Abstract: A system and a method for motion forecasting are provided. The system acquires input data including road map images and historical trajectory information of a set of agents and transforms the input data into a vectorized representation. The system generates a first candidate trajectory prediction for the set of agents by application of a motion prediction neural network on the vectorized representation. The system further generates a second candidate trajectory prediction for the set of agents by application of a rule-based prediction model on the acquired input data. The system trains the motion prediction neural network based on the first candidate trajectory prediction and a set of ground truth trajectories of the set of agents. The system generates ranking results for the first candidate trajectory prediction and the second candidate trajectory prediction based on a routing function network and trains the routing function network based on the ranking results.

Abstract: A method for generating operable driving areas for an autonomous driving vehicle based on a path trajectory of the autonomous driving vehicle is provided. The method may form a space time (ST) graph indicating a distance of travel along the path trajectory with respect to time of the autonomous driving vehicle and path trajectories of devices intersecting with the path trajectory of the autonomous driving vehicle. The method may segment the ST graph into cells, wherein viable cells represent discretized viable unoccupied spaces in the ST graph. The method may find passage ways for the autonomous driving vehicle based on the viable cells. The method may select a desired passage way using quadratic programming (QP) optimization when multiple passage ways are found.

Abstract: A method for generating operable driving areas for an autonomous driving vehicle based on a path trajectory of the autonomous driving vehicle is provided. The method may form a space time (ST) graph indicating a distance of travel along the path trajectory with respect to time of the autonomous driving vehicle and path trajectories of devices intersecting with the path trajectory of the autonomous driving vehicle, wherein the path trajectory of each device is based on current and historical data for each device. The method may segment the ST graph into cells, wherein viable cells represent discretized viable unoccupied spaces in the ST graph. The method may find passage ways for the autonomous driving vehicle based on the viable cells. The method may select a desired passage way using quadratic programming (QP) optimization when multiple passage ways are found.

Abstract: A method for generating operable driving areas for an autonomous driving vehicle based on a path trajectory of the autonomous driving vehicle is provided. The method may form a space time (ST) graph indicating a distance of travel along the path trajectory with respect to time of the autonomous driving vehicle and path trajectories of devices intersecting with the path trajectory of the autonomous driving vehicle. The method may segment the ST graph into cells, wherein viable cells represent discretized viable unoccupied spaces in the ST graph. The method may find passage ways for the autonomous driving vehicle based on the viable cells. The method may select a desired passage way using quadratic programming (QP) optimization when multiple passage ways are found.

Abstract: A method for generating operable driving areas for an autonomous driving vehicle based on a path trajectory of the autonomous driving vehicle is provided. The method may form a space time (ST) graph indicating a distance of travel along the path trajectory with respect to time of the autonomous driving vehicle and path trajectories of devices intersecting with the path trajectory of the autonomous driving vehicle. The method may segment the ST graph into cells, wherein viable cells represent discretized viable unoccupied spaces in the ST graph. The method may find passage ways for the autonomous driving vehicle based on the viable cells. The method may select a desired passage way using quadratic programming (QP) optimization when multiple passage ways are found. The QP optimization may use hard and soft constraints to select the desired passage way to minimize time travel and undesirable movement of the autonomous driving vehicle.

Abstract: A method for generating operable driving areas for an autonomous driving vehicle based on a path trajectory of the autonomous driving vehicle is provided. The method may form a space time (ST) graph indicating a distance of travel along the path trajectory with respect to time of the autonomous driving vehicle and path trajectories of devices intersecting with the path trajectory of the autonomous driving vehicle. The method may segment the ST graph into cells, wherein viable cells represent discretized viable unoccupied spaces in the ST graph, and wherein each cell is defined at each time segment on the ST graph by minimum smin and maximum smax bounds in distance. The method may find passage ways for the autonomous driving vehicle based on the viable cells. The method may generate a lower bound and an upper bound for each passage way. The method may select a desired passage way using quadratic programming (QP) optimization when multiple passage ways are found.

Abstract: A method for generating operable driving areas for an autonomous driving vehicle based on a path trajectory of the autonomous driving vehicle is provided. The method may form a space time (ST) graph indicating a distance of travel along the path trajectory with respect to time of the autonomous driving vehicle and path trajectories of devices intersecting with the path trajectory of the autonomous driving vehicle, wherein the path trajectory of each device is based on current and historical data for each device. The method may segment the ST graph into cells, wherein viable cells represent discretized viable unoccupied spaces in the ST graph. The method may find passage ways for the autonomous driving vehicle based on the viable cells. The method may select a desired passage way using quadratic programming (QP) optimization when multiple passage ways are found.

Abstract: An electronic device and a method for AV trajectory planning using neural networks trained based on knowledge distillation is provided. A set of updated values of a set of variables of an objective function for trajectory planning of an ego AV are determined. A first prediction network is applied on an updated value of the set of updated values, a states of the ego AV and a set of AVs over a past time interval. Based on the application, an output is determined. The output includes states of the ego AV and set of AVs over a future time interval. The electronic device determines a set of optimal values based on the updated value and the determined output satisfying a safety constraint associated with the objective function. Further, the electronic device controls a trajectory of the ego AV based on the set of optimal values of the set of variables.

Abstract: Systems and methods for generating instructions for a vehicle to navigate an unsignaled intersection are provided. The method may include: generating an expected return over a sequence of actions of the vehicle; determining an optimal policy by selecting an action with a maximum value for the vehicle; executing dynamic frame skipping to expedite learning a repeated action of the vehicle; prioritize an experience replay by utilizing an experience replay buffer to break correlations between sequential steps of the vehicle; generate a plurality of state-action representations based on at least one of the expected return, the optimal policy, the dynamic frame skipping, or the prioritized experience replay; generate the instructions for navigating the unsignaled intersection based on the plurality of state-action representations; and transmit the instructions for navigating the unsignaled intersection to the vehicle such that the vehicle executes the instructions to navigate the unsignaled intersection.

Abstract: The present disclosure generally relates to methods and systems for controlling an autonomous vehicle. The vehicle may collect scenario information from one or more sensors mounted on a vehicle. The vehicle may determine a high-level option for a fixed time horizon based on the scenario information. The vehicle may apply a prediction algorithm to the high-level option to mask undesired low-level behaviors for completing the high-level option where a collision is predicted to occur. The vehicle may evaluate a restricted subspace of low-level behaviors using a reinforcement learning system. The vehicle may control the vehicle to perform the high-level option by executing a low-level behavior selected from the restricted subspace. The vehicle may adjust the reinforcement learning system by evaluating a metric of the executed low-level behavior.

Abstract: Systems and methods for generating instructions for a vehicle to navigate an unsignaled intersection are provided. The method may include: generating an expected return over a sequence of actions of the vehicle; determining an optimal policy by selecting an action with a maximum value for the vehicle; executing dynamic frame skipping to expedite learning a repeated action of the vehicle; prioritize an experience replay by utilizing an experience replay buffer to break correlations between sequential steps of the vehicle; generate a plurality of state-action representations based on at least one of the expected return, the optimal policy, the dynamic frame skipping, or the prioritized experience replay; generate the instructions for navigating the unsignaled intersection based on the plurality of state-action representations; and transmit the instructions for navigating the unsignaled intersection to the vehicle such that the vehicle executes the instructions to navigate the unsignaled intersection.

Abstract: The present disclosure generally relates to methods and systems for controlling an autonomous vehicle. The vehicle may collect scenario information from one or more sensors mounted on a vehicle. The vehicle may determine a high-level option for a fixed time horizon based on the scenario information. The vehicle may apply a prediction algorithm to the high-level option to mask undesired low-level behaviors for completing the high-level option where a collision is predicted to occur. The vehicle may evaluate a restricted subspace of low-level behaviors using a reinforcement learning system. The vehicle may control the vehicle to perform the high-level option by executing a low-level behavior selected from the restricted subspace. The vehicle may adjust the reinforcement learning system by evaluating a metric of the executed low-level behavior.