Abstract: This application discloses a computing system to implement map building in an assisted or automated driving system. The computing system can track movement of a vehicle based on sensor measurement data populated in an environmental model and vehicle movement measurements. The computing system can correlate the tracked movement of the vehicle to map data based on a previously detected location of the vehicle relative to the map data. The computing system can modify the map data to include the sensor measurement data utilized to track the movement of the vehicle based on the correlation of the tracked movement of the vehicle to map data. The computing system can modify the map data by building a map of the sensor measurement data and the tracked movement of the vehicle, and populating the map data with the built map.

Abstract: This application discloses a computing system to implement pre-tracking sensor event detection and fusion in an assisted or automated driving system of a vehicle. The computing system can receive an environmental model including sensor measurement data from different types of sensors in the vehicle. The computing system can identify, on a per-sensor type basis, patterns in the sensor measurement data indicative of possible objects proximate to the vehicle. The computing system can associate the patterns in the sensor measurement data from different types of the sensors to identify detection events corresponding to the possible objects proximate to the vehicle. The computing system also can generate values and confidence levels corresponding to properties of the detection events. The computing system can utilize the detection events and corresponding values and confidence levels to pre-classify, identify, and track objects in the environment model.

Abstract: This application discloses a computing system to implement multi-level sensor fusion in an assisted or automated driving system of a vehicle. The computing system can populate an environment model with raw measurement data captured by sensors mounted in a vehicle and with data corresponding to a possible object in an coordinate field associated with the environmental model. The computing system can combine at least a portion of the raw measurement data with the data corresponding to the possible object, and detect an object proximate to the vehicle based, at least in part, on the combination of the raw measurement data and the data corresponding to the possible object. A control system for the vehicle can control operation of the vehicle based, at least in part, on the tracked detection event.

Abstract: This application discloses a computing system to implement vehicle localization in an assisted or automated driving system. The computing system can receive an environmental model populated with measurement data captured by sensors mounted in a vehicle. The computing system can detect a location of the vehicle relative to the map data based on a correlation between the measurement data and the map data. The computing system can detect landmarks in the map data and switch to sparsely-populated map data from higher-definition map data for subsequent location detections. When the computing system does not detect a vehicle location, the computing system can track movement of the vehicle based on subsequent measurement data in the environmental model. After reacquiring a vehicle location, the computing can realign the tracked movement of the vehicle and measured data to the map data or modify the map data to include the tracked data.

Abstract: This application discloses a computing system to implement object tracking in an assisted or automated driving system of a vehicle. The computing system can assign a pre-classification to a detection event in an environmental model, update the environmental model with new sensor measurements and corresponding detection events over time, and track the detection event in the updated environmental model. The computing system can track the detection event by predicting a future state of the detection event with a state change model selected based on the assigned pre-classification, comparing the predicted future state to an actual future state of the detection event in an update to the environmental model, and determining the detection event corresponds to an object proximate to the vehicle based on the comparison. A control system for the vehicle can control operation of the vehicle based, at least in part, on the tracked detection event.

Abstract: This application discloses a computing system to implement low-level sensor fusion in an assisted or automated driving system of a vehicle. The low-level sensor fusion can include receiving raw measurement data from sensors in the vehicle and temporally aligning the raw measurement data based on a time of capture. The low-level sensor fusion can include spatially aligning measurement coordinate fields of the sensors into an environmental coordinate field based, at least in part, on where the sensors are mounted in the vehicle, and then populating the environmental coordinate field with raw measurement data captured by the sensors based on the spatial alignment of the measurement coordinate fields to the environmental coordinate field. The low-level sensor fusion can detect at least one detection event or object based, at least in part, on the raw measurement data from multiple sensors as populated in the environmental coordinate field.

Abstract: Determining a situational annotation of a vehicle based on an annotated environmental model is disclosed. A computing system receives an annotated environmental model for a vehicle. The annotated environmental model can include data from a plurality of modalities. The computing system uses a classifier to determine an annotation of the vehicle situation based, at least in part, on the annotated environmental model. The computing system provides the situational annotation to a driving functionality system. The driving functionality system is configured to use the situational annotation to generate signals to control operation the vehicle.

Abstract: This application discloses a computing system to implement event-driven region of interest management in an assisted or automated driving system of a vehicle. The computing system can identify a portion of an environmental model for a vehicle that corresponds to a region of interest for a driving functionality system. The computing system can detect at least one event associated with the region of interest in the environmental model, and provide data corresponding to the detected event to the driving functionality system. The driving functionality system can utilize the data corresponding to the detected event to control operation of the vehicle.