Systems and methods for generating motion plans for autonomous vehicles are provided. An autonomous vehicle can include a machine-learned motion planning system including one or more machine-learned models configured to generate target trajectories for the autonomous vehicle. The model(s) include a behavioral planning stage configured to receive situational data based at least in part on the one or more outputs of the set of sensors and to generate behavioral planning data based at least in part on the situational data and a unified cost function. The model(s) includes a trajectory planning stage configured to receive the behavioral planning data from the behavioral planning stage and to generate target trajectory data for the autonomous vehicle based at least in part on the behavioral planning data and the unified cost function.

A device implementing a system for estimating device location includes at least one processor configured to receive a first and second set of signals, each set corresponding to location data and being received based on a sampling interval. The at least one processor is configured to, for each sampling period defined by the sampling interval, obtain sensor data corresponding to device motion during the sampling period, determine an orientation of the device relative to that of the vehicle based on the sensor data, calculate a non-holonomic constraint based on the orientation of the device relative to that of the vehicle such that the non-holonomic constraint is iteratively updated, and estimate a device state based on the non-holonomic constraint.

Methods and apparatus are provided for behavior planning for an autonomous vehicle. In one embodiment, a method includes: receiving navigation data including a navigation route; converting the navigation route to road segment data including a plurality of road segments; assigning lane attributes to the plurality road segments of the road segment data; computing cost data for each of the road segments; evaluating the cost data of each of the road segments to determine at least one driving behavior; and generating a display signal for displaying the driving behavior to a user of the autonomous vehicle.

A computer implemented method for determining optimal values for operational parameters for a model predictive controller for controlling a vehicle can receive from a data store or a graphical user interface, ranges for one or more operational parameters. The computer implemented method can determine optimum values for vehicle parameters of the vehicle of one or more other parameters by simulating a vehicle operation across the ranges of the one or more operational parameters by solving a vehicle control problem and determining an output of the vehicle control problem based on a result for the simulated vehicle operation. A vehicle can include a processing component configured to adjust a control input for an actuator of the vehicle according to a control algorithm and based on the optimum values of a parameter as determined by the computer implemented method.

Provided are autonomous vehicles and methods of controlling autonomous vehicles through topological planning with bounds, including receiving map data and sensor data, expanding a topological tree by adding a plurality of nodes to represent a plurality of actions associated with the plurality of constraints, generating a bound based on a constraint in the geographic area, the bound associated with an action for navigating the autonomous vehicle relative to the at least one constraint, storing the bound in a central bound storage, linking a set of bounds of a tree node to the bound via a bound identifier, wherein the first bound is initially linked as an active bound, or alternatively, as an inactive bound after determining it is not the most restrictive bound at any sample index, and control the autonomous vehicle based on the topological tree, to navigate the plurality of constraints.

A method for obtaining reference signals for vehicle control systems, in function of a vehicle geographical position along a travel route, includes providing data relating to the vehicle and data relating to a route to travel, and determining a vehicle driving force reference signal and a vehicle speed reference signal through a first optimisation process configured to optimise the driving force along the travel route. An engaged gear reference signal, in function of the positions of the vehicle along the travel route, is determined through a second optimisation process configured to optimise fuel consumption of the vehicle along the travel route. The second optimisation process is subsequent to the first optimisation process, and the data relating to the travel route, as well as the driving force reference signal and the speed reference signal, is received as input, determined through the first optimisation process.

An automotive electronic lateral dynamics control system of an autonomous motor vehicle, comprising a lateral driving path planner designed to plan a lateral driving path of the autonomous motor vehicle and defined by a reference curvature of the autonomous motor vehicle; an automotive electronic driving stability control system designed to control an automotive braking system to apply to the autonomous motor vehicle a yaw torque to hinder a driving instability condition of the autonomous motor vehicle; and an automotive electronic steering control system designed to control an automotive steering system to apply to the autonomous motor vehicle a steering angle or torque to cause the autonomous motor vehicle to follow the lateral driving path planned by the lateral driving path planner. The automotive electronic lateral dynamics control system is designed to cause an intervention of the automotive electronic steering control system to take account of an intervention of the automotive electronic driving stability control system.

A method for setting an anticipator module with which a control device controls the trajectory of a motor vehicle is equipped includes detecting whether the anticipator module is unsuitable during a turn by taking account of a lateral deviation with respect to an ideal trajectory and/or a contribution of a feedback module of the control device, determining primary parameters, calculating a secondary parameter by an optimization-based calculation method taking account of the determined primary parameters, and updating a bicycle model of the vehicle by taking account of the calculated secondary parameter.

A system and a method for controlling an autonomous driving vehicle. The system includes vehicle sensors and a controller. The controller has a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: receive vehicle parameters from the vehicle sensors; obtain a vehicle dynamic model by adding a dynamics error bound to a state space model, wherein the dynamics error bound is estimated using linear least square; minimize a linear quadratic regulator cost function based on the vehicle dynamic model; and control the vehicle using control input obtained from the minimized cost function.

A system for controlling a speed may include: a cognition device configured to provide sensing information by sensing an object at an outside of a host vehicle; a route setting device configured to receive map update information from the outside of the host vehicle to update a map, plan a driving route to a destination set by a driver, based on the map, and provide information on the planned driving route as driving route information; a real-time driving controller configured to generate real-time driving control information, based on the sensing information and driving route information for a preset position in front of the host vehicle, among the driving route information; and a vehicle control output interface configured to provide the real-time driving control information to an engine control system, a braking control system, and a steering control system.