Review
Robotics
Vishnu Rajendran, Bappaditya Debnath, Sariah Mghames, Willow Mandil, Soran Parsa, Simon Parsons, Amir Ghalamzan-E.
Summary: This paper provides an overview of the current state-of-the-art in selective harvesting robots (SHRs) and their potential for addressing the challenges of global food production. It discusses the main components of SHRs, the challenges in developing SHR technologies, and the potential benefits of integrating artificial intelligence and soft robots. The paper also identifies open research questions in the field and highlights the need for further research and development efforts to advance SHR technologies.
JOURNAL OF FIELD ROBOTICS
(2023)
Article
Engineering, Mechanical
Divyansh Khare, Sandra Cherussery, Santhakumar Mohan
Summary: This paper focuses on the mechanical design and control aspects of a new autonomous mobile agricultural robot developed for automated harvesting of fruits in plantations. It discusses the need for automated harvesting and the challenges involved, conceptualizes the design of the robot, and gives a brief overview of its control aspects.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE
(2022)
Article
Robotics
Kaixiang Zhang, Kyle Lammers, Pengyu Chu, Zhaojian Li, Renfu Lu
Summary: The decrease in labor availability and increase in cost are threatening the long-term profitability and sustainability of the apple industry. This paper presents the design and evaluation of a new apple harvesting robot, which consists of perception, manipulator, end-effector, and dropping/catching components. Software algorithms enable efficient and automated harvesting by coordinating these hardware components. Field tests in different orchards showed successful harvesting rates of 82.4% and 65.2% with an average cycle time of 6 seconds per fruit.
JOURNAL OF FIELD ROBOTICS
(2023)
Article
Agriculture, Multidisciplinary
Wei Ji, Chencheng Tang, Bo Xu, Guozhi He
Summary: This paper proposes a variable damping impedance control strategy for gripper grasping force tracking, aiming to realize compliant grasping of apple harvesting robot. By establishing a contact force model, the dynamic tracking of grasping force is achieved. The simulation and experimental results demonstrate that the variable damping impedance control outperforms traditional impedance control in terms of smoother tracking effect and improved dynamic performance.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Agriculture, Multidisciplinary
Tao Li, Feng Xie, Zhuoqun Zhao, Hui Zhao, Xin Guo, Qingchun Feng
Summary: Robot harvesting is urgently needed in the apple industry due to a decline in agricultural labor. The use of multiple robotic arms in harvesting robots has gained attention for improving efficiency. However, the efficiency and accuracy of fruit positioning hinder the widespread application of multi-arm harvesting robots in orchard production. This paper proposes a multi-arm apple harvesting robot system that focuses on precise perception and multi-arm collaborative control. It introduces a hardware and software integration method, a fruit recognition and localization algorithm, and a task planning method to optimize collaboration efficiency. Field experiments in orchards validate the effectiveness of the robot and its methods.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Engineering, Electrical & Electronic
Rogelio de Jesus Portillo-Velez, Ivan Andres Burgos-Castro, Jose Alejandro Vasquez-Santacruz, Luis Felipe Marin-Urias
Summary: A conceptual design of a Delta robot is developed using a mechatronic design methodology. The Model Based Systems Engineering (MBSE) paradigm and SysML language are employed to present an integrated conceptual design, clarifying the recurrence of the design process. Multiple design proposals are evaluated using the non-linear Choquet integral, and a nonlinear constrained optimization problem is solved to determine the structural parameters for the Delta robot. A software framework incorporating a genetic algorithm and Monte Carlo method is used to automate the decision making and optimization process, resulting in an optimized conceptual design rendered in CAD software and a physical prototype.
Article
Robotics
Qiang Li, Yunjun Xu
Summary: This paper introduces a vision-based controller for improving the row transition performance of an agricultural robot in a strawberry field. The controller utilizes only RGB cameras for navigation and row alignment, and features a real-time adaptive dynamic programming algorithm for optimal row transition. The proposed controller shows promising results in simulations and field experiments, achieving efficient row transition with a minimal alignment error.
JOURNAL OF FIELD ROBOTICS
(2022)
Article
Computer Science, Hardware & Architecture
Xiaojun Yu, Zeming Fan, Xingduo Wang, Hao Wan, Pengbo Wang, Xilei Zeng, Feng Jia
Summary: This paper introduces an autonomous humanoid robot called LABOR for apple harvesting. Experimental results show high success rates for apple recognition and harvesting functions, with an average apple harvesting time of approximately 14.6 seconds.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Ruilong Gao, Qiaojun Zhou, Songxiao Cao, Qing Jiang
Summary: This paper proposes an apple-picking robot picking path planning algorithm based on the improved PSO to solve the problem of robot collisions with obstacles during picking. The algorithm extracts the fruit and surrounding branches from the 3D point cloud data, calculates the picking direction, establishes a spatial model of obstacles, and uses an improved PSO algorithm to plan the obstacle avoidance trajectory. Experimental results show that the improved PSO has faster convergence speed and the proposed method improves fruit-picking success rate to 85.93% and reduces the picking cycle to 12 s.
Article
Automation & Control Systems
Tom Staessens, Tom Lefebvre, Guillaume Crevecoeur
Summary: In this article, a simple, practical, and intuitive approach using deep reinforcement learning to improve the performance of a conventional controller in uncertain environments is proposed. To ensure safe operation, the methodology follows a residual learning methodology, where reinforcement learning algorithm learns corrective adaptations to a base controller's output. The stability of the method is proven using Lyapunov stability theory.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Agronomy
Takuya Otani, Akira Itoh, Hideki Mizukami, Masatsugu Murakami, Shunya Yoshida, Kota Terae, Taiga Tanaka, Koki Masaya, Shuntaro Aotake, Masatoshi Funabashi, Atsuo Takanishi
Summary: Currently, the agricultural method of Synecoculture (TM) is gaining attention for its ability to produce multiple crops and restore the environment. To improve efficiency in this method, a robot has been developed that can sow, prune, and harvest in dense and diverse vegetation that grows under solar panels. The robot has a four-wheel mechanism for uneven terrains and a two orthogonal axes mechanism for adjusting tool positioning. In field experiments, the robot successfully maneuvered on slopes, overcame obstacles, and performed harvesting and weeding tasks.
Article
Automation & Control Systems
Chuxiong Hu, Ran Zhou, Ze Wang, Yu Zhu, Masayoshi Tomizuka
Summary: This paper proposes a novel real-time iterative compensation (RIC) control framework for achieving excellent tracking performance in precision motion systems. By accurately predicting tracking errors and applying real-time iterative compensation, the RIC method overcomes the limitations of offline feedforward compensation strategies and achieves high tracking accuracy comparable to or even better than ILC, along with strong robustness.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Automation & Control Systems
Tong Yang, Ning Sun, He Chen, Yongchun Fang
Summary: This article proposes an adaptive tracking controller for underactuated mechatronic systems, aiming to achieve accurate positioning/tracking control while minimizing control effort. By developing an auxiliary compensation term and a robust term, the proposed controller ensures convergence of both actuated and unactuated variables. The controller also incorporates an online approximation of the performance index function, making the stability analysis process more concise.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Engineering, Multidisciplinary
Elio Matteo Curcio, Giuseppe Carbone
Summary: This paper discusses the design of a novel bionic robotic device for upper limb rehabilitation tasks at home. The device aims to be easily portable and remotely managed by a professional therapist, allowing treatment in hard-to-reach regions with cost reduction, and potentially enabling rehabilitation treatments while maintaining social distancing during a pandemic.
JOURNAL OF BIONIC ENGINEERING
(2021)
Article
Engineering, Multidisciplinary
M. H. Korayem, R. Vosoughi, V. Vahidifar
Summary: This study aims to improve the performance of minimally invasive surgeries by remotely controlling laparoscopic devices, so that more patients can have access to skilled surgeons beyond geographical limitations. The study uses a Leap Motion controller to acquire the fine movements of the surgeons' hands and utilizes a 5-DOF robot to control the laparoscopic grasper.
Article
Automation & Control Systems
Kaixiang Zhang, Jian Chen, Yang Li, Xinfang Zhang
IEEE TRANSACTIONS ON CYBERNETICS
(2020)
Article
Automation & Control Systems
Xinfang Zhang, Yanyan Gao, Jian Chen, Kaixiang Zhang
Summary: This paper proposes a 2-point algorithm to estimate the relative pose and absolute scale between two vehicle-mounted cameras efficiently. The algorithm can handle pure rotation scenes and recover absolute scale under certain conditions. By utilizing 2-point correspondences, the algorithm requires less iterations compared to many existing related algorithms, and outperforms them in cases with sharp corners in the camera's trajectory.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Pengyu Chu, Zhaojian Li, Kyle Lammers, Renfu Lu, Xiaoming Liu
Summary: Researchers have developed a novel deep learning-based apple detection framework called Suppression Mask R-CNN, which achieves high detection accuracy and efficiency in complex orchard environments. By collecting a comprehensive apple orchard dataset using a color camera under different lighting conditions, the framework is able to achieve a detection time of 0.25 seconds per frame and an F1 score of 0.905 on a standard desktop computer, outperforming state-of-the-art models.
PATTERN RECOGNITION LETTERS
(2021)
Article
Automation & Control Systems
Kaian Chen, Kaixiang Zhang, Zhaojian Li, Yan Wang, Kai Wu, Uros Kalabi
Summary: This paper presents an efficient stochastic model predictive control framework for nonlinear systems, featuring a composition of LTI models with scheduling variables obtained through system identification. The framework can be transformed into a tube-based MPC optimization problem, efficiently handled through a series of QP problems.
JOURNAL OF DYNAMIC SYSTEMS MEASUREMENT AND CONTROL-TRANSACTIONS OF THE ASME
(2022)
Article
Automation & Control Systems
Kaixiang Zhang, Jian Chen, Guoqing Yu, Xinfang Zhang, Zhaojian Li
Summary: This article discusses the eye-in-hand visual trajectory tracking control problem of wheeled mobile robots (WMRs) and proposes a combined observation/control strategy with a concurrent learning observer and a nonlinear controller to achieve the tracking task. The stability of the closed-loop system is analyzed using Lyapunov methods, demonstrating the effectiveness of the developed approach through simulation and experimental results.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Automation & Control Systems
Kaixiang Zhang, Zhaojian Li, Yongqiang Wang, Ali Louati, Jian Chen
Summary: This paper presents a state decomposition-based privacy preservation scheme to protect the privacy of agents in a decentralized control/estimation framework. The proposed scheme preserves the convergence of average consensus while protecting the agents' privacy. It is applied to the formation control of multiple mobile robots, and its effectiveness is demonstrated through numerical simulation.
Article
Engineering, Civil
Qi Wang, Jian Chen, Jianqiang Deng, Xinfang Zhang, Kaixiang Zhang
Summary: This paper proposes a LiDAR-based estimation method to simultaneously identify the pose and velocity information of an ego vehicle and its surrounding moving obstacles. The method utilizes a neural network to extract point cloud features, analyze static and moving parts, and estimate the poses of the ego vehicle and obstacles.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Automation & Control Systems
Xinfang Zhang, Jian Chen, Zhongle Wu, Lalitesh Kumar, Kaixiang Zhang
Summary: This paper investigates a class of nonlinear systems with multiple time-varying delays and additional disturbances. An observer-based output-feedback controller is designed to achieve uniformly ultimately bounded tracking. The controller utilizes a high-gain-like observer to estimate the unmeasurable current states and employs saturated control input to avoid adverse effects. The stability analysis and simulation results demonstrate the effectiveness of the proposed controller.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2022)
Article
Automation & Control Systems
Kaixiang Zhang, Zhaojian Li, Xiang Yin, Liang Han
Summary: In this article, a hierarchical, decentralized, and auction-based resource allocation model for cloud-enabled automotive vehicles is proposed to improve safety and drivability. Cloud-enabled vehicles bid for resources at a high level and perform onboard resource optimization at a low level. Numerical simulations demonstrate the efficacy of the proposed framework.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Kaixiang Zhang, Kaian Chen, Zhaojian Li, Yang Zheng
Summary: This paper proposes a privacy-preserving data-driven predictive control scheme for cooperative cruise control of connected and automated vehicles in a mixed traffic environment. By developing an affine masking-based privacy protection method and deriving an extended form of the data-enabled predictive control, the privacy of CAVs can be protected without affecting the control performance.
2022 IEEE 25TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)
(2022)
Proceedings Paper
Automation & Control Systems
Amin Vahidi-Moghaddam, Zhaojian Li, Nan Li, Kaixiang Zhang, Yan Wang
Summary: The paper presents a cloud-based nonlinear model predictive control (NMPC) framework, which performs the control on the cloud platform to save computational power. The open-loop control sequence is updated using the neighboring extremal method, and an event-triggered scheme is developed to balance performance and cost.
2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC)
(2022)
Proceedings Paper
Automation & Control Systems
Kaixiang Zhang, Kyle Lammers, Pengyu Chu, Nathan Dickinson, Zhaojian Li, Renfu Lu
Summary: This paper presents a system overview and algorithm design of a recently developed robotic apple harvester prototype. It covers key methods and advancements in multi-view fruit detection and localization, unified picking and dropping planning, and dexterous manipulation control. Indoor and field experiments show a significant improvement in picking rate, achieving an average of 3.6 seconds per apple.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
Article
Agricultural Engineering
Renfu Lu, Nathan Dickinson, Kyle Lammers, Kaixiang Zhang, Pengyu Chu, Zhaojian Li
Summary: The end effector is crucial in the fruit harvesting system operated by a robotic apple harvesting system. The original thin foam end effector was unable to adapt to different fruit sizes, hindering its picking performance. Therefore, this study aimed to develop new end effectors to enhance the robot's fruit picking performance. Three new silicone-based end effectors of different geometries were designed and evaluated, and they outperformed the original end effector in various performance metrics.
JOURNAL OF THE ASABE
(2022)
Article
Automation & Control Systems
Ran Jiao, Wenjie Liu, Ramy Rashad, Jianfeng Li, Mingjie Dong, Stefano Stramigioli
Summary: A novel end-effector bilateral rehabilitation robotic system (EBReRS) is developed for upper limb rehabilitation of patients with hemiplegia, providing simulations of multiple bimanual coordinated training modes, showing potential for application in home rehabilitation.
Article
Automation & Control Systems
Qiaosheng Pan, Yifang Zhang, Xiaozhu Chen, Quan Wang, Qiangxian Huang
Summary: A resonant piezoelectric rotary motor using parallel moving gears mechanism has been proposed and tested, showing high power output and efficiency.