least one other person. The acquired sensor data and the interaction data is then analyzed in order to generate classifier data from the acquired sensor data and the acquired interaction data. In a subsequent application phase, the method acquires current sensor data on at least the user state of the at least one other person, predicts an interaction score for the user based on the acquired current sensor data and the classifier data, and generates an interaction identifier for the user for an interaction with the at least one other person in the social network based on the predicted interaction score.

Abstract: The present disclosure relates to a system for reminding a person to perform an activity. The system comprise a robot configured to carry out different behaviors, wherein the activity and its corresponding trigger condition are set by a user and the system selects, from the different behaviors, a first behavior assigned to the activity, senses the person, determines, based on the sensors information, whether or not the activity is performed by the person in accordance with the trigger condition. The robot carries out the selected behavior if the activity is not performed by the person in accordance with the trigger condition, wherein after or during the selected behavior is carried out, an activity of the person is determined based on the information derived from the sensors to select a second behavior from the different behaviors.

Abstract: The present disclosure relates to a system for reminding a person to perform an activity. The system comprise a robot configured to carry out different behaviors, wherein the activity and its corresponding trigger condition are set by a user and the system selects, from the different behaviors, a first behavior assigned to the activity, senses the person, determines, based on the sensors information, whether or not the activity is performed by the person in accordance with the trigger condition. The robot carries out the selected behavior if the activity is not performed by the person in accordance with the trigger condition, wherein after or during the selected behavior is carried out, an activity of the person is determined based on the information derived from the sensors to select a second behavior from the different behaviors.

Abstract: A method and corresponding system for improving an interaction process in a social network for a user with at least one other person is provided. The method comprises a step of, in a training phase, acquiring sensor data on at least a user state and interaction data on a social interaction of a human person with the at least one other person. The acquired sensor data and the interaction data is then analyzed in order to generate classifier data from the acquired sensor data and the acquired interaction data. In a subsequent application phase, the method acquires current sensor data on at least the user state of the at least one other person, predicts an interaction score for the user based on the acquired current sensor data and the classifier data, and generates an interaction identifier for the user for an interaction with the at least one other person in the social network based on the predicted interaction score.

Abstract: The present disclosure relates to a system for continuously sharing behavioral states of a creature. The system comprises a robot configured to carry out different behaviors, at least one sensing means for automatically sensing the creature, a determining means for continuously determining the state of the creature based on information derived from the at least one sensing means and a selecting means for selecting, from the different behaviors, a behavior that is assigned to the determined state, wherein the robot is configured to carry out the selected behavior.

Abstract: The invention relates to a driving assistant adapted for active control of a vehicle based on predictions of a behavior of a detected object. A method aspect of the invention comprises accepting a first prediction of a behavior associated with the detected object from a first prediction subsystem and a second prediction from a second prediction subsystem; determining a control signal based on a combination of the first prediction and the second prediction; and initiating active control of the vehicle based on the control signal.

Abstract: A method and a system for communicating a an ego-vehicle's determined behavior to a target object is for use in a driver assistance system of a vehicle. The method includes steps of acquiring data of a traffic scene preferably by sensor means configured to sense an environment of the vehicle, calculating a prediction result including a target object's behaviour based on the acquired sensor data, determining an action of the host vehicle based on the prediction result and generating an actuation signal for performing the determined action, and determining a communication information indicating the determined action. The communication information is output to a communication means for communication to the target object via at least one of a lighting means of the vehicle and a car-to-x communication means.

Abstract: A method and vehicle for assisting in controlling an ego-vehicle determines a situation currently encountered by the ego-vehicle comprising the ego-vehicle and another vehicle. Probabilities of future behaviors of the other vehicle are computed based on the current situation. Potential future behaviors of the ego-vehicle are determined and probabilities of a various possible future situations are computed based on combinations of the predicted future behaviors of the other vehicle and the potential future behaviors of the ego-vehicle. Trajectories for associated behaviors are optimized for the ego-vehicle for some of these possible future situations and a trajectory is selected based a future situation probability. Since each trajectory is associated with one potential future behavior of the ego-vehicle, selection of a trajectory means a selection of a particular behavior.

Abstract: A method for computationally predicting future movement behavior of a target object and program includes producing sensor data by at least one sensor physically sensing the environment of a host vehicle, and computing a plurality of movement behavior alternatives of the target object sensed by the sensors. The computing includes predicting movement behaviors of the target object applying context based prediction using at least one indirect indicator and/or indicator combinations derived from senor data. In the context based prediction, a probability that the target object will execute a movement behavior is estimated. A future position of the target object is estimated and a signal representing the estimated future position is outputted. At least one history indicator for a movement behavior alternative is generated for a current point in time using at least one indicator of an indirect indicator at a point in the past.

Abstract: The invention relates to a driving assistance system including a prediction subsystem in a vehicle. According to a method aspect of the invention, the method comprises the steps of accepting an environment representation; calculating a confidence estimate related to the environment representation based on applying plausibility rules on the environment representation, and providing the confidence estimate as input for an evaluation of a prediction based on the environment representation.

Abstract: The invention regards a method for improving performance of a method for computationally predicting a future state of a target object, a driver assistance system and a vehicle with such driver assistance system. First data describing a traffic environment including a target object is acquired. On the basis of the acquired data at least one prediction step for estimating a future state of an object in the traffic environment is performed and a signal indicative of a prediction result describing an estimated future state of the target object and/or an ego vehicle is generated. An actual state of the target object and/or the ego vehicle is observed and quality of the prediction by comparing the observed actual state and the prediction result is estimated. Finally the prediction result and/or parameters of the prediction algorithm is adapted.

Abstract: A system and method assists a driver of a host vehicle in potential lane change situations. The method includes producing sensor data by a sensor physically sensing the environment of the host vehicle, predicting future movement behavior of at least one sensed vehicle, and determining whether a gap on a neighboring lane of the host vehicle exists. If the neighboring lane of the host vehicle would fit better for the predicted future movement behavior, a recommendation information signal is generated. Feasibility is determined by combining the determination result of the existence of a gap and the predicted future behavior. A notification for the host vehicle is output or, if lane change is feasible, signals for performing autonomous lane change based upon the recommendation information signal by the host vehicle are output.

Abstract: The invention regards a method for assisting a driver of a vehicle by computationally predicting a future movement behavior of a target vehicle. The method comprises steps of acquiring data describing a traffic environment of a host vehicle, computing a plurality of future movement behavior alternatives for a target vehicle, by predicting movement behavior of the target vehicle based on the data describing the traffic environment. The prediction step calculates a probability that the target object will execute a movement behavior and information relating to future behavior of the target vehicle is output. The method estimates a global scene context and adapts the predicted behavior based on the estimated global scene context. The adaptation of the behavior prediction is performed by at least one of adapting indicator values in situation models employed by a context-based prediction, by adapting a result of the context-based prediction and adapting the overall prediction result.

Abstract: The invention regards a method for improving performance of a method for computationally predicting a future state of a target object, a driver assistance system and a vehicle with such driver assistance system. First data describing a traffic environment including a target object is acquired. On the basis of the acquired data at least one prediction step for estimating a future state of an object in the traffic environment is performed and a signal indicative of a prediction result describing an estimated future state of the target object and/or an ego vehicle is generated. An actual state of the target object and/or the ego vehicle is observed and quality of the prediction by comparing the observed actual state and the prediction result is estimated. Finally the prediction result and/or parameters of the prediction algorithm is adapted.

Abstract: A method and a system for communicating a an ego-vehicle's determined behavior to a target object is for use in a driver assistance system of a vehicle. The method includes steps of acquiring data of a traffic scene preferably by sensor means configured to sense an environment of the vehicle, calculating a prediction result including a target object's behaviour based on the acquired sensor data, determining an action of the host vehicle based on the prediction result and generating an actuation signal for performing the determined action, and determining a communication information indicating the determined action. The communication information is output to a communication means for communication to the target object via at least one of a lighting means of the vehicle and a car-to-x communication means.

Abstract: The invention relates to a driving assistance system including a prediction subsystem in a vehicle. According to a method aspect of the invention, the method comprises the steps of accepting a set of basic environment representations; allocating a set of basic confidence estimates; associating weights to the basic confidence estimates; calculating a weighted composite confidence estimate for a composite environment representation; and providing the weighted composite confidence estimate as input for an evaluation of a prediction based on the composite environment representation.

Abstract: The invention regards a method for assisting a driver of a vehicle by computationally predicting a future movement behaviour of a target vehicle. The method comprises steps of acquiring data describing a traffic environment of a host vehicle, computing a plurality of future movement behaviour alternatives for a target vehicle, by predicting movement behaviour of the target vehicle based on the data describing the traffic environment. The prediction step calculates a probability that the target object will execute a movement behaviour and information relating to future behaviour of the target vehicle is output. The method estimates a global scene context and adapts the predicted behaviour based on the estimated global scene context. The adaptation of the behaviour prediction is performed by at least one of adapting indicator values in situation models employed by a context-based prediction, by adapting a result of the context-based prediction and adapting the overall prediction result.

Abstract: A system and method assists a driver of a host vehicle in potential lane change situations. The method includes producing sensor data by a sensor physically sensing the environment of the host vehicle, predicting future movement behavior of at least one sensed vehicle, and determining whether a gap on a neighboring lane of the host vehicle exists. If the neighboring lane of the host vehicle would fit better for the predicted future movement behavior, a recommendation information signal is generated. Feasibility is determined by combining the determination result of the existence of a gap and the predicted future behavior. A notification for the host vehicle is output or, if lane change is feasible, signals for performing autonomous lane change based upon the recommendation information signal by the host vehicle are output.

Abstract: A method for computationally predicting future movement behavior of a target object and program includes producing sensor data by at least one sensor physically sensing the environment of a host vehicle, and computing a plurality of movement behavior alternatives of the target object sensed by the sensors. The computing includes predicting movement behaviors of the target object applying context based prediction using at least one indirect indicator and/or indicator combinations derived from senor data. In the context based prediction, a probability that the target object will execute a movement behavior is estimated. A future position of the target object is estimated and a signal representing the estimated future position is outputted. At least one history indicator for a movement behavior alternative is generated for a current point in time using at least one indicator of an indirect indicator at a point in the past.