home..

LiCS: Navigation using Learned-imitation on Cluttered Space

paper

Joshua Julian Damanik, Jae-Won Jung, Chala Adane Deresa, Han-Lim Choi

[Preprint] [Code]

LiCS was featured in BARN Challenge at ICRA 2024 as the first winner for both simulation and hardware categories. šŸ„‡

BARN Challenge


Abstract

In this letter, we propose a robust and fast navigation system in a narrow indoor environment for UGV (Unmanned Ground Vehicle) using 2D LiDAR and odometry. We used behavior cloning with Transformer neural network to learn the optimization-based baseline algorithm. We inject Gaussian noise during expert demonstration to increase the robustness of learned policy. We evaluate the performance of LiCS using both simulation and hardware experiments. It outperforms all other baselines in terms of navigation performance and can maintain its robust performance even on highly cluttered environments. During the hardware experiments, LiCS can maintain safe navigation at maximum speed of 1.5 m/s.

Highlights

LiCS architecture
Figure 1: Training pipeline diagram of the Learned-imitation on Cluttered Space model.

LiCS result
Figure 2: Comparative result with baseline algorithms.

© 2024 Joshua J. Damanik   ā€¢  Powered by Soopr   ā€¢  Theme  Moonwalk