Abstract: Crash detection in a road vehicle includes determining an impact location. Acceleration and yaw rate are measured, and occurrence of an impact is detected by comparing a total acceleration to an impact threshold. An impact angle is determined according to an arctangent of a ratio of lateral and longitudinal accelerations. A center-of-gravity to impact distance is determined according to vehicle mass, moment of inertia, acceleration, and yaw rate. When the yaw rate is less than a yaw threshold and the impact angle is within a predetermined range of an integer multiple of 90°, then the impact location is determined in response to a projection of the impact distance selected according to signs of the accelerations. Otherwise, the impact location is determined in response to a projection of the impact distance selected according to signs of the accelerations and a sign of the yaw rate.

Abstract: Data describing operation of a vehicle is provided to a deep neural network. A vehicle wheel impact event is determined based on output of the deep neural network. Alternatively or additionally, it is possible to determine the wheel impact event based on output of a threshold based algorithm that compares vehicle acceleration and the velocity to one or more thresholds.

Abstract: Disclosed are a method and a device for improving an output accuracy of a digital-to-analog converter. The method includes: calculating an output error of the digital-to-analog converter based on output accuracy and an input error of the digital-to-analog converter; obtaining at least one of the output error, comparing the at least one output error against a preset threshold, and adjusting an integer input value of the digital-to-analog converter according to a comparison result.

Abstract: A method includes controlling charging a battery pack of an electrified vehicle, via a control system of the electrified vehicle, based on climate conditions, traffic conditions, and learned driving habits of a driver of the electrified vehicle. The control system is configured to create a smart charging schedule for either adding or not adding an additional charge to the battery pack in anticipation of an expected upcoming drive cycle.

Abstract: The present invention extends to methods, systems, and computer program products for path planning for autonomous moving devices. Aspects of the invention include planning a path for a mobile robot to move autonomously in an environment that includes other static and moving obstacles, such as, for example, other mobile devices and pedestrians, without reference to a prior map of the environment. A planned path for a mobile robot can be determined, adjusted, and adapted using diffusion maps to avoid collisions while making progress towards a global destination. Path planning can include using transition probabilities between grid points to find a feasible path through parts of the environment to make progress towards the global destination. In one aspect, diffusion maps are used in combination with a receding horizon approach, including computing diffusion maps at specified time intervals.

Abstract: The present disclosure extends to methods, systems, and computer program products for predicting the movement intent of objects. In one aspect, a mobile robot predicts the movement intent of pedestrians from past pedestrian trajectory data and landmark proximity. In another aspect, a host mobile robot predicts the movement intent of other robots/vehicles using motion analysis models for different driving behaviors, including curve negotiation, zigzagging, rapid acceleration/deceleration, and tailgating. In a further aspect, a mobile robot can self-predict movement intent and share movement intent information with surrounding robots/vehicles (e.g., through vehicle-to-vehicle (V2V) communication). The mobile robot can self-predict future movement by comparing the operating values calculated from the monitored components to the operating limits of the mobile robot (e.g., an adhesion limit between the tires and ground).

Abstract: The present disclosure is directed toward a robotic system that includes a robotic arm, a robotic end-effector, a lock, and a control system. The robotic end-effector is detachably coupled to the robotic arm and includes a locomotion device to move the robotic end-effector independent of the robotic arm. The lock is disposed with the robotic arm and robotic end-effector, and is operable to detach and attach the robotic arm and the robotic end-effector. The control system is configured to control the robotic arm and the robotic end-effector, and to operate the lock to detach and attach the robotic arm and the robotic end-effector.

Abstract: A computer includes a processor and a memory, the memory including instructions executable by the processor to identify a mobile vehicle position based on global position coordinates of a stationary location transmitter and a localized trajectory of a vehicle that is based on vehicle component data collected after passing the stationary location transmitter and to actuate a vehicle component based on the identified vehicle position.

Abstract: This disclosure is generally directed to systems and methods for using an autonomous vehicle to provide navigation assistance to a delivery robot. In one exemplary implementation, the delivery robot is transported by the autonomous vehicle to a delivery destination such as a residence or a workplace. The delivery robot disembarks at the delivery destination for delivering a package to a recipient at the residence or workplace. A computer system in the autonomous vehicle communicates with a navigation assistance system of the autonomous vehicle to obtain information pertaining to a terrain between the autonomous vehicle and a package drop-off spot at the residence or workplace, and uses the information to generate a route map of the terrain. The autonomous vehicle may transmit the route map and/or navigation instructions derived from the route map, to the delivery robot to assist the delivery robot navigate around obstacles and reach the package drop-off spot.

Abstract: Disclosed are a method and a device for improving an output accuracy of a digital-to-analog converter. The method includes: calculating an output error of the digital-to-analog converter based on output accuracy and an input error of the digital-to-analog converter; obtaining at least one of the output error, comparing the at least one output error against a preset threshold, and adjusting an integer input value of the digital-to-analog converter according to a comparison result.

Abstract: A computer in a vehicle that includes a processor and memory storing instructions executable by the processor. The instruction may include: receive an indication that the vehicle door is ajar; receive sensor data from a rotational-rate sensor in a vehicle; and based on the indication and sensor data, determine a traversal event.

Abstract: Systems, methods, and computer-readable media are disclosed for enhanced human-robot interactions. A device such as a robot may send one or more pulses. The device may identify one or more reflections associated with the one or more pulses. The device may determine, based at least in part on the one or more reflections, a cluster. The device may associate the cluster with an object identified in an image. The device may determine, based at least in part on an image analysis of the image, a gesture associated with the object. The device may determine, based at least in part on the gesture, a command associated with an action. The device may to perform the action.

Abstract: The present disclosure extends to methods, systems, and computer program products for predicting the movement intent of objects. In one aspect, a mobile robot predicts the movement intent of pedestrians from past pedestrian trajectory data and landmark proximity. In another aspect, a host mobile robot predicts the movement intent of other robots/vehicles using motion analysis models for different driving behaviors, including curve negotiation, zigzagging, rapid acceleration/deceleration, and tailgating. In a further aspect, a mobile robot can self-predict movement intent and share movement intent information with surrounding robots/vehicles (e.g., through vehicle-to-vehicle (V2V) communication). The mobile robot can self-predict future movement by comparing the operating values calculated from the monitored components to the operating limits of the mobile robot (e.g., an adhesion limit between the tires and ground).

Abstract: Data describing operation of a vehicle is provided to a deep neural network. A vehicle wheel impact event is determined based on output of the deep neural network. Alternatively or additionally, it is possible to determine the wheel impact event based on output of a threshold based algorithm that compares vehicle acceleration and the velocity to one or more thresholds.

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.

Abstract: A vehicle system includes a processor with access to a memory storing instructions executable by the processor. The instructions include determining whether an autonomous host vehicle can traverse an environmental obstacle, and if the autonomous host vehicle can traverse the environmental obstacle, controlling an active suspension system in accordance with the environmental obstacle and controlling the autonomous host vehicle to traverse the environmental obstacle.

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.

Abstract: A method for identifying vehicle vibration includes receiving signals indicative of a vehicle vibration from one or more vehicle sensors while the vehicle is in operation. The method also includes determining a magnitude of the vehicle vibration at one or more target frequency bands. The method additionally includes determining whether the vehicle vibration is associated with one or more wheels of the vehicle based on the magnitude of the vehicle vibration at the one or more target frequency bands. The method further includes generating a diagnostic recommendation when the vehicle vibration is associated with the one or more wheels of the vehicle.

Abstract: Light or moderate impacts against a vehicle are detected. Measured acceleration and yaw rate are compared to baseline thresholds in a baseline state. When the acceleration is above the threshold, a distance from an estimated impact location to a vehicle center-of-gravity is determined. When the determined distance is less than a vehicle edge distance, an impact-suspected state will be entered if at least one of the acceleration and yaw rate is above the respective threshold for a predetermined duration. In the impact-suspected state, a plurality of vehicle dynamic behaviors are monitored for confirming occurrence of the light impact. A return is made to the baseline state if the acceleration and yaw rate fail to remain above the respective threshold or if the calculated distance fails to remain less than the edge distance. The impact is detected when at least one of the behaviors confirms the occurrence.

Abstract: A method includes controlling charging a battery pack of an electrified vehicle, via a control system of the electrified vehicle, based on climate conditions, traffic conditions, and learned driving habits of a driver of the electrified vehicle. The control system is configured to create a smart charging schedule for either adding or not adding an additional charge to the battery pack in anticipation of an expected upcoming drive cycle.