30 citations · 43 across the 13 of their papers we have counts for
14 papers
Hybrid Adaptive Kalman Filtering for Data-Efficient Joint Tracking and Classification
Jiho Lee, Nisar R. Ahmed, Rebecca Russell
Kalman filtering performance is highly sensitive to model mismatch and noise covariance tuning. Learning-based approaches address these limitations but typically rely on supervised…
Deep Modeling of Non-Gaussian Aleatoric Uncertainty
Aastha Acharya, Caleb Lee, Marissa D'Alonzo +3
Deep learning offers promising new ways to accurately model aleatoric uncertainty in robotic state estimation systems, particularly when the uncertainty distributions do not confor…
Wide-Area Geolocalization with a Limited Field of View Camera in Challenging Urban Environments
Lena M. Downes, Ted J. Steiner, Rebecca L. Russell +1
Cross-view geolocalization, a supplement or replacement for GPS, localizes an agent within a search area by matching ground-view images to overhead images. Significant progress has…
Surrogate Neural Networks for Efficient Simulation-based Trajectory Planning Optimization
Evelyn Ruff, Rebecca Russell, Matthew Stoeckle +2
This paper presents a novel methodology that uses surrogate models in the form of neural networks to reduce the computation time of simulation-based optimization of a reference tra…
Learning to Forecast Aleatoric and Epistemic Uncertainties over Long Horizon Trajectories
Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
Giving autonomous agents the ability to forecast their own outcomes and uncertainty will allow them to communicate their competencies and be used more safely. We accomplish this by…
Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representations
Marissa D'Alonzo, Rebecca Russell
Knowledge of the symmetries of reinforcement learning (RL) systems can be used to create compressed and semantically meaningful representations of a low-level state space. We prese…
Learning and Understanding a Disentangled Feature Representation for Hidden Parameters in Reinforcement Learning
Christopher Reale, Rebecca Russell
Hidden parameters are latent variables in reinforcement learning (RL) environments that are constant over the course of a trajectory. Understanding what, if any, hidden parameters…
Wide-Area Geolocalization with a Limited Field of View Camera
Lena M. Downes, Ted J. Steiner, Rebecca L. Russell +1
Cross-view geolocalization, a supplement or replacement for GPS, localizes an agent within a search area by matching images taken from a ground-view camera to overhead images taken…
Uncertainty Quantification for Competency Assessment of Autonomous Agents
Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
For safe and reliable deployment in the real world, autonomous agents must elicit appropriate levels of trust from human users. One method to build trust is to have agents assess a…
Competency Assessment for Autonomous Agents using Deep Generative Models
Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
For autonomous agents to act as trustworthy partners to human users, they must be able to reliably communicate their competency for the tasks they are asked to perform. Towards thi…
Explaining Conditions for Reinforcement Learning Behaviors from Real and Imagined Data
Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
The deployment of reinforcement learning (RL) in the real world comes with challenges in calibrating user trust and expectations. As a step toward developing RL systems that are ab…
Multivariate Uncertainty in Deep Learning
Rebecca L. Russell, Christopher Reale
Deep learning has the potential to dramatically impact navigation and tracking state estimation problems critical to autonomous vehicles and robotics. Measurement uncertainties in…
Real-Time Object Pose Estimation with Pose Interpreter Networks
Jimmy Wu, Bolei Zhou, Rebecca Russell +5
In this work, we introduce pose interpreter networks for 6-DoF object pose estimation. In contrast to other CNN-based approaches to pose estimation that require expensively annotat…
SegICP-DSR: Dense Semantic Scene Reconstruction and Registration
Jay M. Wong, Syler Wagner, Connor Lawson +8
To enable autonomous robotic manipulation in unstructured environments, we present SegICP-DSR, a real- time, dense, semantic scene reconstruction and pose estimation algorithm that…