Abstract: Systems and techniques are provided for generating a secondary track based on unused sensor data of an autonomous vehicle (AV). An example method can include receiving unused sensor data collected by one or more sensors of an AV. The unused sensor data can be a remainder of sensor data that is used for generating a primary track of one or more objects. Also, the unused sensor data can include a detection of an object. The example method can further include validating the object that is detected in the unused sensor data based on one or more parameters associated with the object, comparing the object detected in the unused sensor data with the one or more objects of the primary track for similarity, determining kinematics of the object based on a geometry of the object, and generating a secondary track of the object for localization of the AV.

Abstract: The disclosed technology provides solutions for calculating a sensitivity metric and determining, based on the sensitivity metric, whether to continue training the machine learning model. A method of the disclosed technology can include steps for determining a first value of a first output parameter during a first training iteration of a machine learning model; calculating a first sensitivity metric based on the first value of the first output parameter and one or more values of a first input parameter that are provided to the machine learning model during the first training iteration, wherein the first sensitivity metric is indicative of a rate of change of the first output parameter relative to the first input parameter; and determining, based on the first sensitivity metric, whether to continue training of the machine learning model. Systems and machine-readable media are also provided.

Abstract: Systems and techniques are disclosed for determining an autonomous vehicle (AV) boundary at which an occluded object is realized. An example method can include generating, based on sensor data collected in a driving environment, a first set of data representing the driving environment; generating, based on the sensor data, a second set of data representing an occluded scene element in the driving environment; generating, based on the sensor data, a third set of data representing an occluding object that at least partially occludes the occluded scene element from a view and/or perspective of one or more sensors of an AV in the driving environment; and based on the first, second, and third set of data and a trajectory of the AV, determine a dissipation boundary associated with the occluded scene element, the dissipation boundary comprising a location(s) where the AV is predicted to perceive the occluded scene element.

Abstract: A sequence of images generated at respective times by one or more sensors configured to sense an environment through which objects are moving relative to the one or more sensors is received. A message passing graph having a multiplicity of layers associated with the sequence of images is constructed. A neural network supported by the message passing graph is trained. The training includes performing a pass through the message passing graph in a forward direction including by adding a new feature node based on a feature detection and a new edge node and performing a pass through the message passing graph in a backward direction, including by updating at least one edge node of the message passing graph. Multiple features are tracked through the sequence of images, including passing messages through the message passing graph.

Abstract: A surround multi-object tracking and surround vehicle motion prediction framework is provided. A full-surround camera array and LiDAR sensor based approach provides for multi-object tracking for autonomous vehicles. The multi-object tracking incorporates a fusion scheme to handle object proposals from the different sensors within the calibrated camera array. A motion prediction framework leverages the instantaneous motion of vehicles, an understanding of motion patterns of freeway traffic, and the effect of inter-vehicle interactions. The motion prediction framework incorporates probabilistic modeling of surround vehicle trajectories. Additionally, subcategorizing trajectories based on maneuver classes leads to better modeling of motion patterns. A model takes into account interactions between surround vehicles for simultaneously predicting each of their motion.

Abstract: A method for multi-object tracking includes receiving a sequence of images generated at respective times by one or more sensors configured to sense an environment through which objects are moving relative to the one or more sensors, and constructing a message passing graph in which each of a multiplicity of layers corresponds to a respective one in the sequence of images.

Abstract: A method for multi-object tracking includes receiving a sequence of images generated at respective times by one or more sensors configured to sense an environment through which objects are moving relative to the one or more sensors, and constructing a message passing graph in which each of a multiplicity of layers corresponds to a respective one in the sequence of images. The method also includes tracking multiple features through the sequence of images, including passing messages in a forward direction and a backward direction through the message passing graph to share information across time.

Abstract: A method for multi-object tracking includes receiving a sequence of images generated at respective times by one or more sensors configured to sense an environment through which objects are moving relative to the one or more sensors, and constructing a message passing graph in which each of a multiplicity of layers corresponds to a respective one in the sequence of images.

Abstract: A surround multi-object tracking and surround vehicle motion prediction framework is provided. A full-surround camera array and LiDAR sensor based approach provides for multi-object tracking for autonomous vehicles. The multi-object tracking incorporates a fusion scheme to handle object proposals from the different sensors within the calibrated camera array. A motion prediction framework leverages the instantaneous motion of vehicles, an understanding of motion patterns of freeway traffic, and the effect of inter-vehicle interactions. The motion prediction framework incorporates probabilistic modeling of surround vehicle trajectories. Additionally, subcategorizing trajectories based on maneuver classes leads to better modeling of motion patterns. A model takes into account interactions between surround vehicles for simultaneously predicting each of their motion.