Abstract: Techniques are disclosed for evaluating an autonomous vehicle (“AV”) control system by determining deviations between data generated using the AV control system and manual driving data. In many implementations, manual driving data captures action(s) of a vehicle controlled by a manual driver. Additionally or alternatively, multiple AV control systems can be evaluated by comparing deviations for each AV control system, where the deviations are determined using the same set of manual driving data.

Abstract: In one embodiment, a lateral drifting error is determined based on at least a current location of an ADV. The lateral drifting error is segmented into a first drifting error and a second drifting error using a predetermined segmentation algorithm. A planning module plans a path or trajectory for a current driving cycle (e.g., planning cycle) to drive the ADV from the current location for a predetermined period of time. The planning module performs a first drifting error correction on the trajectory by modifying at least a starting point of the trajectory based on the first drifting error to generate a modified trajectory. A control module controls the ADV to drive according to the modified trajectory, including performing a second drifting error correction based on the second drifting error.

Abstract: Via a first processing thread, an ADV is controlled according to a first trajectory that was generated based on a first reference line starting at a first location. Concurrently via a second processing thread, a second reference line is generated based on a second location of the first trajectory that the ADV will likely reach within a predetermined period of time in future. The predetermined period of time is greater than or equals to an amount of time to generate a reference line for the ADV. The second reference line is generated while the ADV is moving according to the first trajectory and before reaching the second location. Subsequently, in response to determining that the ADV is within a predetermined proximity of the second location, a second trajectory is generated based on the second reference line without having to calculate the second reference line at the second location.

Abstract: In one embodiment, instead of using map data, a relative coordinate system is utilized to assist perception of the driving environment surrounding an ADV for some driving situations. One of such driving situations is driving on a highway. Typically, a highway has fewer intersections and exits. The relative coordinate system is utilized based on the relative lane configuration and relative obstacle information to control the ADV to simply follow the lane and avoid potential collision with any obstacles discovered within the road, without having to use map data. Once the relative lane configuration and obstacle information have been determined, regular path and speed planning and optimization can be performed to generate a trajectory to drive the ADV. Such a perception system is referred to as a relative perception system based on a relative coordinate system.

Abstract: According to an embodiment, a system generates a number of sample trajectories from a trajectory sample space for a driving scenario. The system determines a reward based on a reward model for each of the sample trajectories, where the reward model is generated using a rank based conditional inverse reinforcement learning algorithm. The system ranks the sample trajectories based on the determined rewards. The system determines a highest ranked trajectory based on the ranking. The system selects the highest ranked trajectory to control the ADV autonomously according to the highest ranked trajectory.

Abstract: In one embodiment, a lateral drifting error is determined based on at least a current location of an ADV. The lateral drifting error is segmented into a first drifting error and a second drifting error using a predetermined segmentation algorithm. A planning module plans a path or trajectory for a current driving cycle (e.g., planning cycle) to drive the ADV from the current location for a predetermined period of time. The planning module performs a first drifting error correction on the trajectory by modifying at least a starting point of the trajectory based on the first drifting error to generate a modified trajectory. A control module controls the ADV to drive according to the modified trajectory, including performing a second drifting error correction based on the second drifting error.

Abstract: A first localization system performs a first localization using a first set of sensors to track locations of the ADV along the path from a starting point to a destination point. A first localization curve is generated as a result representing the locations of the ADV along the path tracked by the first localization system. Currently, a second localization system performs a second localization using a second set of sensors to track the locations of the ADV along the path. A second localization curve is generated as a result representing the locations of the ADV along the path tracked by the second localization system. A system delay of the second localization system is determined by comparing the second localization curve against the first localization curve as a localization reference. The system delay of the second localization system can then be utilized to compensate path planning of the ADV subsequently.

Abstract: In one embodiment, instead of using map data, a relative coordinate system is utilized to assist perception of the driving environment surrounding an ADV for some driving situations. One of such driving situations is driving on a highway. Typically, a highway has fewer intersections and exits. The relative coordinate system is utilized based on the relative lane configuration and relative obstacle information to control the ADV to simply follow the lane and avoid potential collision with any obstacles discovered within the road, without having to use map data. Once the relative lane configuration and obstacle information have been determined, regular path and speed planning and optimization can be performed to generate a trajectory to drive the ADV. Such a perception system is referred to as a relative perception system based on a relative coordinate system.

Abstract: According to one embodiment, an ADV is controlled according to a first trajectory planned during a first planning cycle. A control error is determined which represents a drifting error at a first location of the ADV at a first point in time at the end of the first planning cycle. A second point in time is selected on the first trajectory. A second trajectory is generated from a second location on the first trajectory corresponding o the second point in time as a starting location of the second trajectory for a second planning cycle as a next planning cycle. A segment of the first trajectory between the first point in time and the second point in time is combined with the second trajectory to generate a third trajectory for the second planning cycle. The ADV is driven and controlled according to the third trajectory corresponding to the second planning cycle.

Abstract: In one embodiment, a data processing system for an autonomous driving vehicle (ADV) includes a processor, and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations. The operations include generating a station-time (ST) graph based on perception data obtained from one or more sensors of the ADV, the ST graph including representing a location of an obstacle at different points in time, obtaining a tensor based on the ST graph, the tensor including a plurality of layers, the plurality of layers including a first layer having data representing one or more obstacles on a path in which the ADV is moving, applying a machine-learning model to the plurality of layers of the tensor to generate a plurality of numerical values, the plurality of numerical values defining a potential path trajectory of the ADV, and determining a path trajectory of the ADV based on the plurality of numerical values.

Abstract: In one embodiment, in response to a route from a source location to a target location, the route is analyzed to identify a list of one or more driving scenarios along the route that match one or more predetermined driving scenarios. The route is segmented into a list of route segments based on the driving scenarios. At least one of the route segments corresponds to one of the identified driving scenarios. A path is generated based on the route segments for driving an autonomous driving vehicle from the source location to the target location. The path includes a number of path segments corresponding to the route segments. At least one of the path segments of the path is determined based on a preconfigured path segment of a predetermined driving scenario associated with the path segment, without having to calculating the same at real time.

Abstract: A station-time (S-T) graph may be obtained in response to a first reference line representing a path from a first location to a second location associated with an autonomous driving vehicle (ADV). One or more kernels may be applied to the S-T graph. Each of the one or more kernels may indicate a plurality of points on the S-T graph. One or more constraints may be applied to the S-T graph. Each of the one or more constraints may indicate a condition for points in the S-T graph. A set of speeds for portions of the path is determined based on the one or more kernels and the one or more constraints.

Abstract: According to some embodiments, a system calculates a first trajectory based on a map and a route information. The system generates a path profile based on the first trajectory, traffic rules, and an obstacle information describing one or more obstacles perceived by the ADV. The system generates a speed profile based on the path profile, where the speed profile includes, for each of the obstacles, a decision to yield or overtake the obstacle. The system performs a quadratic programming optimization on the path profile and the speed profile to identify an optimal path with optimal speeds. The system generates a second trajectory based on the optimal path and optimal speeds to control the ADV autonomously according to the second trajectory.

Abstract: In one embodiment, when an ADV is driving on a trajectory generated based on a reference line, a separate processing thread is executed to precalculate a new reference line as a future reference line for a future planning cycle in parallel. The future reference line is being created while the ADV is moving along a trajectory generated based on the original reference line and before reaching a location corresponding to the starting point of the future reference line. The future reference line is overlapped with an end section of the original reference line, such that the future reference line can be connected to the end section of the original reference line. The future reference line serves an extension of the original reference line before the ADV reaches the end section of the original reference line.

Abstract: In one embodiment, a data processing system for an autonomous driving vehicle (ADV) includes a processor, and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations. The operations include generating a station-time (ST) graph based on perception data obtained from one or more sensors of the ADV, the ST graph including representing a location of an obstacle at different points in time, obtaining a tensor based on the ST graph, the tensor including a plurality of layers, the plurality of layers including a first layer having data representing one or more obstacles on a path in which the ADV is moving, applying a machine-learning model to the plurality of layers of the tensor to generate a plurality of numerical values, the plurality of numerical values defining a potential path trajectory of the ADV, and determining a path trajectory of the ADV based on the plurality of numerical values.

Abstract: According to an embodiment, a system generates a number of sample trajectories from a trajectory sample space for a driving scenario. The system determines a reward based on a reward model for each of the sample trajectories, where the reward model is generated using a rank based conditional inverse reinforcement learning algorithm. The system ranks the sample trajectories based on the determined rewards. The system determines a highest ranked trajectory based on the ranking. The system selects the highest ranked trajectory to control the ADV autonomously according to the highest ranked trajectory.

Abstract: A first localization system performs a first localization using a first set of sensors to track locations of the ADV along the path from a starting point to a destination point. A first localization curve is generated as a result representing the locations of the ADV along the path tracked by the first localization system. Currently, a second localization system performs a second localization using a second set of sensors to track the locations of the ADV along the path. A second localization curve is generated as a result representing the locations of the ADV along the path tracked by the second localization system. A system delay of the second localization system is determined by comparing the second localization curve against the first localization curve as a localization reference.

Abstract: According to some embodiments, a system selects a number of polynomials representing a number of time segments of a time duration to complete the path trajectory. The system selects an objective function based on a number of cost functions to smooth speeds between the time segments. The system defines a set of constraints to the polynomials to at least ensure the polynomials are smoothly joined together. The system performs a quadratic programming (QP) optimization on the objective function in view of the set of constraints, such that a cost associated with the objective function reaches a minimum while the set of constraints are satisfied. The system generates a smooth speed for the time duration based on the optimized objective function to control the ADV autonomously.

Abstract: According to some embodiments, a system determines a number of boundary areas having predetermined dimensions centered around each of a number of control points of a first reference line. The system selects a number of two-dimensional polynomials each representing a segment of an optimal reference line between adjacent control points. The system defines a set of constraints to the two-dimensional polynomials to at least ensure the two-dimensional polynomials passes through each of the boundary areas. The system performs a quadratic programming (QP) optimization on a target function such that a total cost of the target function reaches minimum while the set of constraints are satisfied. The system generates a second reference line representing the optimal reference line based on the QP optimization to control the ADV autonomously according to the second reference line.

Abstract: According to some embodiments, a system segments a first path trajectory selected from an initial location of the ADV into a number of path segments, where each path segment is represented by a polynomial function. The system selects an objective function in view of the polynomial functions of the path segments for smoothing connections between the path segments. The system defines a set of constraints to the polynomial functions based on adjacent path segments in view of at least a road boundary and an obstacle perceived by the ADV. The system performs a quadratic programming (QP) optimization on the objective function in view of the added constraints, such that an output of the objective function reaches a minimum. The system generates a second path trajectory representing a path trajectory with an optimized objective function based on the QP optimization to control the ADV autonomously.