Author name cluster

Na Dong

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

IROS Conference 2025 Conference Paper

Advancing Robot Interaction Safety: A Teleoperated Shared-Control Approach Using a Lightweight Force-Feedback Exoskeleton

Ruohan Wang
Guangwei Zhang
Zhengjie Zhu
Honghao Lyu
Xiaoyan Huang
Na Dong
Lipeng Chen
M. Jamal Deen

Tele-homecare has become a promising approach to meet the growing demand for elderly and disability care. In such a context, ensuring human-robot interaction safety during teleoperation poses a critical challenge. Existing teleoperation control approaches focus solely on the robot’s end-effector trajectory, failing to handle inevitable or even desirable contacts on other robot links. This paper proposes a teleoperated shared-control strategy to deal with this challenge. A lightweight exoskeleton is developed to teleoperate the robot and give force feedback to the operator. Additionally, an exoskeleton-based shared-control strategy is proposed to integrate operator commands with real-time proximity sensing information, allowing the robot to avoid collisions while executing tasks. To react to inevitable contact, the force feedback function is incorporated into the proposed strategy to enable the operator to experience intuitive contact. Comparative experiments and a demonstration are designed to evaluate the feasibility and reliability of the proposed strategy in a tele-homecare scenario. Compared to the traditional teleoperation strategy, the proposed method can greatly reduce the contact forces on the robot’s links, indicating the potential of the proposed strategy in advancing safety in tele-homecare systems.

Details

AAAI Conference 2023 Conference Paper

Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning

Na Dong
Yongqiang Zhang
Mingli Ding
Gim Hee Lee

Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object detection that rely on the availability of abundant training samples per novel class that substantially limits the scalability to real-world setting where novel data can be scarce. In this paper, we propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector. To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision from additional object proposals generated using Selective Search as pseudo labels. We further introduce an incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without forgetting the base classes. Extensive experiments conducted on standard incremental object detection and incremental few-shot object detection settings show that our approach significantly outperforms state-of-the-art methods by a large margin. Our source code is available at https://github.com/dongnana777/Incremental-DETR.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection

Na Dong
Yongqiang Zhang
Mingli Ding
Gim Hee Lee

Deep networks have shown remarkable results in the task of object detection. However, their performance suffers critical drops when they are subsequently trained on novel classes without any sample from the base classes originally used to train the model. This phenomenon is known as catastrophic forgetting. Recently, several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection. Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novel classes. This requirement is impractical in many real-world settings since the base classes do not necessarily co-occur with the novel classes. In view of this limitation, we consider a more practical setting of complete absence of co-occurrence of the base and novel classes for the object detection task. We propose the use of unlabeled in-the-wild data to bridge the non co-occurrence caused by the missing base classes during the training of additional novel classes. To this end, we introduce a blind sampling strategy based on the responses of the base-class model and pre-trained novel-class model to select a smaller relevant dataset from the large in-the-wild dataset for incremental learning. We then design a dual-teacher distillation framework to transfer the knowledge distilled from the base- and novel-class teacher models to the student model using the sampled in-the-wild data. Experimental results on the PASCAL VOC and MS COCO datasets show that our proposed method significantly outperforms other state-of-the-art class-incremental object detection methods when there is no co-occurrence between the base and novel classes during training.

PDF Details

IS Journal 2019 Journal Article

Noncooperative Target Detection of Spacecraft Objects Based on Artificial Bee Colony Algorithm

Xinyu Liu
Donghui Li
Na Dong
Wai Hung Ip
Kai Leung Yung

Although heuristic algorithms have achieved the state-of-the-art performance for object detection, they have not been demonstrated to be sufficiently accurate and robust for multiobject detection. To address this problem, this article incorporates the concept of species into the artificial bee colony algorithm and proposes a multipeak optimization algorithm named species-based artificial bee colony (SABC). Then, we apply SABC to detect the noncooperative target (NCT) from two aspects: Multicircle detection and multitemplate matching. Experiments are conducted using real cases of “ShenZhou8” and “Apollo 9” space missions as well as the “Chang'e” camera point system developed by the Hong Kong Polytechnic University. Experimental results show that the proposed method is robust to detect NCT under various kinds of noise, weak light, and in-orbit and leads to accurate detection results with less time than other methods.

Details DOI