5 citations · 7 across the 7 of their papers we have counts for
9 papers
EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion
Lucas Berry, Axel Brando, Wei-Di Chang +2
Large text-to-image diffusion models rarely expose reliable signals of when a prompt is likely to produce a poorly aligned generation, especially when training data is undisclosed.…
IL-flOw: Imitation Learning from Observation using Normalizing Flows
Wei-Di Chang, Juan Camilo Gamboa Higuera, Scott Fujimoto +2
We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only. Our approach decouples reward modelling from policy learning, unlike state-of-…
Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles
Travis Manderson, Juan Camilo Gamboa Higuera, Stefan Wapnick +4
We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot…
One-Shot Informed Robotic Visual Search in the Wild
Karim Koreitem, Florian Shkurti, Travis Manderson +3
We consider the task of underwater robot navigation for the purpose of collecting scientifically relevant video data for environmental monitoring. The majority of field robots that…
Optimizing Through Learned Errors for Accurate Sports Field Registration
Wei Jiang, Juan Camilo Gamboa Higuera, Baptiste Angles +3
We propose an optimization-based framework to register sports field templates onto broadcast videos. For accurate registration we go beyond the prevalent feed-forward paradigm. Ins…
Learning Domain Randomization Distributions for Training Robust Locomotion Policies
Melissa Mozifian, Juan Camilo Gamboa Higuera, David Meger +1
Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policie…
Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks
Sanjay Thakur, Herke van Hoof, Juan Camilo Gamboa Higuera +2
Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from…
Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning
Juan Camilo Gamboa Higuera, David Meger, Gregory Dudek
We present an algorithm for rapidly learning controllers for robotics systems. The algorithm follows the model-based reinforcement learning paradigm, and improves upon existing alg…
Underwater Multi-Robot Convoying using Visual Tracking by Detection
Florian Shkurti, Wei-Di Chang, Peter Henderson +7
We present a robust multi-robot convoying approach that relies on visual detection of the leading agent, thus enabling target following in unstructured 3-D environments. Our method…