Article
Automation & Control Systems
Wenzheng Zhao, Yinhua Liu, Yinan Wang, Xiaowei Yue
Summary: Many industrial robots are equipped in the multi-station autobody assembly line to collaboratively complete spot welding tasks. The task allocation and sequential planning of welding spots are two key sub-problems that significantly affect the efficiency of multi-station multi-robot coordination. This study proposes an integrated framework that considers complex engineering constraints to model the coordination process and optimizes it using an enhanced biased random key genetic algorithm (BRKGA).
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Robotics
Valentin N. Hartmann, Andreas Orthey, Danny Driess, Ozgur S. Oguz, Marc Toussaint
Summary: Robotic construction assembly planning is a parallelizable task and motion planning problem. We propose a planning system that parallelizes complex task and motion planning by solving smaller subproblems. By combining optimization methods and a sampling-based path planner, we can plan cooperative multi-robot manipulation with unknown arrival times. We demonstrate the robustness and scalability of this approach in multiple construction case studies and showcase the feasibility of executing the computed plans in the real world.
IEEE TRANSACTIONS ON ROBOTICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Niccolo Lucci, Andrea Monguzzi, Andrea Maria Zanchettin, Paolo Rocco
Summary: With the emergence of Industry 4.0, industries are required to offer customized products with numerous tailored features, which cannot be provided by a traditional robotic assembly line. This paper introduces a general library of atomic Predicates combined with first-order logic, allowing for the modeling of general industrial assembly processes in human-robot collaboration. These Predicates are mainly utilized to recognize human activities, enabling the modeling and supervision of workflows.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Computer Science, Interdisciplinary Applications
Zebang Zhang, Mozafar Saadat
Summary: This paper proposes a method for optimizing grasp poses for manipulating pipe assemblies in the manufacturing process. It formulates the problem as a constrained multi-objective optimization problem and uses an algorithm to iteratively improve solutions based on robot workspace reachability and collision avoidance. The method considers multiple inverse kinematics solutions and uses a graph search algorithm to find the optimal trajectory. Extensive benchmarks show that the proposed method achieves better overall results compared to other algorithms.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Automation & Control Systems
Andrea Casalino, Andrea Maria Zanchettin, Luigi Piroddi, Paolo Rocco
Summary: This article introduces a scheduling method for collaborative assembly tasks that optimally plans assembly activities and reduces idle time to improve manufacturing efficiency.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2021)
Article
Robotics
Shiyu Zhang, Federico Pecora
Summary: This letter presents a multi-robot task allocation framework for cooperative task completion under task execution uncertainty, utilizing an online sequential task assignment method and one-step-ahead simulation to react to uncertainties in real-time and improve completion efficiency. Experimental results demonstrate successful cooperation and scalability in both small and large-scale multi-robot systems.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Robotics
Theodoros Stouraitis, Michael Gienger
Summary: This letter presents a novel concept to support physically impaired humans in daily object manipulation tasks with a robot, by proposing a predictive model and encoding constancy constraints for considering dependencies between sequential behavior. Numerical studies, simulations and robot experiments were conducted to analyse and evaluate the proposed method in table top tasks.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Zhengwei Wang, Yahui Gan, Xianzhong Dai
Summary: In this paper, a dual-arm robot task sequence planning approach based on environmental constraints and causal reasoning among tasks is proposed. The effectiveness of the approach is demonstrated through simulation experiments.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Yunhui Yan, Ling Tong, Kechen Song, Hongkun Tian, Yi Man, Wenkang Yang
Summary: This paper proposes a network called SISG-Net that integrates instance segmentation and grasp detection, enabling robots to better interact with complex environments and perform grasp tasks. It also introduces a lightweight RGB-D fusion module called SMCF and an FFASP module to address the problem of inaccurate perception of small objects. The stability and robustness of the method are demonstrated through real-world grasping experiments.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Ping Jiang, Junji Oaki, Yoshiyuki Ishihara, Junichiro Ooga, Haifeng Han, Atsushi Sugahara, Seiji Tokura, Haruna Eto, Kazuma Komoda, Akihito Ogawa
Summary: This study proposes an intuitive geometric analytic-based grasp quality evaluation metric and incorporates a reachability evaluation metric for training. The experiment results show that this metric is competitive with a physically-inspired metric, and learning the reachability can improve motion planning computation efficiency.
FRONTIERS IN NEUROROBOTICS
(2022)
Article
Engineering, Industrial
Rong Zhang, Jianhao Lv, Jie Li, Jinsong Bao, Pai Zheng, Tao Peng
Summary: This research presents a method for human-robot collaborative assembly, representing the assembly task of complex products using part-behavior assembly and/or graph based on process requirements. In dynamic scenes, the combination of a human behavior prediction network based on self-attention and the robustness of Soft Actor-Critic algorithm enhances the robot's autonomous decision-making ability. Experimental analysis verifies the effectiveness of the method and demonstrates the feasibility of reinforcement learning for adaptive decision-making in human-robot collaboration environments.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Chemistry, Analytical
Lin Li, Dianxi Shi, Songchang Jin, Shaowu Yang, Chenlei Zhou, Yaoning Lian, Hengzhu Liu
Summary: This paper addresses the coverage path planning problem for multiple Dubins robots. An exact algorithm based on mixed linear integer programming is presented to obtain the shortest coverage path. A heuristic approximate algorithm is also proposed, which uses a credit model to balance tasks and a tree partition strategy to reduce complexity. Experimental results show that the exact algorithm has the least coverage time in small scenes, while the heuristic algorithm has shorter coverage time and less computation time in large scenes. Feasibility experiments demonstrate the applicability of both algorithms to a high-fidelity fixed-wing UAV model.
Article
Robotics
Janine Hoelscher, Mengyu Fu, Inbar Fried, Maxwell Emerson, Tayfun Efe Ertop, Margaret Rox, Alan Kuntz, Jason A. Akulian, Robert J. Webster, Ron Alterovitz
Summary: The study introduces a new sampling-based planning method for a steerable needle lung robot, which has the capability to accurately reach targets in most regions of the lung. The new strategy allows faster performance, reaching targets more efficiently and arriving at lower-risk paths in a shorter time compared to existing techniques.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Xuyang Chen, Xiaojun You, Jinchao Jiang, Jinhua Ye, Haibin Wu
Summary: Efficient trajectory planning and optimization for dual-robot cooperation assembly is achieved through the proposed method based on RRT-Connect algorithm, Floyd algorithm simplification, and Bezier curve smoothing, ultimately obtaining effective paths with a higher success rate and shorter planning time compared to other methods.
Article
Automation & Control Systems
Guoxiang Zhao, Minghui Zhu
Summary: This paper investigates the problem of motion planning for multiple unicycle robots to reach their respective goal regions safely and with minimal traveling times. The authors propose a distributed algorithm that combines decoupled optimal feedback planning and distributed conflict resolution. The algorithm guarantees collision avoidance and finite-time arrival at the goal regions. Furthermore, the computational complexity of the algorithm is independent of the number of robots. Simulations are conducted to verify the scalability and near-optimality of the algorithm.
Article
Robotics
Rafael Papallas, Anthony G. Cohn, Mehmet R. Dogar
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Article
Automation & Control Systems
Wissam Bejjani, Matteo Leonetti, Mehmet R. Dogar
Summary: This paper introduces Visual Receding Horizon Planning (VisualRHP) for efficiently solving short-horizon approximation to a multi-step sequential decision making problem by interleaving real-world execution with look-ahead planning. The robot is guided by a learned heuristic acting on an abstract color-labeled image-based representation of the state, enabling it to generalize behaviors to different environment setups and have transferable manipulation skills. The heuristic is trained with imitation and reinforcement learning in discrete and continuous action spaces, and necessary changes are introduced to improve the stability of existing reinforcement learning algorithms using neural networks with shared parameters.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2021)
Article
Robotics
Luis F. C. Figueredo, Rafael Castro Aguiar, Lipeng Chen, Samit Chakrabarty, Mehmet R. Dogar, Anthony G. Cohn
Summary: This study presents a new metric for calculating quality index in human manipulation and physical human-robot collaboration, addressing the gap in current research. The proposed solution combines pre-computation of biomechanics, ergonomics, muscle assessment, and joint constraints to simplify manipulability assessment for various applications. Numerical evidence shows that the analysis greatly outperforms previous results in terms of computing time without compromising performance.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Automation & Control Systems
Maximo A. Roa, Mehmet Dogar, Jordi Pages, Carlos Vivas, Antonio Morales, Nikolaus Correll, Michael Goerner, Jan Rosell, Sergi Foix, Raphael Memmesheimer, Francesco Ferro
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2021)
Article
Automation & Control Systems
Simon O. Obute, Philip Kilby, Mehmet R. Dogar, Jordan H. Boyle
Summary: This paper presents a study on improving the coordination of a robot swarm using the RepAtt algorithm. Hardware experiments and extensive simulation studies were conducted to validate the effectiveness of the algorithm.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Multidisciplinary
Vasiliki Vouloutsi, Lorenzo Cominelli, Mehmet Dogar, Nathan Lepora, Claudio Zito, Uriel Martinez-Hernandez
Summary: The development of future technologies can be greatly influenced by a deeper understanding of the underlying principles of living organisms. The Living Machines conference showcases the interdisciplinary work of behaving systems based on these principles. This paper highlights the progress and challenges in the fields of biomimetics and robotics for creating artificial systems that can interact with their environment, including tactile sensing, grasping, manipulation, and psychologically plausible agents.
BIOINSPIRATION & BIOMIMETICS
(2023)
Article
Robotics
T. L. Nguyen, A. Blight, A. Pickering, G. Jackson-Mills, A. R. Barber, J. H. Boyle, R. Richardson, M. Dogar, N. Cohen
Summary: Despite advances in robotic technology, conventional cable-tethered robots are still commonly used for sewer pipe inspection. In this paper, a miniaturized mobile robot for pipe inspection is introduced, capable of autonomous control and accessing small-diameter pipes. The control strategy allows the robot to navigate sewer pipe networks without visual aid or power-hungry image processing. The experiments demonstrate the effectiveness of the robot in exploring an unknown pipe network autonomously and without missing any pipe section, marking a significant advance in the field of fully autonomous inspection robot systems for sewer pipe networks.
FRONTIERS IN ROBOTICS AND AI
(2022)
Proceedings Paper
Robotics
Wisdom C. Agboh, Jeffrey Ichnowski, Ken Goldberg, Mehmet R. Dogar
Summary: This study addresses the problem of efficiently grasping and transporting multiple rigid convex polygonal objects into a bin using multi-object push-grasps. The researchers provide necessary conditions for frictionless multi-object push-grasps and develop a novel multi-object grasp planner to filter out inadmissible grasps. The proposed planner is found to be 19 times faster than a Mujoco simulator baseline. Additionally, a picking algorithm that combines single- and multi-object grasps is introduced, achieving a 13.6% higher grasp success rate and a 59.9% faster speed compared to a single-object picking baseline, reaching 340 objects per hour from 212 objects per hour.
ROBOTICS RESEARCH, ISRR 2022
(2023)
Proceedings Paper
Automation & Control Systems
David Russell, Rafael Papallas, Mehmet Dogar
Summary: Trajectory optimisation methods often require derivatives of system dynamics, especially in multi-contact dynamics. However, numerical approximations using finite-differencing can significantly slow down the algorithms. In this study, we propose a method to compute derivatives less frequently and interpolate approximations, resulting in a significant speed-up in overall optimisation time without observable degradation in behavior.
2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023)
(2023)
Proceedings Paper
Automation & Control Systems
Rafael Papallas, Mehmet R. Dogar
Summary: In this paper, a predictive system for motion planning with human-in-the-loop is presented. The system allows a single human operator to effectively guide a fleet of robots in a virtual warehouse. Results show that this approach improves the overall performance of the system and there is a limit to the number of robots that can be effectively guided by a single human operator.
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2022)
Article
Automation & Control Systems
Gustav Markkula, Mehmet R. Dogar
IEEE ROBOTICS & AUTOMATION MAGAZINE
(2022)
Proceedings Paper
Robotics
Wisdom C. Agboh, Daniel Ruprecht, Mehmet R. Dogar
Summary: We present a method for fast and accurate physics-based predictions during non-prehensile manipulation planning and control. The method combines a coarse predictive physics model with a fine predictive physics model to generate a hybrid model that balances speed and accuracy. Experimental results show that using the hybrid physics model can significantly improve planning speed without sacrificing success rates.
ROBOTICS RESEARCH: THE 19TH INTERNATIONAL SYMPOSIUM ISRR
(2022)
Article
Robotics
Luis F. C. Figueredo, Rafael de Castro Aguiar, Lipeng Chen, Thomas C. Richards, Samit Chakrabarty, Mehmet Dogar
Summary: This work addresses the problem of planning a robot configuration and grasp to position a shared object during forceful human-robot collaboration. The planner is designed to reduce human muscular load by predicting human muscular effort, human body kinematic configuration, and robot joint torques.
ACM TRANSACTIONS ON HUMAN-ROBOT INTERACTION
(2022)
Proceedings Paper
Automation & Control Systems
Wissam Bejjani, Wisdom C. Agboh, Mehmet R. Dogar, Matteo Leonetti
Summary: The study focuses on addressing the manipulation task of retrieving a target object from a cluttered shelf using a data-driven hybrid planner and reinforcement learning, which can search and retrieve the target object in near real time in the real world.
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2021)
Proceedings Paper
Automation & Control Systems
Simon O. Obute, Philip Kilby, Mehmet R. Dogar, Jordan H. Boyle
2020 IEEE 16TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE)
(2020)