Abstract: A system and method for path and/or motion planning and for training such a system are described. In one aspect, the method comprises generating a sequence of predicted occupancy grid maps (OGMs) for T?T1 time steps based on a sequence of OGMs for 0?T1 time steps, a reference map of an environment in which an autonomous vehicle is operating, and a trajectory. A cost volume is generated for the sequence of predicted OGMs. The cost volume comprises a plurality of cost maps for T?T1 time steps. Each cost map corresponds to a predicted OGM in the sequence of predicted OGMs and has the same dimensions as the corresponding predicted OGM. Each cost map comprises a plurality of cells. Each cell in the cost map represents a cost of the cell in corresponding predicted OGM being occupied in accordance with a policy defined by a policy function.

Abstract: The present disclosure relates to methods and systems for spatiotemporal graph modelling of road users in observed frames of an environment in which an autonomous vehicle operates (i.e. a traffic scene), clustering of the road users into categories, and providing the spatiotemporal graph to a trained graphical convolutional neural network (GNN) to predict a future pedestrian action. The future pedestrian action can be: one of the pedestrian will cross a road and the pedestrian will not cross the road. The spatiotemporal graph includes a better understanding of the observed frames (i.e. traffic scene).

Abstract: A processor-implemented method and system for determining a predictive occupancy grid map (OGM) for an autonomous vehicle are disclosed. The method includes: receiving a set of OGMs including a current predicted OGM and one or more future predicted OGMs, the current OGM associated with a current timestamp and each future predicted OGM associated with a future timestamp; generating a weight map associated with the current timestamp based on one or more kinodynamic parameters of the vehicle at the current time stamp, and one or more weight map associated with a future timestamp; generating a set of filtered predicted OGMs by filtering the current predicted OGM with the weight map associated the current timestamp and filtering each respective future predicted OGM associated with a future timestamp with the weight map associated with the respective future timestamp; and sending a single predicted OGM to a trajectory generator.

Abstract: Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about the object and the environment in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about the object and the environment in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the object and the environment to corresponding control actions that are not applied to the object.

Abstract: Methods and systems for generating a predicted occupancy grid map (OGM) over at least one future time step are described. The system include a first encoder for extracting OGM features from an input OGM in a current time step. The system also includes a recurrent neural network for generating a corrective term from at least the OGM features, wherein the corrective term represents predicted change to the input OGM, and wherein the corrective term is applied to the input OGM to generate a corrected OGM. The corrected OGM represents features corresponding to occupancy of the environment in a first future time step. The system also includes a classifier for converting the corrected OGM to the predicted OGM for the first future time step. The predicted OGM is fed back as input for performing generating a predicted OGM for a second future time step.

Abstract: Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about the object and the environment in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about the object and the environment in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the object and the environment to corresponding control actions that are not applied to the object.

Abstract: A processor-implemented method and system for determining a predictive occupancy grid map (OGM) for an autonomous vehicle are disclosed. The method includes: receiving a set of OGMs including a current predicted OGM and one or more future predicted OGMs, the current OGM associated with a current timestamp and each future predicted OGM associated with a future timestamp; generating a weight map associated with the current timestamp based on one or more kinodynamic parameters of the vehicle at the current time stamp, and one or more weight map associated with a future timestamp; generating a set of filtered predicted OGMs by filtering the current predicted OGM with the weight map associated the current timestamp and filtering each respective future predicted OGM associated with a future timestamp with the weight map associated with the respective future timestamp; and sending a single predicted OGM to a trajectory generator.

Abstract: Methods and systems for predicting behavior of a dynamic object of interest in an environment of a vehicle are described. Time series feature data are received, representing features of objects in the environment, including a dynamic object of interest. The feature data are categorized into one of a plurality of defined object categories. Each categorized set of data is encoded into a respective categorical representation that represents temporal change of features within the respective defined object category. The categorical representations are combined into a single shared representation. A categorical interaction representation is generated based on the single shared representation that represents contributions of temporal change in each defined object category to a final time step of the shared representation.

Abstract: A processor-implemented method and system for determining a predictive occupancy grid map (OGM) for an autonomous vehicle are disclosed. The method includes: receiving a set of OGMs including a current predicted OGM and one or more future predicted OGMs, the current OGM associated with a current timestamp and each future predicted OGM associated with a future timestamp; generating a weight map associated with the current timestamp based on one or more kinodynamic parameters of the vehicle at the current time stamp, and one or more weight map associated with a future timestamp; generating a set of filtered predicted OGMs by filtering the current predicted OGM with the weight map associated the current timestamp and filtering each respective future predicted OGM associated with a future timestamp with the weight map associated with the respective future timestamp; and sending a single predicted OGM to a trajectory generator.

Abstract: A method for generation of an augmented point cloud with point features from aggregated 3D coordinate data and related device. The method comprises receiving a current point cloud in the form of 3D coordinate data in ego coordinates from one or more detection and ranging (DAR) devices of a vehicle. Features are extracted from the current point cloud. A previous point cloud is transformed into ego coordinates using a current location of the vehicle. Each point in the previous point cloud is transformed to align with a corresponding point in the current point cloud to generate a transformed point cloud. The current point cloud is aggregated with the transformed point cloud to generate an aggregated point cloud. The current point features are aggregated with the point features of the transformed point cloud to generate aggregated point features.

Abstract: Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about a state of the object in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about a current state of the object in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the state of the object to corresponding control actions that are not applied to the object.

Abstract: Method and system for controlling the behavior of an object. Behavior of the object is controlled during a first time period by using a first agent that applies a first behavior policy to map observations about the object and the environment in the first time period to a corresponding control action. Control is transitioned from the first agent to a second agent during a transition period following the first time period. Behavior of the object during a second time period following the transition period is controlled by using a second agent that applies a second behavior policy to map observations about the object and the environment in the second time period to a corresponding control action that is applied to the object. During transition the first agent applies the first behavior policy control the object and the second agent applies the second behavior policy to map observations about the object and the environment to corresponding control actions that are not applied to the object.

Abstract: A LIDAR scanning system. The LIDAR system comprises a laser configured to transmit laser light. An optical switch is optically coupled to the laser to receive laser light via an input port. The optical switch includes a plurality of output ports for transmitting received laser light to an environment to be scanned. Each of the plurality of output ports is oriented in a different direction. A detector subsystem is positioned to receive reflected laser light. A processor is coupled to the detector subsystem. The processor is configured to receive data signals from the detector subsystem. The processor is also configured to determine a distance from the LIDAR scanning system to one or more objects in an environment of the LIDAR scanning system based on a time between a transmission of beams of laser light and a reception of a reflection of the beams of laser light.

Abstract: A method for generation of an augmented point cloud with point features from aggregated 3D coordinate data and related device. The method comprises receiving a current point cloud in the form of 3D coordinate data in ego coordinates from one or more detection and ranging (DAR) devices of a vehicle. Features are extracted from the current point cloud. A previous point cloud is transformed into ego coordinates using a current location of the vehicle. Each point in the previous point cloud is transformed to align with a corresponding point in the current point cloud to generate a transformed point cloud. The current point cloud is aggregated with the transformed point cloud to generate an aggregated point cloud. The current point features are aggregated with the point features of the transformed point cloud to generate aggregated point features.

Abstract: A system and method for path and/or motion planning and for training such a system are described. In one aspect, the method comprises generating a sequence of predicted occupancy grid maps (OGMs) for T-T1 time steps based on a sequence of OGMs for 0-T1 time steps, a reference map of an environment in which an autonomous vehicle is operating, and a trajectory. A cost volume is generated for the sequence of predicted OGMs. The cost volume comprises a plurality of cost maps for T-T1 time steps. Each cost map corresponds to a predicted OGM in the sequence of predicted OGMs and has the same dimensions as the corresponding predicted OGM. Each cost map comprises a plurality of cells. Each cell in the cost map represents a cost of the cell in corresponding predicted OGM being occupied in accordance with a policy defined by a policy function.

Abstract: Methods and systems for observation prediction in autonomous vehicles are described. A set of observations is received, including a current observation and one or more previous observations. Each observation includes a respective view of the environment and a vehicle state at each time step. A current action is received. A current-action embedded view is produced, the current-action embedded view representing an estimated change in vehicle state caused by the current action in a current view. A predicted view is generated from the current-action embedded view and the set of observations. The predicted view is re-centered. A predicted observation is fed back, including the re-centered predicted view and estimated change in vehicle state, to be included in the set of observations as input for multi-step training of the action-based prediction subsystem.

Abstract: A processor-implemented method and system for determining a predictive occupancy grid map (OGM) for an autonomous vehicle are disclosed. The method includes: receiving a set of OGMs including a current predicted OGM and one or more future predicted OGMs, the current OGM associated with a current timestamp and each future predicted OGM associated with a future timestamp; generating a weight map associated with the current timestamp based on one or more kinodynamic parameters of the vehicle at the current time stamp, and one or more weight map associated with a future timestamp; generating a set of filtered predicted OGMs by filtering the current predicted OGM with the weight map associated the current timestamp and filtering each respective future predicted OGM associated with a future timestamp with the weight map associated with the respective future timestamp; and sending a single predicted OGM to a trajectory generator.

Abstract: A method and system for localization of a ground-based vehicle or moving object within an environment. The system acquires radar map data from a radar system and compares the radar map data to reference map data. The position of the vehicle or moving object is then obtained by matching the radar map data to the reference map data.

Abstract: A multi layer learning based control system and method for an autonomous vehicle or mobile robot. A mission planning layer, behavior planning layer and motion planning layer each having one or more neural neworks are used to develop an optimal route for the autonomous vehicle or mobile robot, provide a series of functional tasks associated with at least one or more of the neural networks to follow the planned optimal route and develop commands to implement the functional tasks.

Abstract: Methods and systems for generating a predicted occupancy grid map (OGM) over at least one future time step are described. The system include a first encoder for extracting OGM features from an input OGM in a current time step. The system also includes a recurrent neural network for generating a corrective term from at least the OGM features, wherein the corrective term represents predicted change to the input OGM, and wherein the corrective term is applied to the input OGM to generate a corrected OGM. The corrected OGM represents features corresponding to occupancy of the environment in a first future time step. The system also includes a classifier for converting the corrected OGM to the predicted OGM for the first future time step. The predicted OGM is fed back as input for performing generating a predicted OGM for a second future time step.