Abstract: A lane departure detection system detects that an autonomous driving vehicle (ADV) is departing from the lane in which the ADV is driving based on sensor data captured when the ADV contact a deceleration curb such as a speed bump laid across the lane. When the ADV contacts the deceleration curb, the lane departure detection system detects and calculates an angle of a moving direction of the ADV vs a longitudinal direction of the deceleration curb. Based on the angle, the system calculates how much the moving direction of the ADV is off compared to a lane direction of the lane. The lane direction is typically substantially perpendicular to the longitudinal direction of the deceleration curb. A control command such as a speed control command and/or a steering control command is generated based on the angle to correct the moving direction of the ADV.

Abstract: It is determined an ADV is inevitable to collide with at least one of the objects surrounding the ADV based on the relative positions and speeds between the ADV and the objects in view of the physical dimensions of the ADV. An object may be another vehicle, a pedestrian, a bicycle, a static obstacle. For each of the objects, a collision cost between the ADV and the object is calculated using a set of one or more cost functions or cost algorithms. A collision cost represents an amount of potential damage if the collision is to occur. One of the objects is selected whose collision cost is the least amongst the objects. A path or trajectory is planned for the ADV leading or towards to the selected object to minimize the potential damage when the ADV potentially collide with the selected object compared to the remaining objects.

Abstract: In one embodiment, an autonomous driving vehicle (ADV) speed following system determines how much and when to apply a throttle or a brake control of an ADV to maneuver the ADV around, or to avoid, obstacles of a planned route. The speed following system calculates a first torque force to accelerate the ADV, a second torque force to counteract frictional forces and wind resistances to maintain a reference speed, and a third torque force to minimize an initial difference and external disturbances thereafter between predefined target speed and actual speed of the ADV over a planned route. The speed following system determines a throttle-brake torque force based on the first, second, and third torque forces and utilizes the throttle-brake torque force to control a subsequent speed of the ADV.

Abstract: Described herein are systems and methods that allow for dense depth map estimation given input images. In one or more embodiments, a neural network model was developed that significantly differs from prior approaches. Embodiments of the deep neural network model comprises more computationally efficient structures and fewer layers but still produces good quality results. Also, in one or more embodiments, the deep neural network model may be specially configured and trained to operate using a hardware accelerator component or components that can speed computation and produce good results, even if lower precision bit representations are used during computation at the hardware accelerator component.

Abstract: In one embodiment, when an ADV is driving on a road segment, a driving parameter is recorded in response to a first control command. A difference between the first driving parameter and a target driving parameter corresponding to the first control command is determined. In response to determining that the difference exceeds a predetermined threshold, a second control command is issued to compensate the difference and cause the ADV to drive with a second driving parameter closer to the target driving parameter. A slope status of the road segment is derived based on at least the second control command. Map data of a map corresponding to the road segment of the road is updated based on the derived slope status. The updated map can be utilized to generate and issue proper control commands in view of the slope status of the road when the ADV drives on the same road subsequently.

Abstract: In one embodiment, autonomous driving control for an autonomous vehicle is provided by determining a first state of the autonomous vehicle from among a number of states and determining whether one or more conditions have been satisfied, based on current information and historical information of the autonomous vehicle. A next state of the autonomous vehicle and a transition of the autonomous vehicle from the first state to the next state are determined, based on the one or more conditions that are determined to have been satisfied. Based on the transition of the autonomous vehicle, one of a plurality of motion plans is selected.

Abstract: When an ADV is detected to transition from a manual driving mode to an autonomous driving mode, a first pedal value corresponding to a speed of the ADV at a previous command cycle during which the ADV was operating in the manual driving mode is determined. A second pedal value is determined based on a target speed of the ADV at a current command cycle during which the ADV is operating in an autonomous driving mode. A pedal value represents a pedal percentage of a maximum pedal pressure or maximum pedal pressed distance of a throttle pedal or brake pedal from a neutral position. A speed command is generated and issued to the ADV based on the first pedal value and the second pedal value, such that the ADV runs in a similar acceleration before and after switching from the manual driving mode to the autonomous driving mode.

Abstract: In one embodiment, a request is received to turn the autonomous driving vehicle (ADV) from a first direction to a second direction. In response to the request, a number of segment masses of a number of segments of the ADV are determined. The segment masses are located on a plurality of predetermined locations within a vehicle platform of the ADV. A location of a mass center for an entire ADV is calculated based on the segment masses of the segments of the ADV, where the mass center represents a center of an entire mass of the entire ADV. A steering control command based on the location of the mass center of the entire ADV for steering control of the ADV.

Abstract: In one embodiment, a lane departure detection system detects at a first point in time that a wheel of an ADV rolls onto a lane curb disposed on an edge of a lane in which the ADV is moving. The system detects at a second point in time that the wheel of the ADV rolls off the lane curb of the lane. The system calculates an angle between a moving direction of the ADV and a lane direction of the lane based on the time difference between the first point in time and the second point in time in view of a current speed of the ADV. The system then generates a control command based on the angle to adjust the moving direction of the ADV in order to prevent the ADV from further drifting off the lane direction of the lane.