Traversing terrain with good traction is crucial for achieving fast off-road navigation. Instead of manually designing costs based on terrain features, existing methods learn terrain properties directly from data via self-supervision to automatically penalize trajectories moving through undesirable terrain, but challenges remain in properly quantifying and mitigating the risk due to uncertainty in the learned models. To this end, we present evidential off-road autonomy (EVORA), a unified framework to learn uncertainty-aware traction model and plan risk-aware trajectories. For uncertainty quantification, we efficiently model both aleatoric and epistemic uncertainty by learning discrete traction distributions and probability densities of the traction predictor's latent features. Leveraging evidential deep learning, we parameterize Dirichlet distributions with the network outputs and propose a novel uncertainty-aware squared Earth Mover's Distance loss with a closed-form expression that improves learning accuracy and navigation performance. For risk-aware navigation, the proposed planner simulates state trajectories with the worst-case expected traction to handle aleatoric uncertainty and penalizes trajectories moving through terrain with high epistemic uncertainty. Our approach is extensively validated in simulation and on wheeled and quadruped robots, showing improved navigation performance compared to methods that assume no slip, assume the expected traction, or optimize for the worst-case expected cost.

This research to practice full paper presents the experience and evaluation of engaging students in a theoretical online signals and systems course through a set of application-oriented MATLAB lab exercises. Learning signals and systems concepts often poses challenges to students due to the abstract nature of the concepts and students' lack of prior experience. Many interventions have been proposed in the literature to address this issue with the goal of improving the student learning experience. The challenge is how to select/adapt these activities for use in a compact, accelerated online introductory signals and systems course, in which students have a wide range of prior experience and limited interactions with faculty and peer. Specifically, this paper will discuss how five MATLAB lab exercises were introduced to connect theory to practice. The impact of this addition was evaluated through student survey and grade analysis. Survey results showed that most students, regardless of course performance, enjoyed the labs. They acknowledged that the labs helped them solidify theory through practice and also helped them connect and apply signals and systems concepts to real world applications.

We propose robust methods for estimating camera egomotion in noisy, real-world monocular image sequences in the general case of unknown observer rotation and translation with two views and a small baseline. This is a difficult problem because of the nonconvex cost function of the perspective camera motion equation and because of non-Gaussian noise arising from noisy optical flow estimates and scene non-rigidity. To address this problem, we introduce the expected residual likelihood method (ERL), which estimates confidence weights for noisy optical flow data using likelihood distributions of the residuals of the flow field under a range of counterfactual model parameters. We show that ERL is effective at identifying outliers and recovering appropriate confidence weights in many settings. We compare ERL to a novel formulation of the perspective camera motion equation using a lifted kernel, a recently proposed optimization framework for joint parameter and confidence weight estimation with good empirical properties. We incorporate these strategies into a motion estimation pipeline that avoids falling into local minima. We find that ERL outperforms the lifted kernel method and baseline monocular egomotion estimation strategies on the challenging KITTI dataset, while adding almost no runtime cost over baseline egomotion methods.

This article consists of a collection of slides from the author's conference presentation on the special features, system design and architectures, processing capabilities, and targeted markets for Oracle's M7, the next generation SPARC family of products.