Article
Computer Science, Interdisciplinary Applications
Shuhan Kou, Bruce Golden, Stefan Poikonen
Summary: This article investigates the effectiveness of using the standard deviation predictor for predicting optimal tour lengths in the traveling salesman problem. They update and extend previous computational experiments and empirically reveal the relationship between the standard deviation predictor and the predictor for Euclidean instances, validating its effectiveness in different types of instances.
COMPUTERS & OPERATIONS RESEARCH
(2022)
Article
Automation & Control Systems
Zhengcai Zhao, Yao Li, Yucan Fu
Summary: This paper proposes a novel path planning methodology and develops an automatic collision avoidance strategy for measurement. Measurement points are generated using different sampling methods and shortest-path algorithm and non-interference path algorithm are used for sequence planning. The safe-plane-based method is introduced to simplify the calculation expense of collision-free paths, and an optimized method is proposed to minimize the whole measurement path.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Jinjin Yan, Sisi Zlatanova, Jinwoo (Brian) Lee, Qingxiang Liu
Summary: This paper presents a general solution to the indoor traveling salesman problem (ITSP) path based on Dijkstra and branch and bound (B&B) algorithm, and demonstrates it by applying it in path planning in a large shopping mall with six floors. The results show that the presented solution can successfully compute the ITSP paths and their potentials to apply to other indoor navigation applications at museums or hospitals.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Computer Science, Information Systems
Yu-Hsin Hsu, Rung-Hung Gau
Summary: In this paper, a reinforcement learning approach combined with optimization theory is proposed for collision avoidance and trajectory planning in UAV communication networks. Simulation results demonstrate the superiority of the proposed approach over other methods.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)
Article
Chemistry, Analytical
Abhishek Nayak, Sivakumar Rathinam
Summary: This paper addresses the MinMax variant of the Dubins multiple traveling salesman problem (mTSP) in mission planning applications involving UAVs and ground robots. A mixed-integer linear program (MILP) is formulated to solve the routing problem. Heuristic-based search methods using tour construction algorithms and variable neighborhood search (VNS) metaheuristic are developed. Additionally, a graph neural network is explored to learn policies for the problem using reinforcement learning. The proposed algorithms are implemented and their performance is evaluated on modified TSPLIB instances, showing effectiveness for different instance sizes.
Article
Computer Science, Interdisciplinary Applications
Laszlo Zahoran, Andras Kovacs
Summary: Task sequencing problems are common in robotic applications and can be solved by defining different constraints and cost functions. These problems are often closely related to other sub-problems in process planning and need to be solved jointly. Current methods are often developed for specific applications but rely on similar mathematical models. To avoid redundancies, this paper proposes a generic problem definition language and solver for robotic task sequencing problems. Experimental results show that the proposed language and solver can be applied to a variety of task sequencing problems in robotics.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Automation & Control Systems
Yujiao Hu, Zhen Zhang, Yuan Yao, Xingpeng Huyan, Xingshe Zhou, Wee Sun Lee
Summary: This paper introduces a bidirectional graph neural network (BGNN) for the arbitrary symmetric TSP, which learns to sequentially visit cities through imitation learning. It is more likely to produce near-optimal solutions and can be combined with informed search to further improve performance.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Chemistry, Multidisciplinary
Haichuang Xia, Xiaoping Zhang, Hong Zhang
Summary: This paper proposes a new foot trajectory planning method for legged robots to enhance adaptability to complex terrains, demonstrating its effectiveness through experiments.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Manufacturing
Sadaival Singh, Ambrish Singh, Sajan Kapil, Manas Das
Summary: Toolpath planning is crucial in Additive Manufacturing (AM). This paper proposes a TSP-based algorithm for efficient and accurate area filling with minimum tool retractions and turns. The digitization process is explored to generate grid points, and a novel method for reducing turns in the toolpath is introduced. The proposed path planning method allows for orientation of the toolpath, favoring one direction of motion over the other.
ADDITIVE MANUFACTURING
(2022)
Article
Engineering, Marine
Shuai Zhou, Zheng Wang, Longmei Li, Houpu Li
Summary: This study proposes a novel path cost estimation strategy based on neural networks to address the inadequacies in computation time and solution quality present in existing path planning algorithms. The proposed strategy swiftly generates an accurate cost matrix, ensuring high-quality traversal orders and globally optimal path. Simulation experiments and an actual UUV prototype experiment validate the computational efficiency and practical effectiveness of the proposed algorithm.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Chemistry, Analytical
Junghwan Gong, Seunghwan Lee
Summary: In this study, a systematic exploration of hierarchical designs for multirobot coverage path planning (MCPP) is presented, with a special focus on surveillance applications. The study proposes a general MCPP framework that incorporates renowned algorithms such as genetic algorithms and ant colony optimization. It was found through extensive comparative analysis that the area-based approaches tend to perform better in terms of execution time and path length, while the path-based approaches have the advantage of smaller idle time.
Article
Computer Science, Artificial Intelligence
Artur Wolek, James McMahon, Benjamin R. Dzikowicz, Brian H. Houston
Summary: The Orbiting Dubins Traveling Salesman Problem (ODTSP) involves planning a minimum-time tour for a Dubins vehicle model to inspect a set of targets in the plane by orbiting each target along a circular arc. Algorithms are presented for different scenarios, including when each orbit inspects a single target and when orbits inspect multiple targets. The approach involves identifying admissible clusters of targets to facilitate path planning.
Article
Mechanics
Christian Zauner, Hubert Gattringer, Andreas Mueller, Matthias Joergl
Summary: Tracking predefined open and closed paths is crucial for laser cutting and similar production processes. Heuristic methods are used to find the best sequencing of these paths, considering system limits and minimizing process time. Exact traversing times are computed for non-productive linking trajectories, and two heuristic algorithms for travelling salesman problem are extended to handle open and nested paths. The best performing algorithm is further extended to address problems with nested cutting path structures and their associated precedence constraints.
MULTIBODY SYSTEM DYNAMICS
(2023)
Article
Automation & Control Systems
Yulong Ding, Bin Xin, Hao Zhang, Jie Chen, Lihua Dou, Ben M. Chen
Summary: This paper addresses a UAV path planning problem for a team of cooperating heterogeneous vehicles composed of one unmanned aerial vehicle (UAV) and multiple unmanned ground vehicles (UGVs). The paper proposes a memetic algorithm to efficiently search for the shortest tour that enables the UAV to visit all UGVs, and a transformation procedure to optimize the visiting time. The results demonstrate that this method is more effective in generating paths compared to other competitive algorithms.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Marine
Xu Sun, Ling Zhang, Dalei Song, Q. M. Jonathan Wu
Summary: This paper proposes a global path planning method for collecting data from seabed-based observation networks using multiple unmanned surface vessels (USVs). The method can simultaneously solve the multiple traveling salesmen problem, close-enough traveling salesman problem, and obstacle avoidance problem. It consists of a low level probabilistic focused search method for path cost estimation, an improved partheno-genetic algorithm for task allocation, and an estimated solution method for optimal path point determination. The proposed method is verified to be valid and superior through benchmark experiments, effectively solving the path planning problem for multiple USVs in a sea area with obstacles.
Article
Chemistry, Physical
Gongzhuo Yang, Qibai Huang, Mingquan Yang, Yizhe Huang
Summary: This research investigates the sound transmission loss of metamaterial honeycomb core sandwich plates and proposes a new tuning method to generate specific frequencies of piezoelectric resonance. Numerical calculations and finite element simulations demonstrate that the metamaterial plates have high sound transmission loss in specific frequency bands.
Article
Multidisciplinary Sciences
Jun Wang, Fei Liang, Hongjun Zhou, Mingquan Yang, Quan Wang
Summary: In this study, a parallel robot equipped with a constant force actuator for grinding applications was designed. The characteristics of the robot's spatial positions and poses were analyzed using DH parameters and geometric methods. The workspace for grinding objects was found to be a cylindrical shape with a cross section similar to a symmetric circular sector. The forces produced by the robot system were analyzed using the Newton-Euler method, and the rationality of the force decoupling design was verified. The theoretical analyses were confirmed through theoretical calculations, simulations, and experimental analyses, providing a theoretical foundation for the design, manufacture, and control of the proposed parallel robot system.
Article
Chemistry, Multidisciplinary
Xiaowen Wu, Chaopeng Li, Yizhe Huang, Mingquan Yang, Qibai Huang
Summary: This study focuses on reducing vibration and noise by actively controlling the multiple modes of the compressor shell. The improved algorithm effectively suppresses the structural mode vibration and has a higher convergence speed.
APPLIED SCIENCES-BASEL
(2022)
Article
Materials Science, Multidisciplinary
Yini Song, Jun Wang, Guangyu Lou, Kai Zhang
Summary: An experimental method is proposed to analyze the influence of system parameters on the density of powder layers in laser powder bed fusion technology. The results show that the radius and translational velocity of the recoater have significant effects on powder layer density, while the angular velocity has little impact.
Article
Engineering, Multidisciplinary
Jun Wang, Kai Zhang, Mingquan Yang, Xuwei Zhang, Fei Liang
Summary: In this paper, a method for location prediction and interception grasping of moving objects is proposed to grasp the target object in the shortest time. By introducing position-time functions, the time-optimal grasping point is found at the intersection of the two functions. The method is verified through simulation analysis.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Yizhe Huang, Jiaen Liu, Xuwei Zhang, Jun Wang, Xiao Li, Xikai Tu, Shuisheng Chen, Chenlin Wang, Qibai Huang
Summary: Two algorithms, SQP and BP-SQP, are proposed for creating the inverse kinematics model of the UR10 robot. The SQP algorithm relies heavily on initial values, leading to deviations and reduced solution speed. To mitigate this, the BP-SQP algorithm incorporating a neural network optimizes the initial values. Results show that SQP has a narrow range of applications, while BP-SQP eliminates limitations and reduces time complexity. Both algorithms significantly reduce operation time compared to the closed algorithm, with BP-SQP being faster but requiring a certain number of samples as a prerequisite.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Electrical & Electronic
Jun Wang, Xuwei Zhang, Jiaen Liu, Yuanyuan Shi, Yizhe Huang
Summary: In this paper, a fillet weld identification and location method for highly reflective materials is proposed. The method improves the semantic segmentation performance of the DeeplabV3+ network for structural light and reflective noise and replaces the main trunk network with MobilnetV2 to improve detection efficiency. An improved closing operation using dilation in a combined Zhang-suen algorithm is proposed for structural light skeleton extraction. Experimental results on highly reflective stainless steel fillet welds show that the method is robust, universal, and accurate.