Will Vega-Brown

We present the first asymptotically optimal algorithm for motion planning problems with piecewise-analytic differential constraints, like manipulation or rearrangement planning. This class of problems is
characterized by the presence of differential constraints that are local in nature: a robot can only move an object once the object has been grasped. These constraints are not analytic and thus cannot be addressed by standard differentially constrained planning algorithms. We demonstrate… Show more

We present the first asymptotically optimal algorithm for motion planning problems with piecewise-analytic differential constraints, like manipulation or rearrangement planning. This class of problems is
characterized by the presence of differential constraints that are local in nature: a robot can only move an object once the object has been grasped. These constraints are not analytic and thus cannot be addressed by standard differentially constrained planning algorithms. We demonstrate that, given the ability to sample from the locally reachable subset of the configuration space with positive probability, we can construct random geometric graphs that contain optimal plans with probability one in the limit of infinite samples. This approach does not require a hand-coded symbolic abstraction. We demonstrate our approach in simulation on a simple manipulation planning problem, and show it generates lower-cost plans than a sequential task and motion planner. Show less

Many algorithms in computer vision and robotics make strong assumptions about uncertainty, and rely on the validity of these assumptions to produce accurate and consistent state estimates. In practice, dynamic environments may degrade sensor performance in predictable ways that cannot be captured with static uncertainty parameters. In this paper, we employ fast nonparametric Bayesian inference techniques to more accurately model sensor uncertainty. By setting a prior on observation uncertainty,… Show more

Many algorithms in computer vision and robotics make strong assumptions about uncertainty, and rely on the validity of these assumptions to produce accurate and consistent state estimates. In practice, dynamic environments may degrade sensor performance in predictable ways that cannot be captured with static uncertainty parameters. In this paper, we employ fast nonparametric Bayesian inference techniques to more accurately model sensor uncertainty. By setting a prior on observation uncertainty, we derive a predictive robust estimator, and show how our model can be learned from sample images, both with and without knowledge of the motion used to generate the data. We validate our approach through Monte Carlo simulations, and report significant improvements in localization accuracy relative to a fixed noise model in several settings, including on synthetic data, the KITTI dataset, and our own experimental platform. Show less

We develop a model by choosing the maximum entropy distribution from the set of models satisfying certain smoothness and independence criteria; we show that inference on this model generalizes local kernel estimation to the context of Bayesian inference on stochastic processes. Our model enables Bayesian inference in contexts when standard techniques like Gaussian process inference are too expensive to apply. Exact inference on our model is possible for any likelihood function from the… Show more

We develop a model by choosing the maximum entropy distribution from the set of models satisfying certain smoothness and independence criteria; we show that inference on this model generalizes local kernel estimation to the context of Bayesian inference on stochastic processes. Our model enables Bayesian inference in contexts when standard techniques like Gaussian process inference are too expensive to apply. Exact inference on our model is possible for any likelihood function from the exponential family. Inference is then highly efficient, requiring only O (log N) time and O (N) space at run time. We demonstrate our algorithm on several problems and show quantifiable improvement in both speed and performance relative to models based on the Gaussian process. Show less

We present CELLO (Covariance Estimation and Learning through Likelihood Optimization), an algorithm for predicting the covariances of measurements based on any available informative features. This algorithm is intended to improve the accuracy and reliability of on-line state estimation by providing a principled way to extend the conventional fixed-covariance Gaussian measurement model. We show that in experiments, CELLO learns to predict measurement covariances that agree with empirical… Show more

We present CELLO (Covariance Estimation and Learning through Likelihood Optimization), an algorithm for predicting the covariances of measurements based on any available informative features. This algorithm is intended to improve the accuracy and reliability of on-line state estimation by providing a principled way to extend the conventional fixed-covariance Gaussian measurement model. We show that in experiments, CELLO learns to predict measurement covariances that agree with empirical covariances obtained by manually annotating sensor regimes. We also show that using the learned covariances during filtering provides substantial quantitative improvement to the overall state estimate. Show less

We present an algorithm for providing a dynamic model of sensor measurements. Rather than depending on a model of the vehicle state and environment to capture the distribution of possible sensor measurements, we provide an approximation that allows the sensor model to depend on the measurement itself. Building on previous work, we show how the sensor model predictor can be learned from data without access to ground truth labels of the vehicle state or true underlying distribution, and we show… Show more

We present an algorithm for providing a dynamic model of sensor measurements. Rather than depending on a model of the vehicle state and environment to capture the distribution of possible sensor measurements, we provide an approximation that allows the sensor model to depend on the measurement itself. Building on previous work, we show how the sensor model predictor can be learned from data without access to ground truth labels of the vehicle state or true underlying distribution, and we show our approach to be a generalization of non-parametric kernel regressors. Our algorithm is demonstrated in simulation and on real world data for both laser-based scan matching odometry and RGB-D camera odometry in an unknown map. The performance of our algorithm is shown to quantitatively improve estimation, both in terms of consistency and absolute accuracy, relative to other algorithms and to fixed covariance models. Show less