robotics

Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions

We propose a cross-modal contrastive learning for representation (CM-CLR) method that maximizes the agreement between mmWave radar data and LiDAR data in a deep reinforcement learning model. All pretrained models and hardware settings are open access for reproducing this study and can be obtained at https://arg-nctu.github.io/projects/deeprl-mmWave.html.

Xbee Wireless Mesh Network and Communication-aware Planning in Mobile Robot Exploration

Spring 2020 Undergraduate Project in NCTU

Uwb-based Positioning System Analysis and Applications in Mobile Robot Exploration

Fall 2019 Undergraduate Project in NCTU