7 papers · 1 filter
Multimodal Adversarial Quality Policy for Safe Grasping
Kunlin Xie, Chenghao Li, Haolan Zhang +1
Vision-guided robot grasping based on Deep Neural Networks (DNNs) generalizes well but poses safety risks in the Human-Robot Interaction (HRI). Recent works solved it by designing…
IL-SLAM: Intelligent Line-assisted SLAM Based on Feature Awareness for Dynamic Environments
Haolan Zhang, Thanh Nguyen Canh, Chenghao Li +3
Visual Simultaneous Localization and Mapping (SLAM) plays a crucial role in autonomous systems. Traditional SLAM methods, based on static environment assumptions, struggle to handl…
SR-SLAM: Scene-reliability Based RGB-D SLAM in Diverse Environments
Haolan Zhang, Chenghao Li, Thanh Nguyen Canh +2
Visual simultaneous localization and mapping (SLAM) plays a critical role in autonomous robotic systems, especially where accurate and reliable measurements are essential for navig…
Adaptive Prior Scene-Object SLAM for Dynamic Environments
Haolan Zhang, Thanh Nguyen Canh, Chenghao Li +1
Visual Simultaneous Localization and Mapping (SLAM) plays a vital role in real-time localization for autonomous systems. However, traditional SLAM methods, which assume a static en…
Quality-focused Active Adversarial Policy for Safe Grasping in Human-Robot Interaction
Chenghao Li, Razvan Beuran, Nak Young Chong
Vision-guided robot grasping methods based on Deep Neural Networks (DNNs) have achieved remarkable success in handling unknown objects, attributable to their powerful generalizabil…
Pyramid-Monozone Synergistic Grasping Policy in Dense Clutter
Chenghao Li, Nak Young Chong
Grasping a diverse range of novel objects in dense clutter poses a great challenge to robotic automation mainly due to the occlusion problem. In this work, we propose the Pyramid-M…