Article
Engineering, Electrical & Electronic
Hu Cheng, Yingying Wang, Max Q-H Meng
Summary: In this article, a novel deep model for robot grasp pose detection is proposed, which can generate grasp poses for unknown objects in unstructured environments. With the use of rotated bounding boxes and fully convolutional style generation, the model is able to generate a large number of grasps at the pixel level. Moreover, the detection accuracy is improved by extracting and combining low-level high-resolution features and high-level abstract features.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Robotics
Bin Hu, Xiaodong Zhang, Tianju Ding, Xisong Dong, Bidan Huang, Yu Zheng
Summary: The solution proposed in the letter successfully competed in the Robotic Grasping and Manipulation Competition, utilizing a new type of modular gripper design, machine vision, and force control techniques.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Robotics
Zichao Ji, Guangming Song, Fei Wang, Yawen Li, Aiguo Song
Summary: This letter introduces a snake robot with a gripper for inspection and maintenance in narrow spaces. The proposed robot has a gripper equipped with a camera and a laser distance sensor for inspection and object grasping. The control methods of the robot include a double-layer controller based on central pattern generator (CPG) for locomotion, a circular posture to improve the payload capacity, and a three-stage grasping strategy for semi-automatic grasping operations. A prototype of the robot has been developed and its effectiveness has been verified in various experiments.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Yuanhao Li, Yu Liu, Zhiqiang Ma, Panfeng Huang
Summary: In this article, a novel generative convolutional neural network model is proposed to improve the accuracy and robustness of robot grasp detection in real-world scenes. The method achieves excellent performance on the Cornell Grasping datasets and Jacquard datasets, and is put to the test in a real-world robot grasping scenario.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Automation & Control Systems
Hu Cheng, Yingying Wang, Max Q. -H. Meng
Summary: An intelligent robot grasping system is proposed, which utilizes a deep grasp detector designed for a robot equipped with a parallel gripper. The model consumes RGB or depth data and extracts features via a feature pyramid network. Multiple grasp prediction units are used to output grasp parameters without refining process, increasing the model's capability to predict different-size grasps. The system is evaluated on three datasets and validated in real-scene grasp experiments, showing superior performance compared to state-of-the-art methods.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Tomoki Anzai, Moju Zhao, Takuzumi Nishio, Fan Shi, Kei Okada, Masayuki Inaba
Summary: This study proposes a fully autonomous pick-and-place scheme in outdoor environments using articulated aerial robots. It develops an articulated robot model with an actively tiltable sensor and designs object detection methods based on the distance between the robot and target object. A comprehensive motion strategy is developed for autonomous object searching, picking, and placing. Experimental results show the successful autonomous brick picking and placing in various outdoor environments.
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2023)
Article
Computer Science, Information Systems
Inhyuk Baek, Kyoosik Shin, Hyunjun Kim, Seunghoon Hwang, Eric Demeester, Min-Sung Kang
Summary: The study focuses on objects suitable for power grasp, but direct power grasping is hindered due to the desired location being near the support surface. A pre-grasp manipulation planning method using two robot arms has been proposed to create space for power grasping by rotating the object while supported against the surface.
Article
Robotics
Gal Gorjup, Geng Gao, Anany Dwivedi, Minas Liarokapis
Summary: In response to the increasing demand for customized production, a flexible robotic assembly system has been developed. This system combines CAD based component localization, compliance control, and a multi-modal gripper for efficient programming of complex tasks. With a dedicated Graphical User Interface, the system can be easily configured for novel assemblies, showing high efficiency and effectiveness.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Automation & Control Systems
Dexin Wang, Chunsheng Liu, Faliang Chang, Nanjun Li, Guangxin Li
Summary: This article presents a pixel-level grasp detection method based on deep neural network, which achieves high accuracy and fast speed on RGB images through novel representation models, adaptive attribute models, and feature fusion and grasp-aware network.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Engineering, Electrical & Electronic
Hongkun Tian, Kechen Song, Song Li, Shuai Ma, Yunhui Yan
Summary: Grasping detection is crucial for robots to achieve automation and intelligence. This article proposes a pixel-wise RGB-D dense fusion method based on a generative strategy, which is experimentally validated and shown to have high accuracy and efficiency.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Hu Cao, Guang Chen, Zhijun Li, Yingbai Hu, Alois Knoll
Summary: The article introduces a new neuromorphic vision sensor and corresponding dataset, further developing a multimodal neural network for robotic grasping with better performance in grasp pose estimation.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Automation & Control Systems
Lu Chen, Panfeng Huang, Yuanhao Li, Zhongjie Meng
Summary: This article proposes an edge-based grasp detection strategy that combines low-level features and a lightweight CNN, introducing two grip criteria and rapidly training a model with limited samples to identify feasible grasps. The method does not require additional sensor information and can work well with only RGB images, outperforming existing grasp search strategies in accuracy and efficiency.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2021)
Article
Computer Science, Information Systems
Hsin-Han Chiang, Jiun-Kai You, Chen-Chien James Hsu, Jun Jo
Summary: This paper proposes an optimal grasping strategy for target objects with any poses, and experimental results demonstrate its superior performance.
Article
Robotics
Shaochen Wang, Zhangli Zhou, Zhen Kan
Summary: TF-Grasp is a transformer-based architecture for robotic grasp detection. It combines local and cross window attention mechanisms to capture both local and global information, and utilizes multi-scale feature fusion for improved accuracy. Experimental results demonstrate that TF-Grasp achieves competitive performance on different datasets and shows good grasp capability in real-world scenarios.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Automation & Control Systems
Riby Abraham Boby
Summary: This article proposes a new method for kinematic identification of an industrial robot using a monocular camera mounted on its end-effector. By measuring solely in 2-D image space, the need for 3-D poses input in this process is eliminated, allowing for estimation of parameter corrections in a single stage. The use of camera enables a combination of geometric and parametric techniques of identification, providing a well-defined experimental strategy and identification of externally defined coordinate frames.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Yongchen Guo, Bo Pan, Yanwen Sun, Guojun Niu, Yili Fu, Max Q. -H. Meng
Summary: This paper proposes a motion hysteresis compensation method for cable-driven mechanism, which leverages the relationship between actuate motor current and hysteresis phases to generate compensation curves. The method is shown to improve the accuracy and efficiency of compensation, and has potential applications in large-scale identification or repeated usage scenarios.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Ang Zhang, Zhe Min, Zhengyan Zhang, Xing Yang, Max Q-H Meng
Summary: This article presents a novel, robust, and accurate 3D rigid point set registration method that incorporates high-dimensional point set alignment and anisotropic positional noise into the Bayesian coherent point drift framework. The proposed method utilizes normal vectors to enhance robustness and accuracy, and guarantees theoretical convergence by incorporating registration into the framework.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Yingying Wang, Hu Cheng, Max Q-H Meng
Summary: In this paper, a novel hybrid neural network model, SC-HNN, is proposed for pose-invariant inertial odometry. The model utilizes both convolutional neural network (CNN) and long short-term memory (LSTM) recurrent neural network (RNN) to capture local and global features and incorporates attention mechanisms for better model representation. Experimental results demonstrate the effectiveness and superior generalization ability of the model.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Robotics
Kuanqi Cai, Weinan Chen, Chaoqun Wang, Hong Zhang, Max Q. -H. Meng
Summary: Mobile robots are increasingly used in large-scale and crowded environments, but localization in such settings is challenging due to sparse landmarks and crowd noise. Additionally, navigating safely while considering human comfort is unreliable. To address this problem, we propose a curiosity-based framework that considers human comfort and crowd density, localization uncertainty, and cost-to-go to the target. The framework involves three parts: distance assessment, Curiosity for Positive Content (CPC), and Curiosity for Negative Content (CNC). Evaluation in large-scale and crowded environments demonstrates that our method can find a feasible path that considers localization uncertainty and avoids crowded areas.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Automation & Control Systems
Kuanqi Cai, Weinan Chen, Chaoqun Wang, Shuang Song, Max Q. -H. Meng
Summary: In this paper, an integrated framework for finding the optimal path in complex environments is proposed, considering collision risk, social norms, and crowded areas. The framework includes a dynamic group model, a collision risk and human space model, and an improved navigation method. Experimental results demonstrate that this method can generate the optimal human-aware collision-free path in complex environments.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Erli Lyu, Tingting Liu, Jiaole Wang, Shuang Song, Max Q-H Meng
Summary: This paper proposes a points-guided sampling net (PGSN) that utilizes geometric information to guide the sampling process in a sampling-based motion planner. By extracting geometric features from point clouds, a VAE feature extraction net and a multi-modal sampling net are designed. Additionally, a sampling-based motion planning algorithm called PG-RRT is presented based on PGSN, and its effectiveness is demonstrated through experiments.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Robotics
Keyu Li, Yangxin Xu, Ziqi Zhao, Ang Li, Max Q. -H. Meng
Summary: This paper presents a closed-loop magnetic manipulation framework for robotic transesophageal echocardiography (TEE) acquisitions. The framework utilizes magnetic control methods for more direct, intuitive, and accurate manipulation of the probe. Extensive experiments validate the effectiveness of the framework in terms of localization accuracy, update rate, workspace size, and tracking accuracy.
IEEE TRANSACTIONS ON ROBOTICS
(2023)
Article
Automation & Control Systems
Fei Meng, Liangliang Chen, Han Ma, Jiankun Wang, Max Q. -H. Meng
Summary: Building a general and efficient path planning framework in uncertain nonconvex environments is challenging. Traditional methods involve convexifying obstacles and presuming Gaussian distribution, which are not universal. Our novel neural risk-bounded path planner quickly finds near-optimal solutions with acceptable collision probability in complex environments.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Robotics
Yongchen Guo, Bo Pan, Yili Fu, Max Q. -H. Meng
Summary: Learning-based grip force measurement methods in RAMIS outperform traditional model-based methods and avoid the issues of sensor-based approaches. However, there is limited research on grip force measurement in mass-produced surgical instruments. This letter proposes a novel learning-based method, ACAM-FoC, which considers the differences in motion hysteresis and mechanism friction among mass-produced surgical instruments.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Review
Engineering, Biomedical
Zhe Min, Ang Zhang, Zhengyan Zhang, Jiaole Wang, Shuang Song, Hongliang Ren, Max Q. -H. Meng
Summary: This paper provides a concise review of rigid point set registration methods in computer-assisted orthopedic surgery (CAOS). The challenge lies in establishing point correspondences between two point sets under noise, outliers, and partial overlapping. The paper discusses and compares the advantages and disadvantages of surveyed registration algorithms, and also proposes potential future research directions.
IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS
(2023)
Article
Automation & Control Systems
Chenming Li, Han Ma, Peng Xu, Jiankun Wang, Max Q. -H. Meng
Summary: Adaptively Informed Trees (AIT*) is an algorithm that improves performance by using a problem-specific heuristic to avoid unnecessary searches. However, AIT* consumes a lot of computational resources and its bidirectional searching strategy is not fully optimized. In this article, we propose an extension called BiAIT* which uses symmetrical bidirectional search for both the heuristic and space searching. BiAIT* outperforms state-of-the-art methods in finding the initial solution and updating the heuristic.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Hu Cheng, Yingying Wang, Max Q. -H. Meng
Summary: An intelligent robot grasping system is proposed, which utilizes a deep grasp detector designed for a robot equipped with a parallel gripper. The model consumes RGB or depth data and extracts features via a feature pyramid network. Multiple grasp prediction units are used to output grasp parameters without refining process, increasing the model's capability to predict different-size grasps. The system is evaluated on three datasets and validated in real-scene grasp experiments, showing superior performance compared to state-of-the-art methods.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Keyu Li, Ang Li, Yangxin Xu, Huahua Xiong, Max Q. -H. Meng
Summary: This paper presents RL-TEE, a learning-based solution to the 3-DOF control of a transesophageal echocardiography (TEE) probe based on ultrasound image feedback. The proposed method, utilizing reinforcement learning and a hybrid deep Q-network model, effectively guides the probe movement for TEE standard view acquisition tasks. The framework is validated in simulations with real patient data and shows good generalization to unseen patients.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Robotics
Yameng Zhang, Ao Xu, Yuhan Chen, Max Q. -H. Meng, Li Liu
Summary: This letter introduces an innovative framework for optical microscopy that utilizes auto-calibration and multi-scale visual servoing techniques to automatically reposition the microscope and observe high-magnification targets. Experimental results demonstrate the precision, stability, and robustness of the proposed methods.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Zhe Min, Ang Zhang, Delong Zhu, Jin Pan, Zhengyan Zhang, Max Q. -H. Meng
Summary: This article addresses the problem of registration of two-point sets (PSs) by formulating and solving the problem with consideration of both positional and normal error vectors. The proposed method utilizes multivariate Gaussian distribution and Kent distribution to model the error vectors, and solves the registration task through maximum likelihood estimation and expectation maximization technique. Experimental results demonstrate that the method achieves superior registration accuracy and robustness compared to state-of-the-art methods under noise and outliers.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)