A system and a method for autonomous decisioning and operation by an autonomous agent includes: collecting decisioning data including: collecting a first stream of data includes observation data obtained by onboard sensors of the autonomous agent, wherein each of the onboard sensors is physically arranged on the autonomous agent; collecting a second stream of data includes observation data obtained by offboard infrastructure devices, the offboard infrastructure devices being arranged geographically remote from and in an operating environment of the autonomous agent; implementing a decisioning data buffer that includes the first stream of data from the onboard sensors and the second stream of data from the offboard sensors; generating current state data; generating/estimating intent data for each of one or more agents within the operating environment of the autonomous agent; identifying a plurality of candidate behavioral policies; and selecting and executing at least one of the plurality of candidate behavioral policies.

An adaptive cruise control system for a vehicle, includes: a stop location determination system configured to determine a stop location where the vehicle will have to stop because of a possible event occurring ahead of the vehicle on a road where the latter is moving; a cross traffic location determination system configured to determine whether the determined stop location is a location where cross traffic can occur, called cross traffic location; and an adaptive control system configured to adapt at least one driving control of the vehicle, based on the determination that the determined stop location is a cross traffic location.

A graphical ultrasonic module and driver assistance system are provided. The graphical ultrasonic module includes an ultrasonic sensor array and an ultrasonic transmitter array. The ultrasonic sensor array includes three or more ultrasonic sensors, and the ultrasonic sensors form a virtual plane. The ultrasonic transmitter array includes a plurality of ultrasonic transmitters. The geometric center of the ultrasonic transmitter array is substantially the same as the geometric center of the ultrasonic sensor array.

Systems and methods for managing environmental conditions for an autonomous vehicle are disclosed. In one aspect, an autonomous vehicle includes a perception sensor configured to generate perception data indicative of a condition of the environment, a network communication transceiver configured to communicate with an oversight system and an external weather condition source, a non-transitory computer readable medium, and a processor. The processor is configured to: receive the perception data from the at least one perception sensor, receive an indication of current weather conditions from the external weather condition source, determine a current environmental condition severity level from a plurality of severity levels based on the perception data and the indication of current weather conditions, modify one or more driving parameters that that govern a range of actions that can be autonomously executed by the autonomous vehicle, and navigate the autonomous vehicle based on the modified driving parameters.

A two-dimensional image segment that includes an outline of an object can be determined in a top-down fisheye image. A six degree of freedom (DoF) pose for the object can be determined based on determining a three-dimensional bounding box determined by one or more of (1) an axis of the two-dimensional image segment in a ground plane included in the top-down fisheye image and a three-dimensional model of the object and (2) inputting the two-dimensional image segment to a deep neural network trained to determine a three-dimensional bounding box for the object.

An apparatus and method for controlling an autonomous vehicle are provided. The apparatus includes a user input unit that receives identification information of a driver within the vehicle during autonomous driving and an information collection unit that acquires a global route of the vehicle and surrounding environment information. A controller determines a learning section on the global route based on the surrounding environment information and outputs a driving pattern of the driver by performing repetitive learning based on operation information of the driver in the learning section. Autonomous driving of the vehicle is then executed based on the output driving pattern of the driver.

Systems and methods are provided for vehicle navigation. In one implementation, a system may comprise an interface to obtain sensing data of an environment of the host vehicle. A processing device may be configured to determine a planned navigational action for the host vehicle; identify a target vehicle in the environment of the host vehicle; predict a following distance between the host vehicle and the target vehicle that would result if the planned navigational action was taken; determine a host vehicle braking distance based on a braking capability, acceleration capability, and speed of the host vehicle; determine a target vehicle braking distance, based on a speed and maximum braking capability of the target vehicle; and implement the planned navigational action when the predicted following distance is greater than a minimum safe longitudinal distance based on the determined host vehicle braking distance and the determined target vehicle braking distance.

A vehicle control device or method controls an output of a drive source of a vehicle based on a color of an illuminated signal of a traffic light in a vehicle-advancing direction during travel in autonomous driving. The vehicle control device includes a control unit that estimates the color of the currently illuminated signal of the traffic light based on oncoming vehicle information and controls the output of the drive source based on an estimation result when the color of the illuminated signal of the traffic light cannot be acquired by the onboard camera. The control unit limits the output of the drive source and reduces a vehicle speed from a current vehicle speed to a vehicle speed at which fuel efficiency is superior to that at the current vehicle speed when the color of the illuminated signal of the traffic light is estimated to be red.

An anticipating module for a device for controlling, in real time, the path of a motor vehicle includes a sub-module for computing a turning command for compensating for the curvature of a bend in the lane of the vehicle and a variable-gain device that is connected to an output of the computing sub-module. The gain of the variable-gain device is connected to a controller to adjust the gain so as to decrease the lateral offset between the centre of gravity of the vehicle and the centre of the lane of the vehicle depending on the result of the comparison of components of a vector of current measurements of state variables of the device to one another and to a detection threshold, the output of the variable-gain device being the steering command for compensating for the curvature of the bend.

An autonomous vehicle uses machine learning based models to predict hidden context attributes associated with traffic entities. The system uses the hidden context to predict behavior of people near a vehicle in a way that more closely resembles how human drivers would judge the behavior. The system determines an activation threshold value for a braking system of the autonomous vehicle based on the hidden context. The system modifies a world model based on the hidden context predicted by the machine learning based model. The autonomous vehicle is safely navigated, such that the vehicle stays at least a threshold distance away from traffic entities.