5 papers
MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
Open-set recognition refers to the problem in which classes that were not seen during training appear at inference time. This requires the ability to identify instances of novel cl…
Movement Primitives in Robotics: A Comprehensive Survey
Nolan B. Gutierrez, Joseph M. Cloud, William J. Beksi
Biological systems exhibit a continuous stream of movements, consisting of sequential segments, that allow them to perform complex tasks in a creative and versatile fashion. This o…
ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control
Lingling Chen, Zongyao Lyu, William J. Beksi
Vision-language-action (VLA) models have emerged as generalist robotic controllers capable of mapping visual observations and natural language instructions to continuous action seq…
UEOF: A Benchmark Dataset for Underwater Event-Based Optical Flow
Nick Truong, Pritam P. Karmokar, William J. Beksi
Underwater imaging is fundamentally challenging due to wavelength-dependent light attenuation, strong scattering from suspended particles, turbidity-induced blur, and non-uniform i…
Inertia-Informed Orientation Priors for Event-Based Optical Flow Estimation
Pritam P. Karmokar, William J. Beksi
Event cameras, by virtue of their working principle, directly encode motion within a scene. Many learning-based and model-based methods exist that estimate event-based optical flow…