TAS LAB Trustworthy AI and Autonomous Systems Laboratory

Dataset & Code

We are committed to open science and reproducible research. Below are the open-source tools, software packages, and datasets developed by TAS Lab. All repositories are publicly available on GitHub.

2026 (1)

TasFusion
TasFusion

2025 (7)

TDL-GNSS
TDL-GNSS

A tightly coupled deep learning framework for GNSS.

TC-VIML
TC-VIML

Tightly-coupled Visual/Inertial/Map Integration with Observability Analysis for Reliable Localization of Intelligent Vehicles

TASGNSS

A simple python GNSS interface for positioning.

pyrtklib

Unleash all the performance of the most popular GNSS library – RTKLIB in python. A python binding for RTKLIB provides full functions.

SafetyQuantifiable-PLVINS
SafetyQuantifiable-PLVINS

Safety-quantifiable Line Feature-based Monocular Visual Localization with 3D Prior Map

KLT Dataset
KLT Dataset

The KLT dataset is a light urban scenario dataset with LOS/NLOS label

Semantic-Vector HD Map
Semantic-Vector HD Map

This is a pipeline to construct HD Semantic Map and HD Vector Map.