Specifications are input, comprising: a plurality of lanes in an environment for a controlled system; a plurality of lane maneuvers associated with the plurality of lanes; a plurality of lane subconditions associated with the controlled system; and a rule set comprising a plurality of rules, wherein a rule in the rule set specifies a rule condition and a rule action to take when the rule condition is satisfied, wherein the rule condition comprises a corresponding set of lane subconditions, and wherein the rule action comprises a corresponding lane maneuver. The controlled system is automatically navigated dynamically, at least in part by: monitoring the plurality of lane subconditions; evaluating rule conditions associated with the plurality of rules in the rule set to determine one or more rules whose corresponding rule conditions has been met; and executing one or more lane maneuvers that correspond to the one or more determined rules.

Among other things, a vehicle having autonomous driving capabilities is operated in a mixed driving mode.

A computer-implemented method of evaluating the performance of a full or partial autonomous vehicle (AV) stack in simulation, the method comprising: applying an optimization algorithm to a numerical performance function defined over a scenario space, wherein the numerical performance function quantifies the extent of success or failure of the AV stack as a numerical score, and the optimization algorithm searches the scenario space for a driving scenario in which the extent of failure of the AV stack is substantially maximized, wherein the optimization algorithm evaluates multiple driving scenarios in the search space over multiple iterations, by running a simulation of each driving scenario in a simulator, in order to provide perception inputs to the AV stack, and thereby generate at least one simulated agent trace and a simulated ego trace reflecting autonomous decisions taken in the AV stack in response to the simulated perception inputs, wherein later iterations of the multiple iterations are guided by the results of previous iterations of the multiple iterations, with the objective of finding the driving scenario for which the extent of failure of the AV stack is maximized.

The present disclosure relates generally to autonomous vehicles, and more specifically to techniques for representing trajectories of objects such as traffic participants (e.g., vehicles, pedestrians, cyclists) in a computationally efficient manner (e.g., for multi-object tracking by autonomous vehicles). An exemplary method for generating a control signal for controlling a vehicle includes: obtaining a parametric representation of a trajectory of a single object in the same environment as the vehicle; updating the parametric representation of the single-object trajectory based on data received by one or more sensors of the vehicle within a framework of multi-object and multi-hypothesis tracker; and generating the control signal for controlling the vehicle based on the updated trajectory of the object.

A system for an autonomous vehicle that predicts a location-based maneuver of a remote vehicle located in a surrounding environment includes one or more vehicle sensors collecting sensory data indicative of one or more vehicles located in the surrounding environment. The system also includes one or more automated driving controllers in electronic communication with the one or more vehicle sensors. The one or more automated driving controllers execute instructions to compare a lane of travel of the remote vehicle with a current lane of travel of the autonomous vehicle. In response to determining the lane of travel of the remote vehicle is a different lane than the current lane of the autonomous vehicle, the one or more automated driving controllers predict the location-based maneuver of the remote vehicle based on aggregated vehicle metrics that are based on historical data collected at the specific geographical location.

Provided is a determination device capable of safely and reliably causing a vehicle on a side road to enter and merge into a main road when merging into the main road. Information is acquired that indicates the vehicle status of vehicles CA, etc., and vehicles Ca, etc., that are traveling on a side road SR that merges with a main road MR on which the vehicles CA, etc., are traveling. When, on the basis of said information, an intervehicular space is to be formed between the vehicles CA, etc., that will make it possible for a vehicle Ca, etc., to enter, the vehicles CA, etc., are caused to form an interval on the basis of the acceleration applied to each of the vehicles CA, etc., and the entering vehicle Ca, etc., is allowed to move to a position in the intervehicular space.

Disclosed are techniques for improving an advanced driver-assistance system (ADAS) using a secure channel area. In one embodiment, a method is disclosed comprising establishing a secure channel area extending from at least one side of a first vehicle; detecting a presence of a second vehicle in the secure channel area; establishing a secure connection with the second vehicle upon detecting the presence; exchanging messages between the first vehicle and the second vehicle, the messages including a position and speed of a sending vehicle; taking control of a position and speed of the first vehicle based on the contents of the messages; and releasing control of the position and speed of the first vehicle upon detecting that the secure connection was released.

An environmental information acquiring unit (11) to acquire environmental information on an environment around a mobile object, an action information acquiring unit (12) to acquire action information on an action of a driver of the mobile object, a calculation unit (13) to obtain control information for performing automated driving control of the mobile object on the basis of the environmental information acquired by the environmental information acquiring unit (11) and a machine learning model (18) that uses the environmental information as an input and outputs the control information, a contribution information determining unit (14) to determine contribution information having a high degree of contribution to the control information on the basis of the environmental information and the control information, a cognitive information calculating unit (15) to calculate cognitive information indicating a cognitive region of the driver in the environment around the mobile object on the basis of the action information and the environmental information, a specification unit (16) to specify unrecognized contribution information estimated not to be recognized by the driver on the basis of the contribution information and the cognitive information, and an information output control unit (17) to output driving assistance information necessary for driving assistance on the basis of the unrecognized contribution information specified by the specification unit (16) are provided.

A vehicle control device that autonomously controls a vehicle so as not to cause rapid deceleration that leads to a deterioration in ride quality. The vehicle control device controls first and second deceleration, means that reduce a speed at a deceleration rate large than a deceleration rate of the first deceleration means. The vehicle control device includes a blind spot area detecting unit that detects a blind spot area of a sensor that recognizes an external environment, and a blind spot object estimating unit that estimates a blind spot object that is a virtual moving body hidden in the blind spot area. When a vehicle approaches the blind spot area at a speed reduced by the first deceleration means, the vehicle is decelerated by the second deceleration means when a type of a moving body detected by the sensor is different from a type of the blind spot object.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for monitoring a dedicated roadway the runs in parallel to a railroad. In some implementations, a system includes a central server, an interface, and sensors. The interface receives data from a railroad system that manages the railroad parallel to the dedicated roadway. The sensors are positioned in a fixed location relative to the dedicated roadway. Each sensor can detect vehicles in a first field of view on the dedicated roadway. For each detected vehicle, each sensor can generate sensor data based on the detected vehicle in the dedicated roadway and the data received at the interface. Each sensor can generate observational data and instruct the detected vehicle to switch to an enhanced processing mode. Each sensor can determine an action for the detected vehicle to take based on the generated observational data.