Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent trajectory prediction using anchor trajectories.

An example operation may include one or more of identifying transports operating on a roadway, determining a degree of transport traffic based on the identified transports, when the degree of transport traffic has exceeded a traffic level, assigning one or more of the identified transports as a roadway manager, controlling movement of the roadway manager, and generating a roadway indicator on the roadway manager to direct the identified transports.

The invention relates to a computer-aided method for generating a drive cycle for a vehicle which is suitable for simulating a driving operation, in particular a real driving operation. The computer-aided method comprises establishing a state vector of the drive cycle for a current time interval from a past speed curve, providing an acceleration prediction model, determining an acceleration value in consideration of probabilities resulting from the acceleration prediction model and the state vector, integrating the determined acceleration value over the current time interval in order to obtain a predicted speed value for a next future time interval, and appending the predicted speed value to the past speed curve in order to generate the drive cycle. Furthermore, the invention relates to a device for generating a drive cycle for a vehicle which is suitable for simulating a driving operation, in particular a real driving operation, and means for establishing a state vector of the drive cycle for a current time interval from a past speed curve, means for determining an acceleration value in consideration of probabilities resulting from the acceleration prediction model and the state vector, means for integrating the determined acceleration value over the current time interval in order to obtain a predicted speed value for a next future time interval, and means for appending the predicted speed value to the past speed curve in order to generate the drive cycle.

Systems and methods are provided for predicting blind spot incursions for a host vehicle. In one implementation, a navigation system for a host vehicle may comprise a processor. The processor may be programmed to receive, from an image capture device located on a rear of the host vehicle, at least one image representative of an environment of the host vehicle. The processor may be programmed to analyze the at least one image to identify an object in the environment of the host vehicle and to determine kinematic information associated with the object. The processor may further be programmed to predict, based on the kinematic information, that the object will travel in a region outside of a field of view of the image capture device and perform a control action based on the prediction.

Implementations for an intelligent road barrier (IRB) system can include a plurality of road barriers located along a roadway, and a plurality of IRB kits, each IRB kit being including a set of sensors configured to obtain sensor data representative of at least a portion of a road state of the roadway proximate to the respective road barrier, a data processing unit configured to process at least a portion of the sensor data, a communication unit configured to send at least a portion of the sensor data and to receive sensor data from the one or more other IRB kits, and a state conveyance system configured to convey at least a portion of road state data to one or more vehicles associated with the roadway, the at least a portion of road state data being determined based on the at least a portion of the sensor data.

A communication device includes a communication unit configured to receive first path information from a first vehicle and to receive second path information from a second vehicle, and a processor configured to determine a possibility of the first and second vehicles entering a predetermined area based on the first and second path information, and based on the possibility being greater than a reference, transmit a message for controlling at least one of the first vehicle or the second vehicle through the communication unit to allow the first and second vehicles to enter the predetermined area at different time points.

Techniques for generating simulations for evaluating a performance of a controller of an autonomous vehicle are described. A computing system may evaluate the performance of the controller to navigate the simulation and respond to actions of one or more objects (e.g., other vehicles, bicyclists, pedestrians, etc.) in a simulation. Actions of the objects in the simulation may be controlled by the computing system (e.g., by an artificial intelligence) and/or one or more users inputting object controls, such as via a user interface. The computing system may calculate performance metrics associated with the actions performed by the vehicle in the simulation as directed by the autonomous controller. The computing system may utilize the performance metrics to verify parameters of the autonomous controller (e.g., validate the autonomous controller) and/or to train the autonomous controller utilizing machine learning techniques to bias toward preferred actions.

Among other things, stored data is maintained indicative of potential stopping places that are currently feasible stopping places for a vehicle within a region. The potential stopping places are identified as part of static map data for the region. Current signals are received from sensors or one or more other sources current signals representing perceptions of actual conditions at one or more of the potential stopping places. The stored data is updated based on changes in the perceptions of actual conditions. The updated stored data is exposed to a process that selects a stopping place for the vehicle from among the currently feasible stopping places.

A computing framework for addressing a variety of vehicle conditions includes receiving, from a first set of sensors by an edge compute node, first transportation network data associated with a transportation network region, receiving, from a second set of sensors by a cloud computing node, second transportation network data associated multiple transportation network regions, providing, by the edge compute node to one or more autonomous vehicles at the transportation network region, real-time transportation network region information based on at least the first transportation network data to facilitate control decisions by the one or more autonomous vehicles, and providing, by the cloud computing node to at least the one or more autonomous vehicles, non-real-time transportation network region information based on at least the second transportation network data to facilitate the control decisions by the at least one or more autonomous vehicles.

A system configured to, and method of, generating and providing a data product using data supplied by a multitude of vehicles. The system/method includes carrying out a re-segmentation process in which an initial set of road segments are processed so as to obtain a re-segmented set of road segments; attributing traffic data to at least a subset of the re-segmented set of road segments, wherein, for each road segment of the subset of road segments, a portion of the traffic data is attributed to the road segment based on geographical proximity; carrying out a road segment merging process on the re-segmented set of road segments in order to obtain a merged set of road segments; aggregating metrics associated with the merged set of road segments to obtain aggregated road segment data; generating the data product using the aggregated road segment data; and providing the data product to a third party.