Automatic steering control is essential part for autonomous vehicle which controls the steering in various scenarios to achieve safe and comfortable driving. The present subject matter discloses a system and method for steering control during autonomous vehicle driving using neural networks. In an embodiment, a lane side offset, a radius of curvature and a speed of a vehicle are received. Further, an ideal steering angle required to keep the vehicle at a center of a lane is determined using the radius of curvature. Furthermore, an offset error is determined based on the lane side offset using a reference offset. In addition, a corrective steering angle is determined using the radius of curvature, speed of the vehicle and offset error. Also, a steering angle required to keep the vehicle at a center of a lane is computed using the ideal steering angle and the corrective steering angle.

A traveling control apparatus of vehicle includes a lane change controller, a position detector, and a lane detector. The lane change controller includes first and second course generators that respectively generate first and second courses as target courses of a vehicle in first and second lanes. The first and the second course generators respectively calculate first and second target movement amounts, in width directions of the first and the second lanes, of the vehicle when the vehicle is moved along the first and the second courses, and respectively generate the first and the second courses on a basis of the first and the second target movement amounts and first and second jerks. The first and the second jerks are each a rate of change of acceleration of the vehicle in the width direction of the first lane in the first course or the second lane in the second course.

Provided is an anti-collision control device of a vehicle, and a method therefore. Particularly, provided is a method and apparatus for avoiding a collision by previously sensing a risk of collision with a neighboring vehicle when a vehicle is located in a blind spot of the neighboring vehicle.

A lane information detection unit detects the shape and the road width of a traveling lane of a vehicle. A present transverse position detection unit detects a present transverse position indicating a present traveling position of the vehicle in the width direction of the traveling lane. A driver-corresponding transverse position setting unit sets a driver-corresponding transverse position corresponding to a driving tendency of a driver. An upper/lower limit value setting unit sets upper/lower limit values that the driver-corresponding transverse position can take, in accordance with the road width. Then, when change in the road width is detected, a transverse position control amount calculation unit sets, as a target transverse position, the driver-corresponding transverse position within the upper/lower limit values in which the change is reflected, and calculates a transverse position control amount for the vehicle from the present transverse position of the vehicle.

Systems and methods for controlling a vehicle are provided. The systems and methods provide a vehicle dynamics model that relates at least one input vehicle dynamics variable to at least one output vehicle dynamics variable. The systems and methods detect a crosswind impacting the vehicle by detecting a disturbance associated with the vehicle dynamics model caused by the crosswind and adapt control of the vehicle based on the detecting the crosswind impacting the vehicle.

A collision avoidance apparatus includes an object information acquisition device for acquiring object information including a three-dimensional object and dividing lines, a steering input value acquisition device for acquiring a steering input value based on a driver's steering operation, and control unit for executing collision avoidance control when a collision condition is satisfied based on the object information. When the steering input value of a steering operation to the right is defined to be positive, the control unit is configured to perform one of: avoiding executing the collision avoidance control even when the collision condition is satisfied; and changing a threshold value used for the collision condition so that satisfaction of this condition becomes more difficult, in a case where a right side adjacent lane is present, this lane is a lane in the same direction, and the steering input value is a predetermined positive steering threshold value or more.

A computer-implemented method comprises: initiating, by an assisted-driving system that is controlling motion of a vehicle, a lane change of the vehicle from an ego lane to a target lane, the lane change to be performed based only on local information of the vehicle; defining, by the assisted-driving system, a parametric representation of the target lane, the parametric representation based on first waypoints of the target lane; receiving, by the assisted-driving system and during the lane change, a first output of a perception component of the vehicle, the first output being the local information and reflecting second waypoints of the target lane; performing, by the assisted-driving system, a comparison based on the first output and the parametric representation; and providing, by the assisted-driving system, references of a first global path to controllers of the vehicle for actuating the lane change, the references selected based on the comparison.

A path generation device and a vehicle control system capable of inhibiting generation of paths that make a vehicle unstable are provided. The path generation device includes a path generator that generates a plurality of paths along which a vehicle is to travel, in association with each piece of environment measurement data about a travel environment of the vehicle detected by a plurality of detectors; a reliability setting part that sets, for each of the generated paths, the reliability of the path in itself, the reliability corresponding to the degree to which a variation in the path falls within a predetermined range, and a path-weight setting part that sets the weight of each path on the basis of the reliability of the path.

A work machine stability monitoring system may include an environmental sensor configured to capture environmental information about the ground around a work machine, a machine operating sensor configured to capture operation information of the work machine, and a stability analyzer. The stability analyzer may be configured receiving the environmental information and the operation information, prospectively identifying zones with stability issues based on the environmental information, and identifying active stability conditions of the work machine based on the operation information.

Methods and systems are provided for operating a vehicle in a mode to free the vehicle from being stuck in sand are presented. In one example, a speed of an electric machine is adjusted to determine when wheel jitter occurs. The electric machine speed may be maintained at a speed where wheel jitter occurs while the vehicle is stuck.