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: In one embodiment, a control command is generated with an MPC controller, the MPC controller including a cost function with weights associated with cost terms of the cost function. The control command is applied to a dynamic model of an autonomous driving vehicle (ADV) to simulate behavior of the ADV. One or more of the weights are based on evaluation of the dynamic model in response to the control command, resulting in an adjusted cost function of the MPC controller. Another control command is generated with the MPC controller having the adjusted cost function. This second control command can be used to effect movement of the ADV.

Abstract: In one embodiment, control of an autonomous driving vehicle (ADV) includes determining a current scenario of the ADV. Based on the scenario, a control algorithm is selected among a plurality of distinct control algorithms as the active control algorithm. One or more control commands are generated using the active control algorithm, based one or more target inputs. The control commands are applied to effect movement of the ADV.

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: In one embodiment, an ADV is routed by executing a first driving scenario that is active. The first driving scenario is one of a plurality of driving scenario types, each driving scenario type being associated with one or more stages to be executed while a corresponding driving scenario type is active. Based on an environmental condition around the ADV, a second driving scenario is set as active. The ADV is routed by executing the second driving scenario. When the second driving scenario exits, execution of the first driving scenario resumes at the one or more stages of the first driving scenario that remains to be executed.

Abstract: In one embodiment, a method determines a route from a first location of an autonomous driving vehicle (ADV) to a second location within an open space, the first location being a current location of the ADV. The method determines an objective function based on the route, the objective function having a set of costs for maneuvering the ADV from the first location to the second location. The method determines environmental conditions of the open space and uses the environmental conditions to determine a set of weights, each weight to be applied to a corresponding cost of the objective function. The method optimizes the objective function in view of one or more constraints, such that an output of the objective function reaches minimum while the one or more constraints are satisfied and generates a path trajectory with the optimized objective function to control the ADV autonomously according to the path trajectory.

Abstract: A learning based speed planner for autonomous driving vehicles (ADV) is disclosed. An ADV is set into human-driving mode. Driving control elements are under control of a human driver, and other ADV logic is enabled. The ADV plans a route path on a segment of the route having an obstacle. ADV logic generates a station-time graph for the path of the segment, and a grid of cells to encompass the path and obstacle. A feature vector is generated from the grid. Human driving behavior is recorded as the ADV is navigated along the path. Recorded driving data for a large plurality of paths, obstacles and ADVs is transmitted to a server to generate a speed model. The speed model is downloaded to one or more ADVs for use in autonomous driving mode, to determine an initial speed to use in similar driving situations.

Abstract: A system and method for predicting the near-term trajectory of a moving obstacle sensed by an autonomous driving vehicle (ADV) is disclosed. The method applies neural networks such as a LSTM model to learn dynamic features of the moving obstacle's motion based on its past trajectory up to its current position and a CNN model to learn the semantic map features of the driving environment in a portion of an image map. From the learned dynamic features of the moving obstacle and the learned semantic map features of the environment, the method applies a neural network to iteratively predict the moving obstacle's positions for successive time points of a prediction interval. To predict the moving obstacle's position at the next time point from the currently predicted position, the methods may update the learned dynamic features of the moving obstacle based on its past trajectory up to the currently predicted position.

Abstract: A parking system for autonomous driving vehicles optimizes a solution to a parking problem. The ADV detects a parking lot and selects a parking space. The ADV defines constraints for the parking lot, parking space, and kinematic constraints of the ADV, and generates a plurality of potential parking paths to the parking space, taking into account the constraints of the parking lot, parking space, and kinematics of the ADV, but without taking into any obstacles that may be surrounding the ADV. The ADV determines a cost for traversing each of the parking paths. One or more least cost candidate paths are selected from the parking paths, then one or more candidate paths are eliminated based on obstacles surrounding the ADV. Remaining candidates can be analyzed using a quadratic optimization system. A best parking path can be selected from the remaining candidates to navigate the ADV to the parking space.

Abstract: Described is a system for providing an autonomous driving control mechanism in response to a driving obstruction. The system includes a framework for providing a decision process that may learn from surrounding vehicles and traffic flow to determine a suitable responsive action. The system may observe other vehicles and determine a trajectory for the vehicle to follow. The system may rely on a specialized blocking detection and decision components that may provide a set of instructions or rules in order to maneuver around the obstruction. In addition, the system may compare the maneuver with a detour and determine the most suitable route for the vehicle based on an analysis of several factors. Accordingly, the system may continue to provide safe and efficient autonomous control even when encountering a driving obstruction.

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: A method of determining a smooth reference line for navigating an autonomous vehicle in a manner similar to human driving is disclosed. A high density map is used to generate a centerline for a lane of roadway. Using the centerline, a number of sample points is generated that is related to a curvature of the centerline. Adjustment points are generated at each sample point, a few on either side of the centerline at each sample point. Candidate points at a sample point include the adjustment points and sample point. A least cost path is determined through each of the candidate points at each of the sample points. Path cost is based an angle of approach and departure through a candidate point, and a distance of the candidate point from the centerline.

Abstract: A first reference line representing a route from a first location to a second location associated with an autonomous driving vehicle (ADV). In response to the first reference line multiple sets of sample points are generated based on the first reference line. Each set of sample points includes a first subset of sample points and a second subset of sample points that are offset from the first subset of sample points. A plurality of segments is generated between the multiple sets of sample points. A path for the ADV is generated based on the plurality of segments. The path includes one sample point from each of the multiple sets of sample points.

Abstract: Systems and methods are disclosed for identifying time-latency and subsystem control actuation dynamic delay due to second order dynamics that are neglected in control systems of the prior art. Embodiments identify time-latency and subsystem control actuation delays by developing a discrete-time dynamic model having parameters and estimating the parameters using a least-squares method over selected crowd-driving data. After estimating the model parameters, the model can be used to identify dynamic actuation delay metrics such as time-latency, rise time, settling time, overshoot, bandwidth, and resonant peak of the control subsystem. Control subsystems can include steering, braking, and throttling.

Abstract: Various techniques for theft proofing autonomous driving vehicles (ADV) for transporting goods are described. In one embodiment, sensor data of a moving object representing a person within a predetermined proximity of an ADV are captured for real-time analysis by a theft detection module, to determine a moving behavior of the moving object based on the sensor data in view of a set of known moving behaviors. The theft detection module further determines whether an intention of the person is likely to remove at least some of the goods from the ADV using a process derived from historical image set, and sends an alarm to a predetermined destination in response to determining such an intention of the person. Other sensor data, for example, real time movements and weights of the ADV, can be used in conjunction with the process derived from historical image sets to determine the intention of the person.

Abstract: In one embodiment, perception data is received from a number of autonomous driving vehicles (ADVs) over a network. The perception data includes information describing a set of trajectories that a number of vehicles having driven through a road segment of a road and perceived by one or more ADVs using their respective sensors driving on the same road segment. In response to the perception data, an analysis is performed on the perception data, i.e., the trajectories, to determine one or more lanes within the road segment. For each of the lanes, a lane reference line associated with the lane is calculated based on the trajectories within the corresponding lane. The lane metadata describing the lane reference lines for the one or more lanes are stored in a lane configuration data structure such as a database. The lane configuration database can then be utilized for autonomous driving at real-time subsequently without having to use a high definition map.

Abstract: A parking system for autonomous driving vehicles (ADV) is disclosed that utilizes the perception, planning, and prediction modules of ADV driving logic to more safely and accurately park an ADV. An ADV scans a parking lot for an available space, then determines a sequence of portions or segments of a parking path from the ADV's location to a selected parking space. The sequence of segments involves one or more forward driving segments and one or more reverse driving segments. During the forward driving segments, the ADV logic uses the perception, planning, and prediction modules to identify one or more obstacles to the ADV parking path, and speed and direction of those obstacles. During a reverse driving segment, the ADV logically inverts the orientation of the perception, planning, and prediction modules to continue to track the one or more obstacles and their direction and speed while the ADV is driving in a reverse direction.

Abstract: A driving environment is perceived based on sensor data obtained from a plurality of sensors mounted on the ADV. In response to a request for changing lane from a first lane to a second lane, path planning is performed. The path planning includes identifying a first lane change point for the ADV to change from the first lane to the second lane in a first trajectory of the ADV, determining a lane change preparation distance with respect to the first lane change point, and generating a second trajectory based on the lane change preparation distance, where the second trajectory having a second lane change point delayed from the first lane change point. Speed planning is performed on the second trajectory to control the ADV to change lane according to the second trajectory with different speeds at different point in time.

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: A sensor aggregation framework for autonomous driving vehicles is disclosed. In one embodiment, sensor data is 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 sensor data includes obstacle information of the obstacles and vehicle data of the ADV. Each of the vehicle data is timestamped with a current time at which the vehicle data is captured to generate a number of timestamps that correspond to the vehicle data. The obstacle information, the vehicle data, and the corresponding timestamps are aggregated into training data. The training data is used to train a set of parameters that is subsequently utilized to predict at least in part future obstacle behaviors and vehicle movement of the ADV.