A method includes identifying route data including a threshold arrival time for a route for an autonomous vehicle (AV) and calculating, based on the route data and a fuel-efficient speed value for each segment of the route, an estimated arrival time. Responsive to the estimated arrival time not meeting the threshold arrival time, the method includes identifying at least a subset of segments that each represent a candidate for speed increase, computing, for each segment in the subset and based on the fuel economy data, a correlation metric that indicates a correlation between a change in fuel economy and a change in speed for a corresponding segment in the subset, and increasing, for at least one segment from the subset and based on a respective correlation metric, a fuel-efficient speed value of the corresponding segment from the subset to provide a speed profile reflecting the increased fuel-efficient speed value.

An embodiment vehicle includes a collecting device for collecting environment information, a user input for automatic parking of the vehicle, an automatic parking controller for performing the automatic parking based on the environment information and the user input, and a behavior controller for controlling a behavior of the vehicle in response to control of the automatic parking controller. The automatic parking controller calculates a first progress corresponding to determination of whether the user input is a wake-up request, a second progress corresponding to acquisition of a control right for the behavior controller, a third progress corresponding to whether the user input is an execution request for the automatic parking, a fourth progress corresponding to generation of control information for the behavior controller, and a fifth progress corresponding to control of the vehicle's behavior.

Embodiments of the present disclosure disclose a method and apparatus for avoidance control of a vehicle, an electronic device, and a storage medium, where the method includes: obtaining behavior information of a moving obstacle, where the moving obstacle is located in a direction of movement of the vehicle and a distance between the moving obstacle and the vehicle satisfies a preset avoidance distance; determining an avoidance strategy for the vehicle based on the behavior information of the moving obstacle; and controlling movement of the vehicle based on the avoidance strategy. The method in the embodiments of the present disclosure considers the behavior information of the moving obstacle in the process of avoidance control of the vehicle, and the vehicle can be controlled to travel when the moving obstacle takes an avoidance action, thereby improving the accuracy of avoidance for the vehicle and the practicality of intelligent driving.

A method includes identifying route data including a threshold arrival time for a route for an autonomous vehicle (AV) and calculating, based on the route data and a fuel-efficient speed value for each segment of the route, an estimated arrival time. Responsive to the estimated arrival time not meeting the threshold arrival time, the method includes identifying at least a subset of segments that each represent a candidate for speed increase, computing, for each segment in the subset and based on the fuel economy data, a correlation metric that indicates a correlation between a change in fuel economy and a change in speed for a corresponding segment in the subset, and increasing, for at least one segment from the subset and based on a respective correlation metric, a fuel-efficient speed value of the corresponding segment from the subset to provide a speed profile reflecting the increased fuel-efficient speed value.

An autonomous vehicle driving system for autonomously controlling a vehicle. The system includes an environment detection system, a memory including an operational domain definition, and an electronic processor. The electronic processor is configured to detect a behavioral characteristic of a driver of the vehicle, the behavioral characteristic corresponding to a current driving scenario, determine, via the environment detection system, the current driving scenario in response to detecting the behavioral characteristic, and adjust the operational domain definition based on the determined current driving scenario.

The subject matter described in this specification is generally directed control architectures for an autonomous vehicle. In one example, a reference trajectory, a set of lateral constraints, and a set of speed constraints are received using a control circuit. The control circuit determines a set of steering commands based at least in part on the reference trajectory and the set of lateral constraints and a set of speed commands based at least in part on the set of speed constraints. The vehicle is navigated, using the control circuit, according to the set of steering commands and the set of speed commands.

An apparatus and method for controlling driving of a vehicle includes a camera configured to acquire an image in front of a vehicle, a sensor configured to acquire a driving speed of the vehicle, a first neural network configured to calculate a compensation steering angle based on comparing a driving steering angle with a calculated steering angle, and a second neural network configured to set a speed of the vehicle based on comparing the compensation steering angle with a threshold, wherein the driving steering angle comprises steering angle information collected while the vehicle is being driven and the calculated steering angle comprises steering angle information learned by receiving the image and the driving speed.

A vehicle control device includes a peripheral recognition unit configured to recognize a peripheral status of a vehicle including a position of a traffic participant present in a periphery of the vehicle on the basis of an output of an in-vehicle device, an estimation unit configured to estimate a peripheral attention ability of the traffic participant on the basis of an output of the in-vehicle device, and a risk area setting unit configured to set a risk area of the traffic participant on the basis of a result of the estimation performed by the estimation unit.

Performance anomalies in autonomous vehicle can be difficult to identify, and the impact of such anomalies on systems within the autonomous vehicle may be difficult to understand. In examples, systems of the autonomous vehicle are modeled as nodes in a probabilistic graphical network. Probabilities of data generated at each of the nodes is determined. The probabilities are used to determine capabilities associated with higher level functions of the autonomous vehicle.

A method for calculating running resistance of a vehicle includes: calculating, by a controller, an integrated value obtained by integrating a torque of a driving source of the vehicle before the vehicle reaches a reference speed after the vehicle starts; and calculating, by the controller, the running resistance of the vehicle including rolling resistance based on the integrated value of the torque of the driving source.