According to some embodiments, an ADV includes a method to plan a path trajectory. The method initializes a path length to a initial path length and performs a path planning operation using the initial path length. The method determines if the path planning operation successfully generates the path trajectory. If the path trajectory fails to be successfully generated, the method determines a reason for the failure. If the path trajectory fails to be generated for reasons other than an obstacle blocking the vehicle, the method defaults the path trajectory to a backup path. If the path trajectory fails to be generated due to an obstacle blocking the vehicle, the method reduces the path length by an incremental amount to generate a reduced path length. The method performs the path planning operation using the reduced path length until a path trajectory is successfully generated or until a stop condition is reached.

An apparatus for controlling a vehicle capable of performing autonomous driving is provided. The apparatus includes an autonomous driving device that executes the autonomous driving and generates a transition demand when it is impossible to execute the autonomous driving. A driving controller performs a minimum risk maneuver (MRM) of applying a deceleration pattern differently depending on a driving environment of the vehicle, when the transition demand is generated, but when driving manipulation by a driver does not occur. A subsequent safety ensuring function is performed according to the MRM for the driver to recognize the MRM, and a drive mode of the vehicle is changed to a drive mode with a rapid response speed to acceleration or steering.

A method for controlling braking of an autonomous vehicle includes: recognizing, by a driving situation recognizer, a vehicle stop situation based on environment information around the vehicle; generating, by a deceleration profile generator, a n.sup.th-order polynomial-based deceleration profile having a plurality of inflection points (n being a natural number equal to or greater than three) when the vehicle stop situation is recognized; correcting, by a corrector, the n.sup.th-order polynomial-based deceleration profile by setting at least one of a response time of a decelerator, a mass of the vehicle during driving or a deceleration performance of a brake to a control variable; and executing, by a controller, braking of the vehicle based on the corrected n.sup.th-order polynomial-based deceleration profile.

A computer implemented method for scenario generation for autonomous vehicle navigation that can include defining a cellular automaton layer that defines a road network level behavior with at least one rule directed to pathways by vehicles on a passageway for travel. The method may further include defining an active matter layer that defines a vehicle level behavior with at least one rule directed to movement of the vehicles on an ideal route for the pathways; and defining a driver agent layer that defines driving nature with at least one rule that impacts changes in the vehicle level behavior dependent upon a characterization of driver behavior. The method may further include combining outputs from the different layer to provide scenario generations for autonomous vehicle navigation. The combining of the outputs can utilize a pseudo random value to determine at an order in the execution and duration of execution for the layers.

In various examples, sensor data may be collected using one or more sensors of an ego-vehicle to generate a representation of an environment surrounding the ego-vehicle. The representation may include lanes of the roadway and object locations within the lanes. The representation of the environment may be provided as input to a longitudinal speed profile identifier, which may project a plurality of longitudinal speed profile candidates onto a target lane. Each of the plurality of longitudinal speed profiles candidates may be evaluated one or more times based on one or more sets of criteria. Using scores from the evaluation, a target gap and a particular longitudinal speed profile from the longitudinal speed profile candidates may be selected. Once the longitudinal speed profile for a target gap has been determined, the system may execute a lane change maneuver according to the longitudinal speed profile.

A vehicle travel control system for a vehicle may include: a braking profile generator to generate a brake pressure profile or a target speed profile based on monitored driving information of a host vehicle and a target vehicle; and a controller to control a speed or a deceleration of the host vehicle based on the generated profile. In particular, the braking profile generator analyzes an intention of a driver of the host vehicle when the driver intervenes at least one of the speed or deceleration of the host vehicle being controlled, and the braking profile generator further revises the target speed profile or brake pressure profile when the analyzed intention represents preferences of the driver such that the controller controls the host vehicle based on the revised profile.

Various embodiments of the invention enable an ADV to dynamically adjust its behaviors to emulate behaviors of a vehicle operated by a human driver when the ADV encounters an obstacle. A dynamic cost function can be used to collect real-time values of a set of parameters, and use the real-time values to constantly adjust a preferred safety distance where the ADV can be stopped ahead of the obstacle. An method includes determining a first distance to the obstacle in response to detecting an obstacle ahead of the ADV; and for each of a number of iterations, collecting a real-time value for each of a set of parameters, determining an offset to the first distance using the real-time value for each of the set of parameters, calculating a second distance based on the first distance and the offset, and controlling the ADV in view of the second distance using an expected value of each of the set of parameters, such that the ADV can stop at a point having the second distance to the obstacle.

A method of controlling autonomous driving of a vehicle includes: selecting a target object ahead of the vehicle based on driving information, generating a velocity profile for maintaining a desired distance to the target object, calculating a desired acceleration based on the velocity profile and a delay time of the vehicle, and controlling an actuator of the vehicle based on the desired acceleration.

An apparatus comprising an interface, a memory and a processor. The interface may be configured to receive sensor data samples during operation of a vehicle. The memory may be configured to store the sensor data samples over a number of points in time. The processor may be configured to analyze the sensor data samples stored in the memory to detect a pattern. The processor may be configured to manage an application of brakes of the vehicle in response to the pattern.

A forward information acquisition unit acquires a road profile ahead of the own vehicle. A position acquisition unit acquires a current position of the own vehicle. A state acquisition unit acquires a current speed of the own vehicle. A command calculation unit calculates a target speed at each point on a road ahead of the own vehicle, based on the road profile and the current position, and calculates a drive command for driving the own vehicle in the longitudinal direction of the own vehicle, based on the target speed and the current speed. The road profile includes a road gradient. The command calculation unit is configured to adjust the drive command, based on variation in the road gradient and Gzmax that is an acceleration limit limiting acceleration of the own vehicle in the vertical direction.