Placeholder image
Placeholder image


WUT? - A Wrapper for Uncertainty in Tensorflow
Various approximate (Bayesian) inference techniques for estimating both epistemic and aleatoric uncertainty in deep neural networks implemented in eras and TensorFlow (to be officially released in end of May).
BHM: Bayesian Hilbert Maps
Online continuous occupancy mapping with epistemic uncertainty (Numpy and PyTorch)
SimpleLidar: a Simple LIDAR Simulator for Dynamic Environments
A simple 2D LIDAR simulator for dynamic environments. We can define static/moving objects and specify/draw the robot's path on a GUI. The simulator outputs 2D pointcloud data coming from a LIDAR. (Python)
ABHM: Automorphing Bayesian Hilbert Maps
Learning nonstationarity in Bayesian Hilbert maps (TensorFlow and Edward)
BBQ: Black-Box Quantiles
Learning arbitrary RKHS kernels (Python)
POT: Parameter Optimal Transport
Online domain adaptation for occupancy mapping using Optimal Transport (Python)
SpaTUn: Spatio-Temporal Uncertainty
Modeling spatiotemporal epistemic uncertainty with various likelihood models (PyTorch)
AgIS: Agile Information Seeker
Robot exploration using scalable uncertainty maps (PyTorch)