A method for training a behavior planner for an at least partially self-driving target vehicle on the basis of observation data regarding kinematics and/or dynamics that have been recorded during at least one test drive in a test vehicle includes identifying a driving maneuver that moves the test vehicle from an initial state to an end state using the observation data, ascertaining the maneuver end time, retrieving a maneuver duration required by the target vehicle to perform the identified driving maneuver from a dynamics model of the target vehicle, labeling observation data from a time interval, defined by the maneuver duration, with the identified driving maneuver, and training the behavior planner, using the labeled observation data, to map observation data that indicate a state of the target vehicle to at least one driving maneuver to be performed.

A domain specific language for use in constructing simulations within real environments is described. In an example, a computing device associated with a vehicle can receive, from one or more sensors associated with the vehicle, sensor data associated with an environment within which the vehicle is positioned. In an example, the vehicle can be an autonomous vehicle. The computing device associated with the vehicle can receive simulated data associated with one or more primitives that are to be instantiated as a scenario in the environment. The computing device can merge the sensor data and the simulated data to generate aggregated data and determine a trajectory along which the vehicle is to drive based at least in part on the aggregated data. The computing device can determine instructions for executing the trajectory and can assess the performance of the vehicle based on how the vehicle responds to the scenario.

A driver assist design analysis system includes a processing system and a database that stores vehicle data, vehicle operational data, vehicle accident data, and environmental data related to the configuration and operation of a plurality of vehicles with driver assist systems or features. The driver assist design analysis system also includes one or more analysis engines that execute on the processing system to determine one or more driving anomalies (e.g., accidents or poor driving operation) based on the vehicle operational data, and that correlate or determine a statistical relationship between the driving anomalies and the operation of the driver assist systems or features. The driver assist design analysis system then determines an effectiveness of operation of one or more of the driver assist systems or features based on the statistical relationship to determine a potential design flaw in the driver assist systems or features, and the driver assist design analysis system notifies a user or receiver of the potential design flaw.

A computer-implemented method for training a machine learning system to generate driving profiles of a vehicle. The method includes first travel routes are selected from a first database having travel routes, a generator of the machine learning system receives the first travel routes and generates first driving profiles for each of the first travel routes, travel routes and associated driving profiles determined during vehicle operation are stored in a second database, second travel routes and respective associated second driving profiles determined during vehicle operation are selected from the second database, a discriminator of the machine learning system receives pairs made up of one of the first travel routes with the respective associated first generated driving profile and pairs made up of second travel routes with the respective associated second driving profile determined during vehicle operation, as input variables.

A computer-implemented method for training a machine learning system for generating driving profiles and/or driving routes of a vehicle including: a generator obtains first random vectors and generates first driving routes and associated first driving profiles related to the first random vectors, driving routes and respectively associated driving profiles recorded in driving mode are stored in a data base, second driving routes and respectively associated second driving profiles recorded in driving mode are selected from the database, a discriminator obtains first pairs made up of first generated driving routes and respectively associated first generated driving profiles and second pairs made up of second driving routes and respectively associated second driving profiles recorded in driving mode, the discriminator calculates outputs that characterize each pair, and a target function is optimized as a function of the outputs of the discriminator.

A method for reducing exhaust gas emissions of a drive system of a vehicle including an internal combustion engine, including generating first driving profiles using a computer-implemented machine learning system, the statistical distribution of the first driving profiles being a function of a statistical distribution of second driving profiles measured during real driving operation, calculating respective exhaust gas emissions for the first driving profiles using a computer-implemented modeling of the vehicle or the drive system, adapting the drive system as a function of at least one of the calculated exhaust gas emissions, the adaptation taking place as a function of a level or of a profile of the calculated exhaust gas emissions and of a statistical frequency of the corresponding first driving profile, the statistical frequency of the corresponding first driving profile being ascertained with the aid of the statistical distribution of the first driving profiles.

In various examples, training sensor data generated by one or more sensors of autonomous machines may be localized to high definition (HD) map data to augment and/or generate ground truth datae.g., automatically, in embodiments. The ground truth data may be associated with the training sensor data for training one or more deep neural networks (DNNs) to compute outputs corresponding to autonomous machine operationssuch as object or feature detection, road feature detection and classification, wait condition identification and classification, etc. As a result, the HD map data may be leveraged during training such that the DNNsin deploymentmay aid autonomous machines in navigating environments safely without relying on HD map data to do so.

Systems and methods for improving fuel economy in vehicles such as Class 8 trucks are provided. In some embodiments, signals indicating states of the powertrain are collected and used to generate fuel rate optimization values. Fuel rate optimization values may indicate a difference between optimum fuel flow rates and actual fuel flow rates during a vehicle drive cycle. Recorded fuel rate optimization values may be used to compare different vehicle configurations during testing, and may also be used to evaluate vehicle performance during real-world operation.

A plug-compatible interface between a car and its human and/or computer driver makes both car and driver a black box, or abstraction, to the other. The two black boxes can then be developed and built independently before being integrated together only at the final stage. Designers on both the car and driver sides of the interface need design only to the interface and need not worry about how things are done on the other side of it. When cars and computer drivers are built to interact over a plug-compatible interface, any computer driver works with any car. If a computer driver becomes outdated, it can be updated or replaced much more quickly and cheaply than replacing the entire car.

Our car operating system allows a car's driver to controlusing abstract direction and speed commandsthe car's devices that make the car move. The car operating system uses information like the current state of the car's devices to process those high-level abstract commands and generate device-specific commands at a lower level of abstraction to send to the car devices that will implement the driver's commands. The car operating system sits between the driver of the car (which may be a human or an automated driving program) and the car's devices, much like a computer operating system sits between the user of a computer (which may be a human or an application program) and the computer's devices. The car operating system performs two functions: (1) Provides an abstract machine that allows the car's driver to use more powerful abstract commands rather than more primitive device-level commands. (2) Manages the car's resources so that the car's driver does not have to control each device directly.