Abstract: A method for error event analysis performed by an electronic device includes: in response to an error event of an autonomous driving system, feeding a sequence of signal states, collected from the autonomous driving system into a prediction model, where the prediction model is trained based on signal states collected from a plurality of autonomous driving systems for predicting, based on a first signal state, a second signal state, the first signal state representing signals collected at a first time, and the second signal state representing signals collected at a second time succeeding the first time; converting the error event into an event signal state having signal values at an event time; comparing the second signal state with the event signal state; and in response to the second signal state matching the event signal state, tracing the error event back to the first signal state as a root cause.

Abstract: A computing system can receive motion prediction data from a vehicle, where the motion prediction data is generated by a motion prediction model executing on the vehicle. Based on the motion prediction data, the system can determine predicted trajectories for a plurality of entities in a surrounding environment of the vehicle. The system can evaluate a prediction performance of the motion prediction model by (i) matching, for each respective entity of the plurality of entities, a predicted endpoint of each predicted trajectory of the set of predicted trajectories to one or more underlying lanes of the road segment, (ii) matching a ground truth future position of the entity to one or more underlying lanes of the underlying lane topology, and (iii) determining a distance along one or more lane segments between the lane(s) matched to the predicted endpoint and the lane(s) matched to the ground truth future position.

Abstract: An influence of one road user on at least one other road user is predicted by evaluating traffic scenarios by a trained artificial neural network. The neural network is trained by recorded traffic scenarios, the traffic scenarios include several road users and are labelled with score values that represent an influence of one road user by other road users. A respective score value for one road user with respect to another road user is calculated based on a deviation between two trajectories of the one road user. One of the two trajectories is a detected real trajectory that the one road user actually takes in a respective recorded traffic scenario, and the other of the two trajectories is a simulated trajectory determined in a simulation and representing a trajectory that the one road user would take in the same traffic scenario if the other road user were not present.

Abstract: A central computing unit determines and provides lane routes of streets to vehicles of a vehicle fleet. A geometric map having geometric lane boundaries and applying a grid with grid cells of a specified size to the map is provided. Fleet data is collected from fleet, the fleet data including position sequences covered by the fleet vehicles. Vehicle orientations of the vehicles at positions of the grid cells are determined from the collected position sequences. The determined vehicle orientations are discretized and a histogram is generated for each individual grid cell position for the discretized vehicle orientations. A map section having a specified amount of grid cells is selected and the lane routes on the map section are determined using a learning-based method from the histograms created for the grid cells of the map section and the geometric lane boundaries on the map section.

Abstract: Incremental updates are used for versioning digital road maps. A base map is provide. A hash function is applied to the base map to generate a version hash of the base map. Map difference bundles are provided, a map difference bundle includes at least one individual change of a map feature. The digital road map is versioned by forming at least one continuous version chain, beginning with the base map. To generate a current map version, a map difference bundle to be applied is linked to the map version in the version chain before the current map version. For this the version hash of the previous map version and the map difference bundle to be applied are input into the hash function as input parameters to generate a version hash for the current map version.

Abstract: A method for error event analysis performed by an electronic device includes: in response to an error event of an autonomous driving system, feeding a sequence of signal states, collected from the autonomous driving system into a prediction model, where the prediction model is trained based on signal states collected from a plurality of autonomous driving systems for predicting, based on a first signal state, a second signal state, the first signal state representing signals collected at a first time, and the second signal state representing signals collected at a second time succeeding the first time; converting the error event into an event signal state having signal values at an event time; comparing the second signal state with the event signal state; and in response to the second signal state matching the event signal state, tracing the error event back to the first signal state as a root cause.

Abstract: A vehicle computing system can receive sensor data from a sensor suite of the vehicle. The system can execute a autoencoder on the sensor data to compress the sensor data, and can stored the compressed sensor data in an on-board database of the vehicle.

Abstract: A method of detecting ghost objects in sensor measurements of an environment of a vehicle involves obtaining map context information from a digital road map. Objects having associated attributes are recognized in an environment of the vehicle, and social context information of the objects in relation to one another is generated. All available data of a traffic situation with the vehicle and the objects is stored in a graph structure, having nodes and edges. Relational information is depicted in the graph structure by the edges. Anomalies and patterns are searched for in features of the graph structure while taking the map context information and the social context information into account, whereby ghost objects are classified using recognized anomalies and patterns.

Abstract: A system can receive a perception output from an autonomous vehicle as the autonomous vehicle traverses a segment of a route. The perception output can be based on sensor data generated by a sensor suite of the autonomous vehicle. The system can generate, for an output device of a user, a human-perceptible three-dimensional rendering of an external environment of the vehicle based on the perception output. The human-perceptible three-dimensional rendering of the external environment can be as the user performs driving operations for the vehicle to traverse the segment of the route.

Abstract: A computing system can receive motion prediction data from a vehicle, where the motion prediction data is generated by a motion prediction model executing on the vehicle. Based on the motion prediction data, the system can determine predicted trajectories for a plurality of entities in a surrounding environment of the vehicle. The system can evaluate a prediction performance of the motion prediction model by (i) matching, for each respective entity of the plurality of entities, a predicted endpoint of each predicted trajectory of the set of predicted trajectories to one or more underlying lanes of the road segment, (ii) matching a ground truth future position of the entity to one or more underlying lanes of the underlying lane topology, and (iii) determining a distance along one or more lane segments between the lane(s) matched to the predicted endpoint and the lane(s) matched to the ground truth future position.

Abstract: A vehicle computing system can receive raw sensor data in both a traditional sensor data processing module and a learned sensor data processing module. Each module can reproject sensor data in BEV space, and can optionally perform sensor fusion when multiple sensor data types are processed.

Abstract: A backend computing system can receive compressed sensor data from a database of one or more vehicles that operate throughout a road network. The system can execute a set of learnable decoders on the compressed sensor data to decompress the compressed sensor data in accordance with a set of tasks of the set of learnable decoders.

Abstract: A vehicle computing system can receive sensor data from a sensor suite of the vehicle. The system can execute a autoencoder on the sensor data to compress the sensor data, and can stored the compressed sensor data in an on-board database of the vehicle.

Abstract: A system can perform a method that includes receiving sensor data from a subset of human-driven vehicles that have moved through an intersection in a region, where the sensor data indicates a respective set of trajectories of respective human-driven vehicles of the subset through the intersection. The method can further include processing the sensor data to classify driving behavior of each human-driven vehicle of the subset of human-driven vehicles through the intersection. The method can further include classifying the intersection to label an autonomy map to include pass-through information for at least one of autonomous vehicles or semi-autonomous vehicles driving through the intersection.

Abstract: A computing system can receive sensor data from a set of human-driven vehicles operating through a road segment. The system can process the sensor data to determine a set of right-of-way rules for autonomous vehicle driving through the road segment. In certain examples, the system can obtain an autonomous driving map utilized by autonomous vehicles for operating through the road segment, and modify the autonomous driving map to include the set of right-of-way rules for the road segment.

Abstract: In a method for the operation of an internal combustion engine either on all cylinders (as full engine) or with only some cylinders in operation (cylinder cut-off), the cylinders are divided, in the firing order, into two groups of alternating cylinders which are selectively operative with an angular ignition spacing twice that of the cylinders of the engine when operating as full engine, the two groups of cylinders being activated alternately during engine operation with cylinder cut-off.

Abstract: In a method for the operation of an internal combustion engine either on all cylinders (as full engine) or with only some cylinders in operation (cylinder cut-off), the cylinders are divided, in the firing order, into two groups of alternating cylinders which are selectively operative with an angular ignition spacing twice that of the cylinders of the engine when operating as full engine, the two groups of cylinders being activated alternately during engine operation with cylinder cut-off.