A method for operating a motor vehicle in the event of an unavoidable collision with a collision object, in particular another vehicle. Environment data relating to the collision object are determined by an environment sensor device including at least one environment sensor and are evaluated to determine at least one driving intervention information for reducing the consequences of a collision. The motor vehicle is automatically guided in accordance with the driving intervention information, and the evaluation of the environment data is carried out together with structural information of the own motor vehicle describing the vehicle structure, in particular including elements absorbing collision energy of the motor vehicle, in such a way that a changed collision point maximizing the deformation energy absorbed by the vehicle structure and to be produced by the driving intervention information is determined when the driving intervention information is determined.

A vehicle behavior prediction device includes a target vehicle detection unit configured to detect a target vehicle existing in a road region, a distance acquisition unit configured to acquire a front distance that is a distance between the target vehicle and an obstacle existing in front of the target vehicle, a turning radius estimation unit configured to estimate a turning radius of the target vehicle, and an entry prediction unit configured to predict whether or not the target vehicle is able to enter a host lane while avoiding an obstacle.

Systems and methods for operating an autonomous vehicle (AV) are provided. The method includes detecting one or more objects in an environment, predicting a first set of predicted object trajectories comprising one or more trajectories for each of the detected one or more objects, generating a plurality of candidate AV trajectories for the AV, scoring each of the candidate AV trajectories according to a cost function, using the scoring to select a final AV trajectory for execution, determining which of the predicted object trajectories affected the final AV trajectory and which did not do so, adding the predicted object trajectories that affected the final AV trajectory to a persisted prediction cache, excluding from the persisted prediction cache any predicted object trajectories that did not affect the final AV trajectory, and executing the final AV trajectory to cause the AV to move along the final AV trajectory.

Techniques for determining occupancy using unobstructed sensor emissions. For instance, a vehicle may receive sensor data from one or more sensors. The sensor data may represent at least locations to points within an environment. Using the sensor data, the vehicle may determine areas within the environment that are obstructed by objects (e.g., locations where objects are located). The vehicle may also use the sensor data to determine areas within the environment that are unobstructed by objects (e.g., locations where objects are not located). In some examples, the vehicle determines the unobstructed areas as including areas that are between the vehicle and the identified objects. This is because sensor emissions from the sensor(s) passed through these areas and then reflected off of objects located farther distances from the vehicle. The vehicle may then generate a map indicating at least the obstructed areas and the unobstructed areas within the environment.

A vehicle management system manages a vehicle in a management area via communication. The vehicle management system includes one or more processors. The one or more processors are configured to: acquire first vehicle information indicating at least a position of a first vehicle configured to switch between autonomous driving and manual driving; acquire second vehicle information indicating at least a position of a second vehicle that performs at least autonomous driving; determine whether a possibility of collision between the first vehicle being driven manually and the second vehicle being driven autonomously is higher than a first threshold, based on the first vehicle information and the second vehicle information; and when the possibility of collision is higher than the first threshold, instruct the first vehicle being driven manually to impose a driving limitation on the first vehicle.

An autonomous vehicle (AV) includes features that allows the AV to comply with applicable regulations and statues for performing safe driving operation. An example method for operating an AV includes receiving, by a computer located in the AV, sensor data that indicates a condition of one or more devices in the AV or of a roadway on which the autonomous vehicle is operating; and causing, by the computer and based on the sensor data, the autonomous vehicle to operate in accordance with a maneuver by sending instructions to one or more devices in the autonomous vehicle, wherein the maneuver is configured to bring the autonomous vehicle to a complete stop. In some embodiments, the maneuver may be selected from a plurality of maneuvers in response to determining an occurrence of a fault condition based on the sensor data.

A method detects presence of a multi-tone siren type in an acoustic signal. The multi-tone siren type is associated with one or more siren patterns, where each siren pattern includes a number of time patterns at corresponding frequencies. The method includes processing a number of frequency components of a frequency domain representation of the acoustic signal over time to determine a corresponding plurality of values. That processing includes determining, for each frequency component, a value characterizing a presence of a time pattern associated with at least one siren pattern. The method also includes processing the values according to the siren patterns to determine a detection result indicating whether the multi-tone siren type is present in the acoustic signal.

A method of processing data for a driving automation system, the method comprising steps of: obtaining image data from a camera of an autonomous vehicle, AV; image processing the image data to obtain a vehicle registration mark, VRM, of another vehicle within the surrounding area of the AV; looking up the VRM in a vehicle information database to obtain information indicative of the make, the model and the date of manufacture of the other vehicle; looking up information indicative of the make, the model and the date of manufacture of the other vehicle in a vehicle dimensions database to obtain at least one dimension of the other vehicle; and updating a context of the autonomous vehicle based on said at least one dimension of the other vehicle.

Enclosed are embodiments of motion control operations in various traffic scenarios in consideration of the kinematic factor for trajectory planning. In some embodiments, a method includes: determining a danger rating for at least one object identified in an environment, wherein the danger rating represents a perceived risk associated with a respective object; evaluating a set of hierarchical factors with respect to a traffic scenario, wherein a metric is derived for trajectories of the traffic scenario that quantifies passenger ride comfort based on the danger rating and the set of hierarchical factors; determining a motion control operation in the traffic scenario to increase the passenger ride comfort based on the metric; and augmenting a route planner of an autonomous vehicle with motion control operations in different traffic scenarios to increase the passenger ride comfort.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for planning the future trajectory of an autonomous vehicle in an environment. In one aspect, a method comprises obtaining multiple types of scene data characterizing a scene in an environment that includes an autonomous vehicle and multiple agents; receiving route data specifying an intended route for the autonomous vehicle; for each data type, processing at least the data type using a respective encoder network to generate a respective encoding of the data type; processing a sequence of the encodings using an encoder network to generate a respective alternative representation for each data type; and processing the alternative representations using a decoder network to generate a trajectory planning output that comprises respective scores for candidate trajectories that represent predicted likelihoods that the candidate trajectory is closest to resulting in the autonomous vehicle successfully navigating the intended route.