Industrial Robot: the international journal of robotics research and application
ISSN : 0143-991X
Published by: Emerald (10.1108)
Total articles ≅ 4,477
Latest articles in this journal
Published: 16 September 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-02-2021-0030
Purpose This paper aims to develop a robust person tracking method for human following robots. The tracking system adopts the multimodal fusion results of millimeter wave (MMW) radars and monocular cameras for perception. A prototype of human following robot is developed and evaluated by using the proposed tracking system. Design/methodology/approach Limited by angular resolution, point clouds from MMW radars are too sparse to form features for human detection. Monocular cameras can provide semantic information for objects in view, but cannot provide spatial locations. Considering the complementarity of the two sensors, a sensor fusion algorithm based on multimodal data combination is proposed to identify and localize the target person under challenging conditions. In addition, a closed-loop controller is designed for the robot to follow the target person with expected distance. Findings A series of experiments under different circumstances are carried out to validate the fusion-based tracking method. Experimental results show that the average tracking errors are around 0.1 m. It is also found that the robot can handle different situations and overcome short-term interference, continually track and follow the target person. Originality/value This paper proposed a robust tracking system with the fusion of MMW radars and cameras. Interference such as occlusion and overlapping are well handled with the help of the velocity information from the radars. Compared to other state-of-the-art plans, the sensor fusion method is cost-effective and requires no additional tags with people. Its stable performance shows good application prospects in human following robots.
Published: 13 September 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-01-2021-0019
Purpose Conventional learning-based visual odometry (VO) systems usually use convolutional neural networks (CNN) to extract features, where some important context-related and attention-holding global features might be ignored. Without essential global features, VO system will be sensitive to various environmental perturbations. The purpose of this paper is to design a novel learning-based framework that aims to improve accuracy of learning-based VO without decreasing the generalization ability. Design/methodology/approach Instead of CNN, a context-gated convolution is adopted to build an end-to-end learning framework, which enables convolutional layers that dynamically capture representative local patterns and composes local features of interest under the guidance of global context. In addition, an attention mechanism module is introduced to further improve learning ability and enhance robustness and generalization ability of the VO system. Findings The proposed system is evaluated on the public data set KITTI and the self-collected data sets of our college building, where it shows competitive performance compared with some classical and state-of-the-art learning-based methods. Quantitative experimental results on the public data set KITTI show that compared with CNN-based VO methods, the average translational error and rotational error of all the test sequences are reduced by 45.63% and 37.22%, respectively. Originality/value The main contribution of this paper is that an end-to-end deep context gate convolutional VO system based on lightweight attention mechanism is proposed, which effectively improves the accuracy compared with other learning-based methods.
Published: 13 September 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-02-2021-0034
Purpose This paper aims to address the problem of integrating sensor feedback in robotized interior finishing operations. Its motivation is to finally realize automatic operations necessitating no human intervention. A vision-based approach is proposed for monitoring the execution status and changing the action accordingly. Design/methodology/approach First, a robotic system is proposed which can realize two typical interior finishing operations, namely, putty applying and wall sanding. Second, a new method based on a deep neural network is proposed to process the visual information capturing the execution status of the interior finishing operations. It helps to determine essential parameters on where should be processed and how to execute the corresponding operation. With the proposed method, vision information is embedded into the execution of interior finishing in a closed loop style. Findings The experiments demonstrate the feasibility of the proposal and reveal problems for further improvement of the autonomous interior finishing robot. Originality/value This provides an original insight into robotized interior finishing by addressing an attempt on integrating visual feedback into the manual process.
Published: 9 September 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-06-2021-0111
Purpose Laser absolute distance measurement has the characteristics of high precision, wide range and non-contact. In laser ranging system, tracking and aiming measurement point is the precondition of automatic measurement. To solve this problem, this paper aims to propose a novel method. Design/methodology/approach For the central point of the hollow angle coupled mirror, this paper proposes a method based on correlation filtering and ellipse fitting. For non-cooperative target points, this paper proposes an extraction method based on correlation filtering and feature matching. Finally, a visual tracking and aiming system was constructed by combining the two-axis turntable, and experiments were carried out. Findings The target tracking algorithm has an accuracy of 91.15% and a speed of 19.5 frames per second. The algorithm can adapt to the change of target scale and short-term occlusion. The mean error and standard deviation of the center point extraction of the hollow Angle coupling mirror are 0.20 and 0.09 mm. The mean error and standard deviation of feature points matching for non-cooperative target were 0.06 mm and 0.16 mm. The visual tracking and aiming system can track a target running at a speed of 0.7 m/s, aiming error mean is 1.74 pixels and standard deviation is 0.67 pixel. Originality/value The results show that this method can achieve fast and high precision target tracking and aiming and has great application value in laser ranging.
Published: 9 September 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-02-2021-0041
Purpose Robot automatic grasping has important application value in industrial applications. Recent works have explored on the performance of deep learning for robotic grasp detection. They usually use oriented anchor boxes (OABs) as detection prior and achieve better performance than previous works. However, the parameters of their loss belong to different coordinates, this may affect the regression accuracy. This paper aims to propose an oriented regression loss to solve the problem of inconsistency among the loss parameters. Design/methodology/approach In the oriented loss, the center coordinates errors between the ground truth grasp rectangle and the predicted grasp rectangle rotate to the vertical and horizontal of the OAB. And then the direction error is used as an orientation factor, combining with the errors of the rotated center coordinates, width and height of the predicted grasp rectangle. Findings The proposed oriented regression loss is evaluated on the YOLO-v3 framework to the grasp detection task. It yields state-of-the-art performance with an accuracy of 98.8% and a speed of 71 frames per second with GTX 1080Ti on Cornell datasets. Originality/value This paper proposes an oriented loss to improve the regression accuracy of deep learning for grasp detection. The authors apply the proposed deep grasp network to the visual servo intelligent crane. The experimental result indicates that the approach is accurate and robust enough for real-time grasping applications.
Published: 9 September 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-05-2021-0091
Purpose This paper aims to outline and implement a novel hybrid controller in humanoid robots to map an optimal path. The hybrid controller is designed using the Owl search algorithm (OSA) and Fuzzy logic. Design/methodology/approach The optimum steering angle (OS) is used to deal with the obstacle located in the workspace, which is the output of the hybrid OSA Fuzzy controller. It is obtained by feeding OSA's output, i.e. intermediate steering angle (IS), in fuzzy logic. It is obtained by supplying the distance of obstacles from all directions and target distance from the robot's present location. Findings The present research is based on the navigation of humanoid NAO in complicated workspaces. Therefore, various simulations are performed in a 3D simulator in different complicated workspaces. The validation of their outcomes is done using the various experiments in similar workspaces using the proposed controller. The comparison between their outcomes demonstrates an acceptable correlation. Ultimately, evaluating the proposed controller with another existing navigation approach indicates a significant improvement in performance. Originality/value A new framework is developed to guide humanoid NAO in complicated workspaces, which is hardly seen in the available literature. Inspection in simulation and experimental workspaces verifies the robustness of the designed navigational controller. Considering minimum error ranges and near collaboration, the findings from both frameworks are evaluated against each other in respect of specified navigational variables. Finally, concerning other present approaches, the designed controller is also examined, and major modifications in efficiency have been reported.
Published: 2 September 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-08-2021-0166
Purpose The purpose of this paper is to provide a “Q&A interview” conducted by Joanne Pransky of Industrial Robot Journal as a method to impart the combined technological, business and personal experience of a prominent, robotic industry engineer-turned entrepreneur regarding his pioneering efforts in starting robotic companies and commercializing technological inventions. The paper aims to discuss these issues. Design/methodology/approach The interviewee is Brennard Pierce, a world-class robotics designer and serial entrepreneur. Pierce is currently consulting in robotics after exiting from his latest startup as cofounder and chief robotics officer of Bear Robotics. Pierce discusses what led him to the field of robotics, the success of Bear Robotics, the challenges he’s faced and his future goals. Findings Pierce received a Bachelor of Science in computer science from Exeter University. He then founded his first startup, 5TWO, a custom software company. Always passionate about robotics as a hobby and now wanting to pursue the field professionally, he sold 5TWO to obtain a Master of Science, Robotics degree from the newly formed Bristol Robotics Lab (BRL) at Bristol University. After BRL, where he designed and built a biped robot that learned to walk using evolutionary algorithms, he joined the Robotics Research team at Carnegie Mellon University where he worked on a full-size humanoid robot for a large electronics company, designing and executing simple experiments for balancing. He then spent the next six years as a PhD candidate and robotics researcher at the Technical University Munich (TUM), Institute for Cognitive Science, where he built a compliant humanoid robot and a new generation of field programmable gate array-based robotic controllers. Afterwards, Pierce established the robotic startup Robotise in Munich to commercialize the omni-directional mobile platforms that he had developed at TUM. A couple of years later, Pierce left Robotise to cofound Bear Robotics, a Silicon Valley based company that brings autonomous robots to the restaurant industry. He remained at Bear Robotics for four years as chief robotics officer. He is presently a robotics consultant, waiting for post-COVID before beginning his next robotic startup. Originality/value Pierce is a seasoned roboticist and a successful entrepreneur. He has 15+ years’ of unique experience in both designing robotic hardware and writing low level embedded and high level cloud software. During his career he has founded three companies, managed small to middle sized interdisciplinary teams, and hired approximately 100 employees of all levels. Pierce’s robotic startup in Munich, Robotise, was solely based on his idea, design and implementation for an autonomous mobile delivery system. The third company he cofounded, Bear Robotics, successfully raised a $32m Series A funding lead by SoftBank. Bear Robotics is the recipient of the USA’s National Restaurant Association Kitchen Innovation Award; Fast Company’s World Changing Ideas Awards; and the Hospitality Innovation Planet 2020 Award.
Published: 26 August 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-06-2021-0112
Purpose The following paper is a “Q&A interview” conducted by Joanne Pransky of Industrial Robot Journal as a method to impart the combined technological, business and personal experience of a prominent, robotic industry PhD-turned innovator and entrepreneur regarding his pioneering efforts. The paper aims to discuss these issues. Design/methodology/approach The interviewee is Dr Homayoon Kazerooni, Professor of Mechanical Engineering at the University of California (UC) Berkeley, pioneer and leading entrepreneur of robotic exoskeletons. He is a foremost expert in robotics, control sciences, exoskeletons, bioengineering and mechatronics design. Kazerooni shares in this interview details on his second start-up, US Bionics DBA suitX. Findings Kazerooni received his MS and PhD in Mechanical Engineering from the Massachusetts Institute of Technology (MIT). He has been a Professor at UC Berkeley for over 30 years. He also serves as the Director of the Berkeley Robotics and Human Engineering Laboratory “KAZ LAB.” The lab’s early research focused on enhancing human upper extremity strength, and Kazerooni led his team to successfully develop a new class of intelligent assist devices that are currently marketed worldwide and used by manual laborers in distribution centers and factories worldwide. Dr Kazerooni’s later work focused on the control of human–machine systems specific to human lower extremities. After developing BLEEX, ExoHiker and ExoClimber – three load-carrying exoskeletons – his team at Berkeley created Human Universal Load Carrier. It was the first energetically autonomous, orthotic, lower extremity exoskeleton that allowed its user to carry 100-pound weights in various terrains for an extended period, without becoming physically overwhelmed. The technology was initially licensed to Ekso Bionics and then Lockheed Martin. Kazerooni and his team also developed lower-extremity technology to aid persons who have experienced a stroke, spinal cord injuries or have health conditions that obligate them to use a wheelchair. Originality/value In 2005, Kazerooni founded Ekso Bionics, the very first exoskeleton company in America, which went on to become a publicly owned company in 2014. Ekso, currently marketed by Ekso Bionics, was designed jointly between Ekso Bionics and Berkeley for paraplegics and those with mobility disorders to stand and walk with little physical exertion. In 2011, Austin Whitney, a Berkeley student suffering from lower limb paralysis, walked for commencement in one of Kazerooni’s exoskeletons, “The Austin Exoskeleton Project,” named in honor of Whitney. Kazerooni went on in 2011, to found US Bionics, DBA suitX, a venture capital, industry and government-funded robotics exoskeleton company. suitX’s core technology is focused on the design and manufacturing of affordable industrial and medical exoskeletons to improve the lives of workers and people with gait impairment. suitX has received investment from Wistron (Taiwan), been awarded several US government awards and won two Saint-Gobain NOVA Innovation Awards. suitX has also won the US$1m top prize in the “UAE AI and Robotics for Good” Competition. Its novel health-care exoskeleton Phoenix has recently received FDA approval. Kazerooni has won numerous awards including Discover magazine’s Technological Innovation Award, the McKnight-Land Grant Professorship and has been a recipient of the outstanding ASME Investigator Award. His research was recognized as the most innovative technology of the year in New York Times Magazine. He has served in a variety of leadership roles in the mechanical engineering community and served as editor of two journals: ASME Journal of Dynamics Systems and Control and IEEE Transaction on Mechatronics. Kazerooni has published more than 200 articles to date, delivered over 130 plenary lectures internationally and is the inventors of over 100 patents.
Published: 26 August 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-04-2021-0083
Purpose The purpose of this paper is to propose a novel jump control method based on Two Mass Spring Damp Inverted Pendulum (TMS-DIP) model, which makes the third generation of hydraulic driven wheel-legged robot prototype (WLR-3P) achieve stable jumping. Design/methodology/approach First, according to the configuration of the WLR, a TMS-DIP model is proposed to simplify the dynamic model of the robot. Then the jumping process is divided into four stages: thrust, ascent, descent and compression, and each stage is modeled and solved independently based on TMS-DIP model. Through WLR-3P kinematics, the trajectory of the upper and lower centroids of the TMS-DIP model can be mapped to the joint space of the robot. The corresponding control strategies are proposed for jumping height, landing buffer, jumping attitude and robotic balance, so as to realize the stable jump control of the WLR. Findings The TMS-DIP model proposed in this paper can simplify the WLR dynamic model and provide a simple and effective tool for the jumping trajectory planning of the robot. The proposed approach is suitable for hydraulic WLR jumping control. The performance of the proposed wheel-legged jump method was verified by experiments on WLR-3P. Originality/value This work provides an effective model (TMS-DIP) for the jump control of WLR-3P. The results showed that the number of landing shock (twice) and the pitch angle fluctuation range (0.44 rad) of center of mass of the jump control method based on TMS-DIP model are smaller than those based on spring-loaded inverted pendulum model. Therefore, the TMS-DIP model makes the jumping process of WLR more stable and gentler.
Published: 25 August 2021
Industrial Robot: the international journal of robotics research and application; https://doi.org/10.1108/ir-12-2020-0273
Purpose The purpose of this paper is to evaluate three categories of four-degrees of freedom (4-DOFs) upper limb rehabilitation exoskeleton mechanisms from the perspective of relative movement offsets between the upper limb and the exoskeleton, so as to provide reference for the selection of exoskeleton mechanism configurations. Design/methodology/approach According to the configuration synthesis and optimum principles of 4-DOFs upper limb exoskeleton mechanisms, three categories of exoskeletons compatible with upper limb were proposed. From the perspective of human exoskeleton closed chain, through reasonable decomposition and kinematic characteristics analysis of passive connective joints, the kinematic equations of three categories exoskeletons were established and inverse position solution method were addressed. Subsequently, three indexes, which can represent the relative movement offsets of human–exoskeleton were defined. Findings Based on the presented position solution and evaluation indexes, the joint displacements and relative movement offsets of the three exoskeletons during eating movement were compared, on which the kinematic characteristics were investigated. The results indicated that the second category of exoskeleton was more suitable for upper limb rehabilitation than the other two categories. Originality/value This paper has a certain reference value for the selection of the 4-DOFs upper extremity rehabilitation exoskeleton mechanism configurations. The selected exoskeleton can ensure the safety and comfort of stroke patients with upper limb dyskinesia during rehabilitation training.