An automatic parking system is provided. The automatic parking system includes a camera processor that acquires images around a subject vehicle, converts the acquired images into external images and synthesizes the external images. A sensor processor measured spaced distances between the subject vehicle and surrounding vehicles. A parking space recognizing unit periodically receives the spaced distances and the external images and comparing the consecutive external images with the spaced distances using an image recognition technology to recognize parking areas. A controller calculates a moving path between a current position of the subject vehicle and an optimal parking area and operates the subject vehicle based on the moving path.

The technology relates to developing a highly accurate understanding of a vehicle's sensor fields of view in relation to the vehicle itself. A training phase is employed to gather sensor data in various situations and scenarios, and a modeling phase takes such information and identifies self-returns and other signals that should either be excluded from analysis during real-time driving or accounted for to avoid false positives. The result is a sensor field of view model for a particular vehicle, which can be extended to other similar makes and models of that vehicle. This approach enables a vehicle to determine when sensor data is of the vehicle or something else. As a result, the detailed modeling allowing the on-board computing system to make driving decisions and take other actions based on accurate sensor information.

The technology relates to developing a highly accurate understanding of a vehicle's sensor fields of view in relation to the vehicle itself. A training phase is employed to gather sensor data in various situations and scenarios, and a modeling phase takes such information and identifies self-returns and other signals that should either be excluded from analysis during real-time driving or accounted for to avoid false positives. The result is a sensor field of view model for a particular vehicle, which can be extended to other similar makes and models of that vehicle. This approach enables a vehicle to determine when sensor data is of the vehicle or something else. As a result, the detailed modeling allowing the on-board computing system to make driving decisions and take other actions based on accurate sensor information.

A target trajectory generation device generates and outputs target trajectories each including a target position and a target speed of a vehicle. A first target trajectory is intended to perform at least one of steering, acceleration, and deceleration of the vehicle. A second target trajectory is intended to decelerate and stop the vehicle. When a malfunctioning device does not exist, a vehicle traveling control device executes vehicle traveling control based on the first target trajectory. When the malfunctioning device exists, the vehicle traveling control device stops the vehicle by executing the vehicle traveling control based on the second target trajectory output before the malfunction occurs, or based on the second target trajectory output from the target trajectory generation device other than the malfunctioning device.

A machine is disclosed. The machine may include at least one of a propulsion system or a steering system configured to operate under automatic control in an autonomous mode of the machine; and a controller configured to obtain one or more parameters associated with a task that is to be performed in the autonomous mode, determine an estimated completion time for the task based on the one or more parameters associated with the task, and perform one or more actions based on the estimated completion time for the task.

A machine is disclosed. The machine may include at least one of a propulsion system or a steering system configured to operate under automatic control in an autonomous mode of the machine; and a controller configured to obtain one or more parameters associated with a task that is to be performed in the autonomous mode, determine an estimated completion time for the task based on the one or more parameters associated with the task, and perform one or more actions based on the estimated completion time for the task.

An embodiment device for controlling autonomous driving includes a roll angle estimated value calculation device configured to calculate a roll angle estimated value of a vehicle based on a height of a center of gravity of the vehicle, a sprung mass, a spring constant of a suspension, a target speed, and a target turning radius, and a controller configured to compare a roll angle of the vehicle with a preset reference roll angle to adjust the target speed or the target turning radius of the vehicle.

An embodiment device for controlling autonomous driving includes a roll angle estimated value calculation device configured to calculate a roll angle estimated value of a vehicle based on a height of a center of gravity of the vehicle, a sprung mass, a spring constant of a suspension, a target speed, and a target turning radius, and a controller configured to compare a roll angle of the vehicle with a preset reference roll angle to adjust the target speed or the target turning radius of the vehicle.

A method of generating an output trajectory of an ego vehicle includes recording trajectory data of the ego vehicle and pedestrian agents from a scene of a training environment of the ego vehicle. The method includes identifying at least one pedestrian agent from the pedestrian agents within the scene of the training environment of the ego vehicle causing a prediction-discrepancy by the ego vehicle greater than the pedestrian agents within the scene. The method includes updating parameters of a motion prediction model of the ego vehicle based on a magnitude of the prediction-discrepancy caused by the at least one pedestrian agent on the ego vehicle to form a trained, control-aware prediction objective model. The method includes selecting a vehicle control action of the ego vehicle in response to a predicted motion from the trained, control-aware prediction objective model regarding detected pedestrian agents within a traffic environment of the ego vehicle.

A method of generating an output trajectory of an ego vehicle includes recording trajectory data of the ego vehicle and pedestrian agents from a scene of a training environment of the ego vehicle. The method includes identifying at least one pedestrian agent from the pedestrian agents within the scene of the training environment of the ego vehicle causing a prediction-discrepancy by the ego vehicle greater than the pedestrian agents within the scene. The method includes updating parameters of a motion prediction model of the ego vehicle based on a magnitude of the prediction-discrepancy caused by the at least one pedestrian agent on the ego vehicle to form a trained, control-aware prediction objective model. The method includes selecting a vehicle control action of the ego vehicle in response to a predicted motion from the trained, control-aware prediction objective model regarding detected pedestrian agents within a traffic environment of the ego vehicle.