Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive an image including a physical landmark, output a plurality of synthetic images, wherein each synthetic image is generated by simulating at least one ambient feature in the received image, generate respective feature vectors for each of the plurality of synthetic images, and actuate one or more vehicle components upon identifying the physical landmark in a second received image based on a similarity measure between the feature vectors of the synthetic images and a feature vector of the second received image, the similarity measure being one of a probability distribution difference or a statistical distance.

Abstract: The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.

Abstract: A computing system can determine moving objects in a sequence of images based on recursively calculating red-green-blue (RGB) eccentricity 249 k based on a video data stream. A vehicle can be operated based on the determined moving objects. The video data stream can be acquired by a color video sensor included in the vehicle or a traffic infrastructure system.

Abstract: The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine optimal vehicle actions based on a modified version of a Nash equilibrium solution to a multiple agent game, wherein the Nash equilibrium solution is modified by performing an adaptive grid search optimization technique based on calculating rewards and penalties for the agents to determine optimal vehicle actions, wherein the agents include one or more of autonomous vehicles, non-autonomous vehicles, stationary objects, and non-stationary objects including pedestrians and wherein the rewards and the penalties for the agents are determined by simulating behavior of the agents to determine possible future states for the agents to determine the optimal vehicle actions. The instructions can include further instructions to determine a vehicle path based on the optimal vehicle actions and download the vehicle path to the vehicle.

Abstract: A vehicle controller receives sensor outputs and identifies features in the sensor outputs. The controller determines a trajectory based on the features and generates control signals to vehicle actuators to follow the trajectory. Eccentricity of the control signals is evaluated and if it meets a threshold condition is met an intervention is performed such as discarding or modifying the control signal or initiating a safety procedure. Eccentricity may be determined using an unsupervised machine learning model. The threshold condition may be a dynamic threshold condition such as using the n-sigma approach or the Chebyshev inequality.

Abstract: A system, comprising a first computer that includes a processor and a memory. The memory stores instructions executable by the processor to input an expected control input to a second computer, and then, to determine a response resulting from the expected control input. The memory stores instructions to determine a compensated control input based on the expected control input and the response, and to input the compensated control input to the second computer to achieve the expected control input. The second computer is provided to actuate a vehicle component to achieve the expected control input.

Abstract: Information about a device may be emotively conveyed to a user of the device. Input indicative of an operating state of the device may be received. The input may be transformed into data representing a simulated emotional state. Data representing an avatar that expresses the simulated emotional state may be generated and displayed. A query from the user regarding the simulated emotional state expressed by the avatar may be received. The query may be responded to.

Abstract: The present disclosure describes systems and methods that include calculating, via a reinforcement learning agent (RLA) controller, a plurality of state-action values based on sensor data representing an observed state, wherein the RLA controller utilizes a deep neural network (DNN) and generating, via a fuzzy controller, a plurality of linear models mapping the plurality of state-action values to the sensor data.

Abstract: A computing system can receive an image including foreground pixels. The foreground pixels can be determined based on determining eccentricity ?k based on a sequence of images acquired by a stationary sensor. The vehicle can determine moving objects in the image based on the foreground pixels. The vehicle can be operated based on the moving objects in the image.

Abstract: A computing system can determine a vehicle action based on inputting vehicle sensor data to a first neural network including a first safety agent that can determine a probability of unsafe vehicle operation. The first neural network can be adapted, at a plurality of times, by a periodically retrained deep reinforcement learning agent that includes a second deep neural network including a second safety agent. A vehicle can be operated based on the vehicle action.

Abstract: A vehicle controller receives sensor outputs and identifies features in the sensor outputs. The controller determines a trajectory based on the features and generates control signals to vehicle actuators to follow the trajectory. Eccentricity of the control signals is evaluated and if it meets a threshold condition is met an intervention is performed such as discarding or modifying the control signal or initiating a safety procedure. Eccentricity may be determined using an unsupervised machine learning model. The threshold condition may be a dynamic threshold condition such as using the n-sigma approach or the Chebyshev inequality.

Abstract: A system comprises a processor that is programmed to define a plurality of vehicle groups based on vehicle specification data and define a plurality of sub-groups for each of the vehicle groups based on environmental data and sensor data received from each of a plurality of vehicles. The processor is programmed to adjust fuel tank leak detection classifiers for the sub-groups based on ground truth data. The ground truth data include, for each of the plurality of vehicles, a leak detection status and a leak test result.

Abstract: The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.

Abstract: A computing system can receive an image including foreground pixels. The foreground pixels can be determined based on determining eccentricity ?k based on a sequence of images acquired by a stationary sensor. The vehicle can determine moving objects in the image based on the foreground pixels. The vehicle can be operated based on the moving objects in the image.

Abstract: A computing system can determine a vehicle action based on inputting vehicle sensor data to a first neural network including a first safety agent that can determine a probability of unsafe vehicle operation. The first neural network can be adapted, at a plurality of times, by a periodically retrained deep reinforcement learning agent that includes a second deep neural network including a second safety agent. A vehicle can be operated based on the vehicle action.

Abstract: A computing system can determine moving objects in a sequence of images based on recursively calculating red-green-blue (RGB) eccentricity 249 k based on a video data stream. A vehicle can be operated based on the determined moving objects. The video data stream can be acquired by a color video sensor included in the vehicle or a traffic infrastructure system.

Abstract: Methods and systems for adjusting vehicle operation in response to vehicle weight are described. In one example, an adaptive driver demand correction is adjusted in response to vehicle weight. The methods and systems may provide for more consistent powertrain response and lower vehicle emissions at lower vehicle weights.

Abstract: A vehicle controller receives sensor outputs and identifies features in the sensor outputs. The controller determines a trajectory based on the features and generates control signals to vehicle actuators to follow the trajectory. Eccentricity of the control signals is evaluated and if it meets a threshold condition is met an intervention is performed such as discarding or modifying the control signal or initiating a safety procedure. Eccentricity may be determined using an unsupervised machine learning model. The threshold condition may be a dynamic threshold condition such as using the n-sigma approach or the Chebyshev inequality.

Abstract: A system may include a plurality of vehicle sensor and a computer comprising a processor and memory storing instructions executable by the processor. One of the instruction may comprise to determine a driving responsiveness (DR) value using a weighted sum comprising indices of a transition probability matrix (Q), Q being derived from likelihood of transition data (?) between a plurality of driving modes from a set of interacting multiple model (IMM) instruction.