A5091521146- Tactile and Sensory Interactions
- Advanced Sensor and Energy Harvesting Materials
- Robot Manipulation and Learning
- Soft Robotics and Applications
- Muscle activation and electromyography studies
- Modular Robots and Swarm Intelligence
- Reinforcement Learning in Robotics
- Domain Adaptation and Few-Shot Learning
- Interactive and Immersive Displays
- Multimodal Machine Learning Applications
- Conducting polymers and applications
- 3D Surveying and Cultural Heritage
- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
Tsinghua–Berkeley Shenzhen Institute
2022-2025
Tsinghua University
2023-2025
National University of Singapore
2024
King's College London
2024
Beijing University of Posts and Telecommunications
2024
Toronto Metropolitan University
2022
Shanghai University
2022
The grasping of transparent objects is challenging but significance to robots. In this article, a visual–tactile fusion framework for object in complex backgrounds proposed, which synergizes the advantages vision and touch, greatly improves efficiency objects. First, we propose multiscene synthetic dataset named SimTrans12 K together with Gaussian-mask annotation method. Next, based on TaTa gripper, network object-grasping convolutional neural position detection, shows good performance both...
Abstract With the development of artificial intelligence, stiffness sensors are extensively utilized in various fields, and their integration with robots for automated palpation has gained significant attention. This study presents a broad range self-powered sensor based on triboelectric nanogenerator (Stiff-TENG) variable inclusions soft objects detection. The Stiff-TENG employs stacked structure comprising an indium tin oxide film, elastic sponge, fluorinated ethylene propylene film...
Transparent objects are a common part of daily life, but their unique optical properties make estimating 6D pose challenging task. In this letter, we propose TGF-Net, monocular instance-level estimation method for transparent based on geometric fusion. TGF-Net learns the edge features and surface fragments as intermediate reduces influence appearance changes by fusing rich in network. Moreover, an approach generating high-fidelity large-scale synthetic datasets using Blender use to generate...
Intelligent robot is the ultimate goal in robotics field. Existing works leverage learning-based or optimization-based methods to accomplish human-defined tasks. However, challenge of enabling robots explore various environments autonomously remains unresolved. In this work, we propose a framework named GExp, which endows with capability exploring and learning without human intervention. To achieve goal, devise modules including self-exploration, knowledge-base-building, close-loop feedback...
Vibration perception is essential for robotic sensing and dynamic control. Nevertheless, due to the rigorous demand sensor conformability stretchability, enabling soft robots with proprioceptive vibration remains challenging. This paper proposes a novel liquid metal-based stretchable e-skin via kirigami-inspired design enable robot sensing. The fabricated into 0.1mm ultrathin thickness, ensuring its negligible influence on overall stiffness of robot. Moreover, working mechanism based...
Manual oropharyngeal (OP) swab sampling is an intensive and risky task. In this article, a novel OP device of low cost high compliance designed by combining the visuotactile sensor pneumatic actuator-based gripper. Here, concave called CoTac first proposed to address problems poor reliability traditional multi-axis force sensors. Besides, imitating doctor's fingers, soft actuator with rigid skeleton structure designed, which demonstrated be reliable safe via finite element modeling...
Intelligent robot is the ultimate goal in robotics field. Existing works leverage learning-based or optimization-based methods to accomplish human-defined tasks. However, challenge of enabling robots explore various environments autonomously remains unresolved. In this work, we propose a framework named GExp, which enables and learn without human intervention. To achieve goal, devise modules including self-exploration, knowledge-base-building, close-loop feedback based on foundation models....
Advancement in human-robot interaction (HRI) is essential for the development of intelligent robots, but there lack paradigms to integrate remote control and tactile sensing an ideal HRI. In this study, inspired by platypus beak sense, we propose a bionic electro-mechanosensory finger (EM-Finger) synergizing triboelectric visuotactile perception. A sensor array made patterned liquid-metal-polymer conductive (LMPC) layer encodes both touchless interactions with external objects into voltage...
The accurate detection and grasping of transparent objects are challenging but significance to robots. Here, a visual-tactile fusion framework for object under complex backgrounds variant light conditions is proposed, including the position detection, tactile calibration, based classification. First, multi-scene synthetic dataset generation method with Gaussian distribution data annotation proposed. Besides, novel network named TGCNN proposed showing good results in both real scenes. In...