Abstract: In one embodiment, an autonomous driving system of an autonomous driving vehicle perceives a driving environment surrounding the autonomous driving vehicle traveling along a path, including perceiving an obstacle in the driving environment. The system detects a vertical acceleration of the autonomous driving vehicle based on sensor data obtained from a sensor on the autonomous driving vehicle. The system further calibrates the perceived obstacle based on the vertical acceleration of the autonomous driving vehicle. The system then controls the autonomous driving vehicle to navigate through the driving environment in view of the calibrated perceived obstacle.

Abstract: In one embodiment, a computer-implemented method for calibrating autonomous driving vehicles at a cloud-based server includes receiving, at the cloud-based server, one or more vehicle calibration requests from at least one user, each vehicle calibration request including calibration data for one or more vehicles and processing in parallel, by the cloud-based server, the one or more vehicle calibration requests for the at least one user to generate a calibration result for each vehicle. The method further includes sending, by the cloud-based server, the calibration result for each vehicle to the at least one user.

Abstract: In one embodiment, a system of an ADV perceives a driving environment surrounding the ADV using a plurality of sensors mounted on the ADV. The system identifies a blind spot based on the perceived driving environment surrounding the ADV. The system in response to identifying the blind spot, receives an image having the blind spot from an image capturing device disposed within a predetermined proximity of the blind spot. In some embodiments, the system receives the image having the blind spot from a remote server communicatively coupled to the image capturing device. The system identifies an obstacle of interest at the blind spot of the ADV based on the image. The system generates a trajectory based on the obstacle of interest at the blind spot to control the ADV to avoid the obstacle of interest.

Abstract: In one embodiment, a process is performed during controlling Autonomous Driving Vehicle (ADV). A plurality of point confidence scores are determined, each defining a reliability of a corresponding point on a trajectory of a moving obstacle. At least one of the point confidence scores is determined based on a) an overall trajectory confidence score, and b) at least one environmental factor of the obstacle. The ADV is controlled based on the trajectory of the moving obstacle and at least one of the plurality of point confidence scores.

Abstract: In one embodiment, a real time map can be generated by an autonomous driving vehicle (ADV) based on a navigation guideline for a lane and associated lane boundaries for the lane on a particular segment of a road. When travelling in the lane on the road segment, the ADV can use the navigation guideline as a reference line and use the lane boundaries as boundaries. The navigation guideline can be derived from manual driving path data collected by a manned vehicle that has travelled multiple times on the particular segment of the road.

Abstract: In one embodiment, one or more first data items associated with a planned trip of a user riding in an autonomous driving vehicle (ADV) are displayed on a display device within the ADV. Each of the first data items is associated with a user selectable option to indicate whether the user wishes or allows the ADV to store each of the first data items in a persistent storage device. User inputs are received via a user interface such as touch screen of the display device, including a first selection indicating that the user wishes to store a first subset of the first data items. In response to the first selection, the first subset of the data items is stored in the persistent storage device of the ADV.

Abstract: According to one embodiment, a first image identifier (ID) is received identifying a first of a first set of images, where the first image is currently displayed at a mobile device of a user. A number of additional images the user likely accesses from the first image in sequence is determined based on user interactions of a current browsing session and user interactions of a prior browsing session associated with the user. A second set of images are identified based on the number of additional images the user likely accesses. A sequential order is determined based on rankings of the images in the second set in view of a set of image selection rules. The second set of images is transmitted to the mobile device to be displayed on the mobile device in sequence one at a time.

Abstract: According to one embodiment, a driving environment surrounding an ADV is perceived based on sensor data obtained from various sensors mounted on the ADV including detecting one or more obstacles. The obstacles of the detected obstacles are determined and tracked based on the perception process, where the obstacle states of the obstacles may be maintained in an obstacle state buffer associated with the obstacles. When it is detected that a first moving obstacle is blocked by an object by the sensors, the further movement of the first moving obstacle is predicted based on the prior obstacle states of the first moving obstacle, while the first moving obstacle is blocked in view by the object. A trajectory is planned for the ADV in view of the predicted movement of the first moving obstacle while the first moving obstacle is in the blind area.

Abstract: According to one embodiment, during a first planning cycle, a first lane boundary of a driving environment perceived by an ADV is determined using a first lane boundary determination scheme (e.g., current lane boundary), which has been designated as a current lane boundary determination scheme. A first trajectory is planned based on the first lane boundary to drive the ADV to navigate through the driving environment. The first trajectory is evaluated against a predetermined set of safety rules (e.g., whether it will collide or get too close to an object) to avoid a collision with an object detected in the driving environment. In response to determining that the first trajectory fails to satisfy the safety rules, a second lane determination boundary of the driving environment is determined using a second lane boundary determination scheme and a second trajectory is planned based on the second lane boundary to drive the ADV.

Abstract: In one embodiment, a system sends current location information of the ADV to an alert service over a network, where the alert service is communicatively coupled to a number of ADVs. The system receives a broadcasted alert signal from the alert service, where the alert service has determined that the ADV is or will be located in an alert area, and the location of the alert area is determined based on a location of a dispatched vehicle having a higher priority of traveling. In response to receiving the broadcast alert signal, the system examines a current state and the current location of the ADV in view of the alert area to determine whether the ADV should overtake or yield the alert area based on a set of rules. The system generates a trajectory to control the ADV to navigate the alert area based on the examination.

Abstract: In one embodiment, a system uses an actor-critic reinforcement learning model to generate a trajectory for an autonomous driving vehicle (ADV) in an open space. The system perceives an environment surrounding an ADV. The system applies a RL algorithm to an initial state of a planning trajectory based on the perceived environment to determine a plurality of controls for the ADV to advance to a plurality of trajectory states based on map and vehicle control information for the ADV. The system determines a reward prediction by the RL algorithm for each of the plurality of controls in view of a target destination state. The system generates a first trajectory from the trajectory states by maximizing the reward predictions to control the ADV autonomously according to the first trajectory.

Abstract: In one embodiment, a system generates a plurality of driving scenarios to train a reinforcement learning (RL) agent and replays each of the driving scenarios to train the RL agent by: applying a RL algorithm to an initial state of a driving scenario to determine a number of control actions from a number of discretized control/action options for the ADV to advance to a number of trajectory states which are based on a number of discretized trajectory state options, determining a reward prediction by the RL algorithm for each of the controls/actions, determining a judgment score for the trajectory states, and updating the RL agent based on the judgment score.

Abstract: In one embodiment, an open space model is generated for a system to plan trajectories for an ADV in an open space. The system perceives an environment surrounding an ADV including one or more obstacles. The system determines a target function for the open space model based on constraints for the one or more obstacles and map information. The system iteratively, performs a first quadratic programming (QP) optimization on the target function based on a first trajectory while fixing a first set of variables, and performs a second QP optimization on the target function based on a result of the first QP optimization while fixing a second set of variables. The system generates a second trajectory based on results of the first and the second QP optimizations to control the ADV autonomously according to the second trajectory.

Abstract: In one embodiment, a method of training dynamic models for autonomous driving vehicles includes the operations of receiving a first set of training data from a training data source, the first set of training data representing driving statistics for a first set of features; training a dynamic model based on the first set of training data for the first set of features; determining a second set of features as a subset of the first set of features based on evaluating the dynamic model, each of the second set of features representing a feature whose performance score is below a predetermined threshold. The method further includes the following operations for each of the second set of features: retrieving a second set of training data associated with the corresponding feature of the second set of features, and retraining the dynamic model using the second set of training data.

Abstract: In one embodiment, a computer-implemented method of autonomously parking an autonomous driving vehicle, includes generating environment descriptor data describing a driving environment surrounding the autonomous driving vehicle (ADV), including identifying a parking space and one or more obstacles within a predetermined proximity of the ADV, generating a parking trajectory of the ADV based on the environment descriptor data to autonomously park the ADV into the parking space, including optimizing the parking trajectory in view of the one or more obstacles, segmenting the parking trajectory into one or more trajectory segments based on a vehicle state of the ADV, and controlling the ADV according to the one or more trajectory segments of the parking trajectory to autonomously park the ADV into the parking space without collision with the one or more obstacles.

Abstract: In one embodiment, a computer-implemented method of operating an autonomous driving vehicle (ADV) includes perceiving a driving environment surrounding the ADV based on sensor data obtained from one or more sensors mounted on the ADV, determining a driving scenario, in response to a driving decision based on the driving environment, applying a predetermined machine-learning model to data representing the driving environment and the driving scenario to generate a set of one or more driving parameters, and planning a trajectory to navigate the ADV using the set of the driving parameters according to the driving scenario through the driving environment.

Abstract: A new cost design is disclosed for evaluating candidate path curves for navigating an autonomous driving vehicle (ADV) through a segment of a route which may include an obstacle. Each point on each candidate path curve has a plurality of attributes having logical values and an associated priority of evaluation, and at least one numeric attribute having an associated priority of evaluation. A cost for each path curve is determined using the attributes and priorities, and a least cost path curve is selected using the attributes and priorities. By comparing attribute values in accordance with priority, and utilizing logical values, the efficiency of determining path curve cost and selecting a least cost path curve is substantially improved.

Abstract: An autonomous driving vehicle (ADV) receives instructions for a human test driver to drive the ADV in manual mode and to collect a specified amount of driving data for one or more specified driving categories. As the user drivers the ADV in manual mode, driving data corresponding to the one or more driving categories is logged. A user interface of the ADV displays the one or more driving categories that the human driver is instructed collect data upon, and a progress indicator for each of these categories as the human driving progresses. The driving data is uploaded to a server for machine learning. If the server machine learning achieves a threshold grading amount of the uploaded data to variables of a dynamic self-driving model, then the server generates an ADV self-driving model, and distributes the model to one or more ADVs that are navigated in the self-driving mode.

Abstract: According to some embodiments, a system operates an ADV. In one embodiment, the system perceives a driving environment surrounding the ADV based on sensor data obtained from a plurality of sensors, including perceiving a moving obstacle that is moving relative to the ADV. The system projects the moving obstacle as a figure onto a station-time (ST) coordinate system, wherein the ST coordinate system indicates a distance between the figure and a reference point at different points in time. And the system, for each of a plurality of predetermined processing time intervals, determines two points of the figure in the ST coordinate system to represent a shape of the figure, wherein the shape of the figure is utilized to plan a trajectory to drive the ADV to avoid colliding with the moving obstacle.

Abstract: In one embodiment, sensor data are collected from one or more sensors mounted on an autonomous driving vehicle (ADV) while the ADV is moving within a region of interest (ROI) that includes a number of obstacles. The collected sensor data are operated on to obtain obstacle data associated with the obstacles, location data, and a number of timestamps that correspond to the obstacle data and the location data. For each of the timestamps, positions of the obstacles are mapped to some of the obstacle data that correspond to the timestamp based on the location data, thereby generating mapped information of the obstacles. The mapped information is automatically labelled to generate labelled data, where the labelled data is utilized to subsequently train a machine learning algorithm to recognize obstacles during autonomous driving of an ADV.