Abstract: Techniques for determining a prediction probability associated with a disengagement event are discussed herein. A first prediction probability can include a probability that a safety driver associated with a vehicle (such as an autonomous vehicle) may assume control over the vehicle. A second prediction probability can include a probability that an object in an environment is associated the disengagement event. Sensor data can be captured and represented as a top-down representation of the environment. The top-down representation can be input to a machine learned model trained to output prediction probabilities associated with a disengagement event. The vehicle can be controlled based the prediction probability and/or the interacting object probability.

Abstract: Techniques for top-down scene discrimination are discussed. A system receives scene data associated with an environment proximate a vehicle. The scene data is input to a convolutional neural network (CNN) discriminator trained using a generator and a classification of the output of the CNN discriminator. The CNN discriminator generates an indication of whether the scene data is a generated scene or a captured scene. If the scene data is data generated scene, the system generates a caution notification indicating that a current environmental situation is different from any previous situations. Additionally, the caution notification is communicated to at least one of a vehicle system or a remote vehicle monitoring system.

Abstract: Techniques for modeling the probability distribution of errors in perception systems are discussed herein. For example, techniques may include modeling error distribution for attributes such as position, size, pose, and velocity of objects detected in an environment, and training a mixture model to output specific error probability distributions based on input features such as object classification, distance to the object, and occlusion. The output of the trained model may be used to control the operation of a vehicle in an environment, generate simulations, perform collision probability analyses, and to mine log data to detect collision risks.

Abstract: Techniques for top-down scene generation are discussed. A generator component may receive multi-dimensional input data associated with an environment. The generator component may generate, based at least in part on the multi-dimensional input data, a generated top-down scene. A discriminator component receives the generated top-down scene and a real top-down scene. The discriminator component generates binary classification data indicating whether an individual scene in the scene data is classified as generated or classified as real. The binary classification data is provided as a loss to the generator component and the discriminator component.

Abstract: Techniques for determining predictions on a top-down representation of an environment based on object movement are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) may capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle, a pedestrian, a bicycle). A multi-channel image representing a top-down view of the object(s) and the environment may be generated based in part on the sensor data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) may also be encoded in the image. Multiple images may be generated representing the environment over time and input into a prediction system configured to output a trajectory template (e.g., general intent for future movement) and a predicted trajectory (e.g., more accurate predicted movement) associated with each object. The prediction system may include a machine learned model configured to output the trajectory template(s) and the predicted trajector(ies).

Abstract: Techniques to predict object behavior in an environment are discussed herein. For example, such techniques may include determining a trajectory of the object, determining an intent of the trajectory, and sending the trajectory and the intent to a vehicle computing system to control an autonomous vehicle. The vehicle computing system may implement a machine learned model to process data such as sensor data and map data. The machine learned model can associate different intentions of an object in an environment with different trajectories. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on object's intentions and trajectories.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a distribution of predicted positions for the object in the future that meet a criterion, allowing for more efficient sampling. A predicted position of the object in the future may be determined by sampling from the distribution.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a predicted position of the object at a subsequent timestep. Further, a predicted trajectory of the object may be determined using predicted positions of the object at various timesteps.

Abstract: Techniques for determining a response of a simulated vehicle to a simulated object in a simulation are discussed herein. Log data captured by a physical vehicle in an environment can be received. Object data representing an object in the log data can be used to instantiate a simulated object in a simulation to determine a response of a simulated vehicle to the simulated object. Additionally, one or more trajectory segments in a trajectory library representing the log data can be determined and instantiated as a trajectory of the simulated object in order to increase the accuracy and realism of the simulation.

Abstract: Techniques for determining predictions on a top-down representation of an environment based on vehicle action(s) are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) can capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle or a pedestrian). A multi-channel image representing a top-down view of the object(s) and the environment can be generated based on the sensor data, map data, and/or action data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) can be encoded in the image. Action data can represent a target lane, trajectory, etc. of the first vehicle. Multiple images can be generated representing the environment over time and input into a prediction system configured to output prediction probabilities associated with possible locations of the object(s) in the future, which may be based on the actions of the autonomous vehicle.

Abstract: Techniques relating to monitoring map consistency are described. In an example, a monitoring component associated with a vehicle can receive sensor data associated with an environment in which the vehicle is positioned. The monitoring component can generate, based at least in part on the sensor data, an estimated map of the environment, wherein the estimated map is encoded with policy information for driving within the environment. The monitoring component can then compare first information associated with a stored map of the environment with second information associated with the estimated map to determine whether the estimated map and the stored map are consistent. Component(s) associated with the vehicle can then control the object based at least in part on results of the comparing.

Abstract: Techniques for determining a vehicle action and controlling a vehicle to perform the vehicle action for navigating the vehicle in an environment can include determining a vehicle action, such as a lane change action, for a vehicle to perform in an environment. The vehicle can detect, based at least in part on sensor data, an object associated with a target lane associated with the lane change action sensor data. In some instances, the vehicle may determine attribute data associated with the object and input the attribute data to a machine-learned model that can output a yield score. Based on such a yield score, the vehicle may determine whether it is safe to perform the lane change action.

Abstract: A system may automatically create training datasets for training a segmentation model to recognize features such as lanes on a road. The system may receive sensor data representative of a portion of an environment and map data from a map data store including existing map data for the portion of the environment that includes features present in that portion of the environment. The system may project or overlay the features onto the sensor data to create training datasets for training the segmentation model, which may be a neural network. The training datasets may be communicated to the segmentation model to train the segmentation model to segment data associated with similar features present in different sensor data. The trained segmentation model may be used to update the map data store, and may be used to segment sensor data obtained from other portions of the environment, such as portions not previously mapped.

Abstract: Techniques relating to monitoring map consistency are described. In an example, a monitoring component associated with a vehicle can receive sensor data associated with an environment in which the vehicle is positioned. The monitoring component can generate, based at least in part on the sensor data, an estimated map of the environment, wherein the estimated map is encoded with policy information for driving within the environment. The monitoring component can then compare first information associated with a stored map of the environment with second information associated with the estimated map to determine whether the estimated map and the stored map are consistent. Component(s) associated with the vehicle can then control the object based at least in part on results of the comparing.

Abstract: Techniques for top-down scene discrimination are discussed. A system receives scene data associated with an environment proximate a vehicle. The scene data is input to a convolutional neural network (CNN) discriminator trained using a generator and a classification of the output of the CNN discriminator. The CNN discriminator generates an indication of whether the scene data is a generated scene or a captured scene. If the scene data is data generated scene, the system generates a caution notification indicating that a current environmental situation is different from any previous situations. Additionally, the caution notification is communicated to at least one of a vehicle system or a remote vehicle monitoring system.

Abstract: Techniques for top-down scene generation are discussed. A generator component may receive multi-dimensional input data associated with an environment. The generator component may generate, based at least in part on the multi-dimensional input data, a generated top-down scene. A discriminator component receives the generated top-down scene and a real top-down scene. The discriminator component generates binary classification data indicating whether an individual scene in the scene data is classified as generated or classified as real. The binary classification data is provided as a loss to the generator component and the discriminator component.

Abstract: A trajectory estimate of a wheeled vehicle can be determined based at least in part on determining a wheel angle associated with the vehicle. In some examples, at least a portion of the image associated with the wheeled vehicle may be input into a machine-learned model that is trained to classify and/or regress wheel directions of wheeled vehicles. The machine-learned model may output a predicted wheel direction. The wheel direction and/or additional or historical sensor data may be used to estimate a trajectory of the wheeled vehicle. The predicted trajectory of the object can then be used to generate and refine an autonomous vehicle's trajectory as the autonomous vehicle proceeds through the environment.

Abstract: Techniques for determining an uncertainty metric associated with an object in an environment can include determining the object in the environment and a set of candidate trajectories associated with the object. Further, a vehicle, such as an autonomous vehicle, can be controlled based at least in part on the uncertainty metric. The vehicle can determine a traversed trajectory associated with the object and determine a difference between the traversed trajectory and the set of candidate trajectories. Based on the difference, the vehicle can determine an uncertainty metric associated with the object. In some instances, the vehicle can input the traversed trajectory and the set of candidate trajectories to a machine-learned model that can output the uncertainty metric.

Abstract: The described techniques relate to predicting object behavior based on top-down representations of an environment comprising top-down representations of image features in the environment. For example, a top-down representation may comprise a multi-channel image that includes semantic map information along with additional information for a target object and/or other objects in an environment. A top-down image feature representation may also be a multi-channel image that incorporates various tensors for different image features with channels of the multi-channel image, and may be generated directly from an input image. A prediction component can generate predictions of object behavior based at least in part on the top-down image feature representation, and in some cases, can generate predictions based on the top-down image feature representation together with the additional top-down representation.

Abstract: The described techniques relate to predicting object behavior based on top-down representations of an environment comprising top-down representations of image features in the environment. For example, a top-down representation may comprise a multi-channel image that includes semantic map information along with additional information for a target object and/or other objects in an environment. A top-down image feature representation may also be a multi-channel image that incorporates various tensors for different image features with channels of the multi-channel image, and may be generated directly from an input image. A prediction component can generate predictions of object behavior based at least in part on the top-down image feature representation, and in some cases, can generate predictions based on the top-down image feature representation together with the additional top-down representation.