Abstract: A modified Kalman filter may include one or more neural networks to augment or replace components of the Kalman filter in such a way that the human interpretability of the filter's inner functions is preserved. The neural networks may include a neural network to account for bias in measurement data, a neural network to account for unknown controls in predicting a state of an object, a neural network ensemble that is trained differently based on different sensor data, a neural network for determining the Kalman gain, and/or a set of Kalman filters including various neural networks that determine independent estimated states, which may be fused using Bayesian fusion to determine a final estimated state.

Abstract: Techniques to use a trained model to determine a yaw of an object are described. For example, a system may implement various techniques to generate multiple representations for an object in an environment. Each representation vary based on the technique and data used. An estimation component may estimate a representation from the multiple representations. The model may be implemented to output a yaw for the object using the multiple representations, the estimated representation, and/or additional information. The output yaw may be used to track an object, generate a trajectory, or otherwise control a vehicle.

Abstract: A vehicle computing system may implement techniques to determine whether two objects in an environment are related as an articulated object. The techniques may include applying heuristics and algorithms to object representations (e.g., bounding boxes) to determine whether two objects are related as a single object with two portions that articulate relative to each other. The techniques may include predicting future states of the articulated object in the environment. One or more model(s) may be used to determine presence of the articulated object and/or predict motion of the articulated object in the future. Based on the presence and/or motion of the articulated object, the vehicle computing system may control operation of the vehicle.

Abstract: The techniques discussed herein include modifying a Kalman filter to additionally include a loss component that dampens the effect measurements with large errors (or measurements indicating states that are rather different than the predicted state) have on the Kalman filter and, in particular, the updated uncertainty and/or updated prediction. In some examples, the techniques include scaling a Kalman gain based at least in part on a loss function that is based on the innovation determined by the Kalman filter. The techniques additionally or alternatively include a reformulation of a Kalman filter that ensures that the uncertainties determined by the Kalman filter remain symmetric and positive definite.

Abstract: A computer-implemented method. Includes obtaining pointwise data indicating, for a plurality of time steps, a pointwise measurement of a state of an object detected by an object detection system. Includes obtaining, from a runtime model, runtime data indicating, for the plurality of time steps, a runtime estimate of the state of the object. Includes processing, by a benchmark model, the pointwise data to determine, for the plurality of time steps, a benchmark estimate of the state of the object. Includes evaluating a metric measuring, for the plurality of time steps, a deviation between the runtime estimate and the benchmark estimate of the state of the object. Includes updating, based on the on the evaluation of the metric, the runtime model.

Abstract: A computer-implemented method. Includes obtaining pointwise data indicating, for a plurality of time steps, a pointwise measurement of a state of an object detected by an object detection system. Includes obtaining, from a runtime model, runtime data indicating, for the plurality of time steps, a runtime estimate of the state of the object. Includes processing, by a benchmark model, the pointwise data to determine, for the plurality of time steps, a benchmark estimate of the state of the object. Includes evaluating a metric measuring, for the plurality of time steps, a deviation between the runtime estimate and the benchmark estimate of the state of the object. Includes updating, based on the on the evaluation of the metric, the runtime model.

Abstract: Some radar sensors may provide a Doppler measurement indicating a relative velocity of an object to a velocity of the radar sensor. Techniques for determining a two-or-more-dimensional velocity from one or more radar measurements associated with an object may comprise determining a data structure that comprises a yaw assumption and a set of weights to tune the influence of the yaw assumption. Determining the two-or-more-dimensional velocity may further comprise using the data structure as part of regression algorithm to determine a velocity and/or yaw rate associated with the object.

Abstract: Techniques for determining distortion in a map caused by measurement errors are discussed herein. For example, such techniques may include implementing a model to estimate map distortion between the map frame and the inertial frame. Data such as sensor data, map data, and vehicle state data may be input into the model. A map distortion value output from the model may be used to compensate vehicle operations in a local region by approximating the distortion as linearly varying about the region. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on the trajectory.

Abstract: Localization error monitoring using vehicle state information is described. A computing system associated with a vehicle may determine a current state of the vehicle, such as a location, position, orientation, velocity, acceleration, or the like. The vehicle computing system may determine one or more metrics associated with the state of the vehicle. The metrics may include a variance associated with the state, a residual associated with a measurement corresponding to the state, or a correction factor applied to correct an input error. The computing system may determine whether the metric exceeds a threshold value. Based on a threshold exceedance, the computing system may determine one or more errors associated with a state of the vehicle. The vehicle computing system may control the vehicle based on the one or more errors.

Abstract: Localization error monitoring using vehicle state information is described. A computing system associated with a vehicle may determine a current state of the vehicle, such as a location, position, orientation, velocity, acceleration, or the like. The vehicle computing system may determine one or more metrics associated with the state of the vehicle. The metrics may include a variance associated with the state, a residual associated with a measurement corresponding to the state, or a correction factor applied to correct an input error. The computing system may determine whether the metric exceeds a threshold value. Based on a threshold exceedance, the computing system may determine one or more errors associated with a state of the vehicle. The vehicle computing system may control the vehicle based on the one or more errors.

Abstract: Some radar sensors may provide a Doppler measurement indicating a relative velocity of an object to a velocity of the radar sensor. Techniques for determining a two-or-more-dimensional velocity from one or more radar measurements associated with an object may comprise determining a data structure that comprises a yaw assumption and a set of weights to tune the influence of the yaw assumption. Determining the two-or-more-dimensional velocity may further comprise using the data structure as part of regression algorithm to determine a velocity and/or yaw rate associated with the object.