no code implementations • 11 May 2021 • Fanfei Chen, Paul Szenher, Yewei Huang, Jinkun Wang, Tixiao Shan, Shi Bai, Brendan Englot
An agent can use domain knowledge provided by human experts to learn efficiently.
1 code implementation • 3 Mar 2021 • Tixiao Shan, Brendan Englot, Fabio Duarte, Carlo Ratti, Daniela Rus
We propose a methodology for robust, real-time place recognition using an imaging lidar, which yields image-quality high-resolution 3D point clouds.
1 code implementation • IEEE/RSJ International Conference on Intelligent Robots and Systems 2020 • Tixiao Shan, Brendan Englot, Drew Meyers, Wei Wang, Carlo Ratti, Daniela Rus
We propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building.
Robotics
1 code implementation • arXiv 2020 • Tixiao Shan, Jinkun Wang, Fanfei Chen, Paul Szenher, Brendan Englot
We propose a methodology for lidar super-resolution with ground vehicles driving on roadways, which relies completely on a driving simulator to enhance, via deep learning, the apparent resolution of a physical lidar.
Robotics Image and Video Processing
1 code implementation • 6 Jan 2019 • Fanfei Chen, Shi Bai, Tixiao Shan, Brendan Englot
Mapping and exploration of a priori unknown environments is a crucial capability for mobile robot autonomy.
1 code implementation • 1 Oct 2018 • Tixiao Shan, Brendan Englot
We propose a lightweight and ground-optimized lidar odometry and mapping method, LeGO-LOAM, for realtime six degree-of-freedom pose estimation with ground vehicles.