A depth image of an object can be input to a deep neural network to determine a first four degree-of-freedom pose of the object. The first four degree-of-freedom pose and a three-dimensional model of the object can be input to a silhouette rendering program to determine a first two-dimensional silhouette of the object. A second two-dimensional silhouette of the object can be determined based on thresholding the depth image. A loss function can be determined based on comparing the first two-dimensional silhouette of the object to the second two-dimensional silhouette of the object. Deep neural network parameters can be optimized based on the loss function and the deep neural network can be output.

A lane change support device includes a control unit configured to execute lane change control for enabling a vehicle to automatically change lanes from a lane in which the vehicle is traveling to an adjacent lane. The control unit counts a holding time for which an operation part that is operated to a predetermined operation position to start the lane change control is continuously held at the operation position, starts the lane change control when the counted holding time reaches a predetermined threshold time, and calculates a proficiency level of a driver of the vehicle for an operation of the lane change support device during execution of the lane change control and sets the threshold time to be used for a successive lane change control based on the proficiency level.

An apparatus includes at least one camera configured to capture an image of a traffic lane in front of a vehicle. The apparatus also includes a path tracking controller configured to detect lane boundaries and a path curvature for the traffic lane from the image, determine a lateral offset of the vehicle from a reference path for the traffic lane and a heading offset for the vehicle from the path curvature, determine a yaw rate maintaining the vehicle within the traffic lane using a kinematics control, determine a steering angle maintaining the vehicle within the traffic lane using a dynamics control and the yaw rate determined by the kinematics control, and activate a steering control based on the determined steering angle.

An apparatus includes at least one camera configured to capture an image of a traffic lane in front of a vehicle. The apparatus also includes a path tracking controller configured to detect lane boundaries and a path curvature for the traffic lane from the image, determine a lateral offset of the vehicle from a reference path for the traffic lane and a heading offset for the vehicle from the path curvature, determine a yaw rate maintaining the vehicle within the traffic lane using a kinematics control, determine a steering angle maintaining the vehicle within the traffic lane using a dynamics control and the yaw rate determined by the kinematics control, and activate a steering control based on the determined steering angle.

Systems and methods of autonomously controlling a vehicle across the grip driving and drift driving operating ranges, are provided. The contemplated autonomous control can be effectuated using a closed-loop control system. In some embodiments, closed-loop control may be accomplished by deriving control laws involving sideslip angle, yaw rate, wheel speed, and other vehicle states. These control laws may be used to control the vehicle in a stable drift condition.

Systems and methods of autonomously controlling a vehicle across the grip driving and drift driving operating ranges, are provided. The contemplated autonomous control can be effectuated using a closed-loop control system. In some embodiments, closed-loop control may be accomplished by deriving control laws involving sideslip angle, yaw rate, wheel speed, and other vehicle states. These control laws may be used to control the vehicle in a stable drift condition.

Techniques are described to enable a vehicle, such as an autonomous vehicle, to steer and/or apply brakes on a road when a failure condition occurs. An example method for autonomous driving operation includes receiving a reduced set of location information that describes a location of the autonomous vehicle on a road; receiving a reduced set of trajectory information where the autonomous vehicle is expected to be driven; determining a driving path information where the autonomous vehicle is expected to be driven; and in response to determining an occurrence of a fault condition: sending a first instruction to cause the autonomous vehicle to steer the autonomous vehicle using at least the driving path information and the reduced set of location information, and sending a second instruction to cause the autonomous vehicle to apply brakes.

Techniques are described to enable a vehicle, such as an autonomous vehicle, to steer and/or apply brakes on a road when a failure condition occurs. An example method for autonomous driving operation includes receiving a reduced set of location information that describes a location of the autonomous vehicle on a road; receiving a reduced set of trajectory information where the autonomous vehicle is expected to be driven; determining a driving path information where the autonomous vehicle is expected to be driven; and in response to determining an occurrence of a fault condition: sending a first instruction to cause the autonomous vehicle to steer the autonomous vehicle using at least the driving path information and the reduced set of location information, and sending a second instruction to cause the autonomous vehicle to apply brakes.

A vehicle control device is provided for activating a safety device to inhibit occurrence of a collision with a moving object around an own vehicle, when the own vehicle transitions from traveling straight in a lane in which the vehicle is traveling to making a turn. An area setting unit is configured to, based on at least one of an own vehicle speed and a moving object speed, set a potential collision area, provided that the moving object continues to move in its moving direction and the own vehicle is making a right/left turn. An acquisition unit is configured to acquire a position of the moving object relative to the own vehicle. A restriction unit is configured to restrict activation of the safety device against the moving object based on the position of the moving object being out of the potential collision area.

A driving support apparatus includes a surrounding information acquisition device which acquires surrounding information, a steering information acquisition device which acquires steering information, a control unit which executes driving support control including at least one of pre-right/left-turn deceleration assist control or pre-right/left-turn warning control when a predetermined first execution condition is satisfied. When a precondition which is satisfied in a case in which an intersection is detected based on the surrounding information and steering operation is being performed by a driver based on the steering information is satisfied, the control unit determines whether or not the first execution condition is satisfied based on the steering operation being performed and traveling lane arrow information which is road arrow information of a traveling lane or adjacent lane arrow information which is road arrow information of an adjacent lane, both of which being stored in a storage device.