Article
Engineering, Biomedical
Filip Suligoj, Christoff M. Heunis, Sumit Mohanty, Sarthak Misra
Summary: This study demonstrates the visualization of intravascular micro-agents using robotic ultrasound-based tracking and visual servoing in clinically-relevant scenarios. The developed machine vision algorithms are able to detect and track micro-agents inside blood vessels, and the real-time positions are used to guide the robot with the attached ultrasound probe. The experiments show promising results in anthropomorphic surfaces and simulation of physiological movement.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2022)
Article
Robotics
Ali AlBeladi, Evan Ripperger, Seth Hutchinson, Girish Krishnan
Summary: This study presents a hybrid eye-to-hand and eye-in-hand visual servoing (VS) scheme for tracking a desired object in the workspace of soft continuum arms (SCAs). When the target is not within the field-of-view of the tip camera, a wide field-of-view camera on the soft robot's base is used to move the soft robot's tip to a feasible region where the target can be seen by the tip camera. When the target is visible to the tip camera, the system switches to a hand-in-eye controller to keep the target in the desired image position.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Engineering, Aerospace
Guocai Yang, Junhong Ji, Yechao Liu, Songhao Piao
Summary: This article proposes a novel trajectory planning method for space manipulators that can generate trajectories in Cartesian space with continuous joint jerk. The key idea is to generate the corresponding joint trajectory in a control-like manner based on the desired position for an individual joint. The generated jerk acts as the output of the controller, driving an ideal third-order system to the desired position without the need for pre-set discrete points. The proposed method is effective in tracking targets with different types of motion, asymptotically tracking input-bounded signals.
ADVANCES IN SPACE RESEARCH
(2023)
Article
Robotics
Truman Cheng, Weibing Li, Wing Yin Ng, Yisen Huang, Jixiu Li, Calvin Sze Hang Ng, Philip Wai-yan Chiu, Zheng Li
Summary: The letter introduces the first case of implementing deep-learning based instrument tracking on a magnetic anchored surgical endoscope. By combining deep-learning instrument detection with visual servoing control, the magnetic endoscope can automatically track surgical tools without the need for color markers or instrument modification. The performance was verified through experiments and completing mock-up surgical tasks in a simulated thoracic cavity.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Robotics
Weibing Li, Wing Yin Ng, Xue Zhang, Yisen Huang, Yehui Li, Chengzhi Song, Philip Wai-Yan Chiu, Zheng Li
Summary: This study introduces a modular approach to analyze the kinematics of different robotic endoscopes and achieve automatic field-of-view adjustment. The integrated kinematics of a generic robotic endoscope is determined by combining the kinematics of modular elements. The experimental results demonstrate the effectiveness of this method.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Optics
Juuso Heikkinen, Gary S. Schajer
Summary: 2D Digital Image Correlation (2D DIC) and Defocused Speckle Imaging (DSI) are optical methods with complementary advantages and disadvantages in measuring object displacement. By combining the two methods simultaneously, it is possible to compensate for perspective errors and improve measurement accuracy.
OPTICS AND LASERS IN ENGINEERING
(2022)
Article
Automation & Control Systems
Andrew Razjigaev, Ajay Pandey, David Howard, Jonathan Roberts, Anjali Jaiprakash, Ross Crawford, Liao Wu
Summary: This study proposes a semiautonomous controller to assist teleoperation by steering a camera to keep a target in the center of the field of view, thus assisting in surveying different orientations about the target with image-based information. The proposed techniques are simulated and validated on the SnakeRaven robot, with successful operation achieved.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Robotics
Radian Gondokaryono, Mustafa Haiderbhai, Sai Aneesh Suryadevara, Lueder A. Kahrs
Summary: In this study, a vision-based reinforcement learning agent is implemented to investigate the problem of nonprehensile manipulation. Successful transfer of the agent from simulation to real environment is achieved.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Eder A. Rodriguez Martinez, Guillaume Caron, Claude Pegard, David Lara-Alabazares
Summary: The article presents a vision-based navigation system that utilizes an onboard camera for navigating and represents the scene with a set of images. Navigation in this system is considered as a concatenation of positioning tasks in the visual servoing scheme, with the novelty lying in the generation of images that compose the visual path from a preobtained scene model.
IEEE SENSORS JOURNAL
(2021)
Article
Chemistry, Analytical
Azarakhsh Keipour, Guilherme A. S. Pereira, Rogerio Bonatti, Rohit Garg, Puru Rastogi, Geetesh Dubey, Sebastian Scherer
Summary: This paper presents a method for autonomously landing a UAV on a moving vehicle. The method utilizes a visual servoing controller to approach the ground vehicle using velocity commands calculated in image space. It has shown the ability to approach and land on moving platforms in various environments and is the fastest among other available methods.
Article
Engineering, Mechanical
Guocai Yang, Junhong Ji, Jingyang Wei, Yingming Hao, Xu Han
Summary: A novel visual servoing method is proposed to capture a malfunctioning satellite's docking ring by two space manipulators. Structured light is used to estimate the ring's pose. To ensure security, capture target points are planned for both manipulators considering the chaser's orientation to eliminate collision risk. Temporally, synchronism is guaranteed by adding duration parameters. Experimental results show successful capture of a tumbling target, with eliminated collision risk and improved synchronism compared to existing methods.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE
(2023)
Article
Engineering, Biomedical
Lingbo Cheng, Mahdi Tavakoli
Summary: This paper proposes a teleoperation system for beating-heart surgery that utilizes impedance control and ultrasound image-based position control to achieve non-oscillatory force feedback and heart motion compensation. The system is validated through experiments, showing that the strategy with NN algorithm has significant advantages in synchronization accuracy and steady slave-heart contact force compared to other strategies.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Automation & Control Systems
Ning Han, Xuemei Ren, Dongdong Zheng
Summary: In recent years, the visual servoing control of robotics has been widely applied with the development of machine vision and other relative techniques. This article proposes a rectified linear unit (ReLU) activating neural network (NN) estimator to estimate the compound Jacobian matrix of the system. The weight of the NN is updated online by a project algorithm with a novel spectral adaptive law, improving the generalization ability of the NN and the robustness of the system. The stability of the proposed adaptive algorithm and controller is proven by constructing a new Lyapunov function with the spectral norm of the NN weight. Simulations and experimental results validate the effectiveness of the proposed controller.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Engineering, Biomedical
Jiayi Zhou, Norihiro Koizumi, Yu Nishiyama, Kiminao Kogiso, Tomohiro Ishikawa, Kento Kobayashi, Yusuke Watanabe, Takumi Fujibayashi, Miyu Yamada, Momoko Matsuyama, Hiroyuki Tsukihara, Ryosuke Tsumura, Kiyoshi Yoshinaka, Naoki Matsumoto, Masahiro Ogawa, Hideyo Miyazaki, Kazushi Numata, Hidetoshi Nagaoka, Toshiyuki Iwai, Hideyuki Iijima
Summary: This study developed an ultrasound diagnostic robot that works in cooperation with a visual servo system based on deep learning, aiming to alleviate the burdens on physicians. Different image processing methods were used to detect kidney location and evaluate the appropriateness of ultrasound images. The experiments showed that Kalman filtering improved the tracking rate and appropriateness probability of the images.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2023)
Article
Automation & Control Systems
Antonio Paolillo, Marco Forgione, Dario Piga, Enrico Mingo Hoffman
Summary: In this work, a control architecture is proposed to enhance visual servoing with a predictive behavior while maintaining the fast execution of the original reactive controller. A reference governor, implemented as a model predictive control, acts as an outer loop running at a relatively low frequency over the original visual servoing loop. The proposed approach has been validated through simulations and experiments on various robotic systems.
CONTROL ENGINEERING PRACTICE
(2023)