Abstract: Systems, methods, and media for factoring localization uncertainty of an ADV into its planning and control process to increase the safety of the ADV. The uncertainty of the localization can be caused by sensor inaccuracy, map matching algorithm inaccuracy, and/or speed uncertainty. The localization uncertainty can have negative impact on trajectory planning and vehicle control. Embodiments described herein are intended to increase the safety of the ADV by considering localization uncertainty in trajectory planning and vehicle control. An exemplary method includes determining a confidence region for an ADV that is automatically driving on a road segment based on localization uncertainty and speed uncertainty; determining that an object is within the confidence region, and a probability of collision with the ADV based on a distance of the object to the ADV; and planning a trajectory based on the probability of collision, and controlling the ADV based on the probability of collision.

Abstract: Embodiments of the invention are intended to evaluate the performance of a planning module of the ADV in terms of decision consistency in addition to other metrics, such as comfort, latency, controllability, and safety. In one embodiment, an exemplary method includes receiving, at an autonomous driving simulation platform, a record file recorded by the ADV that was automatically driving on a road segment; simulating operations of a dynamic model of the ADV in the autonomous driving simulation platform during one or more driving scenarios on the road segment based on the record file. The method further includes performing a comparison between each planned trajectory generated by a planning module of the dynamic model after an initial period of time with each trajectory stored in a buffer; and modifying a performance score generated by a planning performance profiler in the autonomous driving simulation platform based on a result of the comparison.

Abstract: In one embodiment, an exemplary method includes receiving, at a simulation platform, a record file recorded by a manually-driving ADV on a road segment, the simulation platform including a first encoder, a second encoder, and a performance evaluator; simulating automatic driving operations of a dynamic model of the ADV on the road segment based on the record file, the dynamic model including an autonomous driving module to be evaluated. The method further includes: for each trajectory generated by the autonomous driving module during the simulation: extracting a corresponding trajectory associated with the manually-driving ADV from the record file, encoding the trajectory into a first semantic map and the corresponding trajectory into a second semantic map, and generating a similarity score based on the first semantic map and the second semantic map. The method also includes generating an overall performance score based on each similarity score.

Abstract: In one embodiment, method performed by an autonomous driving vehicle (ADV) that determines, within a driving space, a plurality of routes from a current location of the ADV to a desired location. The method determines, for each route of the plurality of routes, an objective function to control the ADV autonomously along the route and, for each of the objective functions, performs Differential Dynamic Programming (DDP) optimization in view of a set of constraints to produce a path trajectory. The method determines whether at least one of the path trajectories satisfies each constraint and, in response to a path trajectory satisfying each of the constraints, selects the path trajectory for navigating the ADV from the current location to the desired location.

Abstract: In one embodiment, when an autonomous driving vehicle (ADV) is parked, the ADV can determine, based on criteria, whether to operate in an open-space mode or an on-lane mode. The criteria can include whether the ADV is within a threshold distance and threshold heading relative to a vehicle lane. If the criteria are not satisfied, then the ADV can enter the open-space mode. While in the open-space mode, the ADV can maneuver it is within the threshold distance and the threshold heading relative to the vehicle lane. In response to the criteria being satisfied, the ADV can enter and operate in the on-lane mode for the ADV to resume along the vehicle lane.

Abstract: In one embodiment, a plurality of obstacles is sensed in an environment of an automated driving vehicle (ADV). One or more representations are formed to represent corresponding groupings of the plurality of obstacles. A vehicle route is determined in view of the one or more representations, rather than each and every one of the obstacles individually.

Abstract: According to one embodiment, when a predicted trajectory is received, a set of one or more features are extracted from at least some of the trajectory points of the predicted trajectory. The predicted trajectory is predicted using a prediction method or algorithm based on perception data perceiving an object within a driving environment surrounding an autonomous driving vehicle (ADV). The extracted features are fed into a predetermined DNN model to generate a similarity score. The similarity score represents a difference or similarity between the predicted trajectory and a prior actual trajectory that was used to train the DNN model. The similarity score can be utilized to evaluate the prediction method that predicted the predicted trajectory.

Abstract: In one embodiment, static-state curvature error compensation control logic for autonomous driving vehicles (ADV) receives planning and control data associated with the ADV, including a planned steering angle and a planned speed. A steering command is generated based on a current steering angle and the planned steering angle of the ADV. A throttle command is generated based on the planned speed in view of a current speed of the ADV. A curvature error is calculated based on a difference between the current steering angle and the planned steering angle. The steering command is issued to the ADV while withholding the throttle command, in response to determining that the curvature error is greater than a predetermined curvature threshold, such that the steering angle of the ADV is adjusted in view of the planned steering angle without acceleration.

Abstract: Systems and methods are disclosed for collecting driving data from simulated autonomous driving vehicle (ADV) driving sessions and real-world ADV driving sessions. The driving data is processed to exclude manual (human) driving data and to exclude data corresponding to the ADV being stationary (not driving). Data can further be filtered based on driving direction: forward or reverse driving. Driving data records are time stamped. The driving data can be aligned according to the timestamp, then a standardized set of metrics is generated from the collected, filtered, and time-aligned data. The standardized set of metrics are used to grade the performance the control system of the ADV, and to generate an updated ADV controller, based on the standardized set of metrics.

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: Systems and methods are disclosed for reducing second order dynamics delays in a control subsystem (e.g. throttle, braking, or steering) in an autonomous driving vehicle (ADV). A control input is received from an ADV perception and planning system. The control input is translated in a control command to a control subsystem of the ADV. A reference actuation output is obtained from a storage of the ADV. The reference actuation output is a smoothed output that accounts for second order actuation dynamic delays attributable to the control subsystem actuator. Based on a difference between the control input and the reference actuation output, adaptive gains are determined and applied to the input control signal to reduce error between the control output and the reference actuation output.

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 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, simulation of an autonomous driving vehicle (ADV) includes capturing first data that includes a control command output by an autonomous vehicle controller of the ADV, and capturing second data that includes the control command being implemented at a control unit of the ADV. The control command, for example, a steering command, a braking command, or a throttle command, is implemented by the ADV to affect movement of the ADV. A latency model is determined based on comparing the first data with the second data, where the latency model defines time delay and/or amplitude difference between the first data and the second data. The latency model is applied in a virtual driving environment.

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: Systems and methods are disclosed for reducing second order dynamics delays in a control subsystem (e.g. throttle, braking, or steering) in an autonomous driving vehicle (ADV) and increasing control system bandwidth by accounting for time-latency in a control subsystem actuation system. A control input is received from an ADV's autonomous driving system. The control input is translated into a control command of the control subsystem of the ADV. A reference actuation output and a predicted actuation output are generated corresponding to a by-wire (“real”) actuation action for the control subsystem. A control error is determined between the reference actuation action and the by-wire actuation action. A predicted control error is determined between the predicted actuation action and the between the by-wire actuation action. Adaptive gains are determined and applied to the by-wire actuation action to generate a second by-wire actuation action.

Abstract: Systems and methods for sound source detection and localization utilizing an autonomous driving vehicle (ADV) are disclosed. The method includes receiving audio data from a number of audio sensors mounted on the ADV. The audio data comprises sounds captured by the audio sensors and emitted by one or more sound sources. Based on the received audio data, the method further includes determining a number of sound source information. Each sound source information comprises a confidence score associated with an existence of a specific sound. The method further includes generating a data representation to report whether there exists the specific sound within the driving environment of the ADV. The data representation comprises the determined sound source information. The received audio data and the generated data representation are utilized to subsequently train a machine learning algorithm to recognize the specific sound source during autonomous driving of the ADV in real-time.

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: A surrounding environment of an autonomous vehicle is perceived to identify one or more vehicles nearby. For each of the identified vehicles, based on a current location of the identified vehicle, vehicle-independent information is obtained to determine context surrounding the identified vehicle, where the vehicle-independent information includes vehicle surrounding information that defines physical constraints imposed on the identified vehicle. For each of the identified vehicles, one or more trajectories for the identified vehicle are predicted based at least in part on the vehicle-independent information associated with the identified vehicle. The autonomous vehicle is controlled based on the one or more predicted trajectories of the one or more identified vehicles.

Abstract: Disclosed are performance metrics for evaluating the accuracy of a dynamic model in predicting the trajectory of ADV when simulating the behavior of the ADV under the control commands. The performance metrics may indicate the degree of similarity between the predicted trajectory of the dynamic model and the actual trajectory of the vehicle when applied with identical control commands. The performance metrics measure deviations of the predicted trajectory of the dynamic model from the actual trajectory based on the ground truths. The performance metrics may include cumulative or mean absolute trajectory error, end-pose difference (ED), two-sigma defect rate (?2?), the Hausdirff Distance (HAU), the longest common sub-sequence error (LCSS), or dynamic time warping (DTW). The two-sigma defect rate represents the ratio of the number of points with true location error falling out of the 2? range of the predicted location error over the total number of points in the trajectory.