Get a list of cached scenario paths from a local cache. :param cache_path: Root path of the local cache dir. :param feature_names: Set of

trajectory: (bs, R, M, T, 4) valid_mask: (bs, T)

trajectory: (bs, R, M, T, 4) valid_mask: (bs, T)

prediction: (bs, A-1, T, 6) valid_mask: (bs, A-1, T) target: (bs, A-1, 6)

prediction: (bs, A-1, T, 6) valid_mask: (bs, A-1, T) target: (bs, A-1, 6)

Calculates the changing rate of state array representation. :param states: array describing the state of the ego-vehicle :ret

Retrieves type of token. :param token: geometry identifier :return: type of token

Main function for joint estimation of velocity, acceleration, curvature, and curvature rate given N poses sampled at discretization_time. Th

Retrieves roadblock from map-api based on id :param id: id of roadblock :return: roadblock class

Loads route dictionaries from map-api. :param route_roadblock_ids: ID's of on-route roadblocks

Main entrypoint for training/validation experiments. :param cfg: omegaconf dictionary

Execute all available challenges simultaneously on the same scenario. Calls run_simulation to allow planner to be specified via config or dir

Computes negative log likelihood of ground truth trajectory under a predictive distribution with a single mode, with a bivariate Gaussian dis

Plot a group of polylines with the specified config. Args: polylines: Collection of (N, 2) polylines to plot. style: Style of the

Determines wether input-points are in polygons of the occupancy map :param points: input-points :return: boolean array of sha

Propagates ego state array forward with motion model. :param states: state array representation of the ego-vehicle :param com

Remove ending of route, if the roadblock are intersecting the route (forming a loop). :param route_roadblocks: input route roadblocks :pa

Applies several methods to correct route roadblocks. :param ego_state: class containing ego state :param map_api: map object :param r

Execute all available challenges simultaneously on the same scenario. Helper function for main to allow planner to be specified via config or

Calculates the command values given the proposals to track. :param current_iteration: current simulation iteration. :param ne

Updates the config based on some conditions. :param cfg: omegaconf dictionary that is used to run the experiment.

Retrieves geometry of token. :param token: geometry identifier :return: Geometry of token

Initialize the class. :param feature_preprocessor: Feature preprocessor object. :param splitter: Splitter object used to retr

Constructor for LQR controller :param q_longitudinal: The weights for the Q matrix for the longitudinal subystem. :param r_lo

Construct BatchKinematicBicycleModel. :param vehicle: Vehicle parameters. :param max_steering_angle: [rad] Maximum absolute v

Initialize the augmentor, state: [x, y, yaw, vel, acc, steer, steer_rate, angular_vel, angular_acc], :param dt: Time interval

Initialize the augmentor, state: [x, y, yaw, vel, acc, steer, steer_rate, angular_vel, angular_acc], :param dt: Time interval

Initializes the class. :param model: pytorch model :param objectives: list of learning objectives used for supervision at ea

Initializes the class. :param model: pytorch model :param objectives: list of learning objectives used for supervision at ea

Constructor for the Dijkstra class. :param start_edge: The starting edge for the search :param candidate_lane_edge_ids: The c

Constructor of BreadthFirstSearchRoadBlock class :param start_roadblock_id: roadblock id where graph starts :param map_api: m

Initializes the ML planner class. :param model: Model to use for inference.