Systems and methods for generating a virtual environment in a flock of vehicles are provided. In this method a reflector is utilized to define a coverage area. Sensory data from autonomous vehicles within this coverage area is collected, along with non-vehicle data. Then a virtual environment may be replicated using the data at a local computational device on each of the vehicles via the transmission of messages through the reflector. Each vehicle can use this data to make decisions regarding movements, as well as having the traffic patterns optimized based upon an objective. When traffic flow is being optimized it is also possible to assign weights to the vehicles to provide them preferential treatment in the traffic flow model. The traffic flow model that is generated may be a fluid dynamics model, or may be based upon deep learning techniques. The objective for the model is generally to maximize total vehicle throughput in order to reduce overall traffic congestion.

A driving assistance method is for an automated driving vehicle that is capable of switching between manual driving by a driver and automated driving, learns a driving characteristic of the driver during the manual driving, and reflects a learning result to a driving characteristic under control of the automated driving, and the driving assistance method includes: detecting a driving characteristic of an area in which the automated driving vehicle is traveling; and adjusting the learning result according to the detected driving characteristic of the area and executing the control of the automated driving based on the adjusted learning result.

Methods, systems, computer-readable media, and apparatuses for executing an event pertaining to a vehicle and a user of the vehicle are presented. In some embodiments, a includes (a) detecting that a motion state of the vehicle is in a first state, (b) detecting a condition that warrants a change in the motion state of the vehicle to a second state, and (c) detecting the user of the vehicle's engagement in an activity that potentially impairs the user from performing an action to change the motion state of the vehicle to the second state. The method also includes, detecting the condition, and (c) detecting the user of the vehicle's engagement in the activity, executing an event to facilitate the change in the motion state of the vehicle to the second state.

An automated speed control system includes a ranging-sensor, a camera, and a controller. The ranging-sensor detects a lead-speed of a lead-vehicle traveling ahead of a host-vehicle. The camera detects an object in a field-of-view. The controller is in communication with the ranging-sensor and the camera. The controller is operable to control the host-vehicle. The controller determines a change in the lead-speed based on the ranging-sensor. The controller reduces a host-speed of the host-vehicle when the lead-speed is decreasing, no object is detected by the camera, and while a portion of the field-of-view is obscured by the lead-vehicle.

A movable system includes a movable platform that includes a motorized drive to cause the movable platform to move in position, and a compartment located in an interior part of the movable platform; and an LIDAR system mounted to the movable platform including a probe fiber laser module located on the movable platform and producing pulsed probe laser light and scan the pulsed probe laser light out for optically sensing presence of one or more objects in the surrounding area based on detection of reflected probe laser light from the one or more objects. The probe fiber laser module includes a base laser module located inside the enclosure of the compartment and remote laser modules distributed at the platform instrument holding portions to scan the pulsed probe laser light out for optically sensing presence of one or more objects in the surrounding area.

A method for autonomously controlling a vehicle is disclosed. In some examples, a vehicle can maneuver out of a parking space in an autonomous and unmanned operation. While parking, the vehicle can capture first one or more images of its surroundings and store the images in a memory included in the vehicle. Upon starting up, the vehicle can capture second one or more images of its surroundings and compare them to the first one or more images to determine if there is an object, person, or animal proximate to the vehicle, for example. In some examples, in accordance with a determination that there is no object, person, or vehicle present that was not present during parking, the vehicle can autonomously move from the parking space with or without a user present in the vehicle.

A navigation system includes a processor programmed to receive, from a sensor, an output related to a motion of the host vehicle. The output is generated at a first time that is later than a data acquisition time, when a measurement or data acquisition on which the output is based is acquired, and earlier than a second time at which the sensor output is received processor; generate, for a motion prediction time, a prediction of at least one aspect of host vehicle motion based, on the output and how the aspect of host vehicle motion changes over a time interval between the data acquisition time and the motion prediction time; determine a navigational action for the host vehicle; generate a navigational command for implementing at least a portion of the navigational action; and provide the navigational command to at least one actuation system of the host vehicle.

The disclosure relates to smart signs or physical markers for facilitating passenger trips for autonomous vehicles. For instance, a physical marker remote from the autonomous vehicles may receive a first notification indicating a request for a trip has been made via a client computing device. The physical marker may determine when the client computing device has reached a physical marker, and in response to the determination, the physical marker may send a second notification to a dispatching server computing device indicating that the client computing device has reached a physical marker. Other aspects of the disclosure relate to various features and uses for the physical marker.

Among other things, a world model is maintained of an environment of a vehicle. A hypothetical object in the environment that cannot be perceived by sensors of the vehicle is included in the world model.

Data from sensors of a vehicle is captured along with data tracking a driver's gaze. The route traveled by the vehicle may also be captured. The driver's gaze is evaluated with respect to the sensor data to determine a feature the driver was focused on. A focus record is created for the feature. Focus records for many drivers may be aggregated to determine a frequency of observation of the feature. A machine learning model may be trained using the focus records to identify a region of interest for a given scenario in order to more quickly identify relevant hazards.