Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

Efficient robotic task generalization using deep model fusion reinforcement learning

Published in 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2015

Learning-based methods have been used to program robotic tasks in recent years. However, extensive training is usually required not only for the initial task learning but also for generalizing the learned model to the same task but in different environments. In this paper, we propose a novel Deep Reinforcement Learning algorithm for efficient task generalization and environment adaptation in the robotic task learning problem. The proposed method is able to efficiently generalize the previously learned task by model fusion to solve the environment adaptation problem. The proposed Deep Model Fusion (DMF) method reuses and combines the previously trained model to improve the learning efficiency and results. Besides, we also introduce a Multi-objective Guided Reward (MGR) shaping technique to further improve training efficiency.

Robocodraw: Robotic avatar drawing with gan-based style transfer and time-efficient path optimization

Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2020

Robotic drawing has become increasingly popular as an entertainment and interactive tool. In this paper we present RoboCoDraw, a real-time collaborative robot-based drawing system that draws stylized human face sketches interactively in front of human users, by using the Generative Adversarial Network (GAN)-based style transfer and a Random-Key Genetic Algorithm (RKGA)-based path optimization.

Deep n-ary error correcting output codes

Published in MOBIMEDIA 2020: Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cyberspace, 2020

Ensemble learning consistently improves the performance of multi-class classification through aggregating a series of base classifiers. To this end, dataindependent ensemble methods like Error Correcting Output Codes (ECOC) attract increasing attention due to its easiness of implementation and parallelization. Specifically, traditional ECOCs and its general extension N-ary ECOC decompose the original multi-class classification problem into a series of independent simpler classification subproblems. Unfortunately, integrating ECOCs, especially N-ary ECOC with deep neural networks, termed as Deep N-ary ECOC, is not straightforward and yet fully exploited in the literature, due to the high expense of training base learners. To facilitate the training of N-ary ECOC with deep learning base learners, we further propose three different variants of parameter sharing architectures for deep N-ary ECOC. To verify the generalization ability of deep N-ary ECOC, we conduct experiments by varying the backbone with different deep neural network architectures for both image and text classification tasks. Furthermore, extensive ablation studies on deep N-ary ECOC show its superior performance over other deep data-independent ensemble methods.

End-to-end reinforcement learning of robotic manipulation with robust keypoints representation

Published in 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2022

We present an end-to-end Reinforcement Learning (RL) framework for robotic manipulation tasks, using a robust and efficient keypoints representation. The proposed method learns keypoints from camera images as the state representation, through a self-supervised autoencoder architecture. The key-points encode the geometric information, as well as the relationship of the tool and target in a compact representation to ensure efficient and robust learning. After keypoints learning, the RL step then learns the robot motion from the extracted keypoints state representation. The keypoints and RL learning processes are entirely done in the simulated environment. We demonstrate the effectiveness of the proposed method on robotic manipulation tasks including grasping and pushing, in different scenarios. We also investigate the generalization capability of the trained model

500kHz Bandwidth Feedback for Scanning Ion Conductance Microscopy With Nano-Resolution

Published in IEEE Transactions on Industrial Electronics, 2023

Scanning ion conductance microscopy (SICM) has been developing rapidly and has been a versatile tool for nanoscale imaging. However, the imaging quality and scanning speed of SICM have been significant restriction factors for its various applications. One of the main reasons is the mutual restriction of bandwidth and noise of the ion current feedback. Finite element method (FEM) was employed for the first time to simulate the pipette capacitance model.

The target region focused imaging method for scanning ion conductance microscopy

Published in Ultramicroscopy, 2023

Scanning ion conductance microscopy (SICM) has developed rapidly and has wide applications in biomedicine, single-cell science and other fields. SICM scanning speed is limited by the conventional raster-type scanning method, which spends most of time on imaging the substrate and does not focus enough on the target area. In order to solve this problem, a target region focused (TRF) method is proposed, which can effectively avoid the scanning of unnecessary substrate areas and enables SICM to image the target area only to achieve high-speed and effective local scanning. TRF method and conventional hopping mode scanning method are compared in the experiments using breast cancer cells and rat basophilic leukaemia cells as experimental materials.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015