現今，隨著工業 4.0 與智慧製造的持續發展，生產線的模式逐漸在改變，而衍生出人機協作（Human-robot collaboration，HRC）的模式。在人機協作的環境下，工作人員與協作機器人（Cobots）相互合作，因此，人與機器人之間互動產生很多的不確定性，其中，安全性成為主要的問題之一。在傳統的避障方式是先計算出機器人與障礙物之間是否發生干涉，再利用演算法計算出新的移動軌跡。在干涉檢測的步驟中，機器人要不斷地和障礙物進行干涉檢測，此過程的運算量高也相當耗時。
本研究提出建立空間安全評估模型的方法，此方法是先將機器手臂各軸以圓柱體的形式進行包覆，建立出機器手臂模型，並定義出工作空間與障礙物大小，最後建立出機器手臂模型與工作空間中障礙物的關係，並利用隨機森林（Random Forest）的回歸器來建立空間安全評估模型，代替傳統的避障時的干涉檢測，經過研究成果發現利用空間安全評估模型計算危險評估值比直接計算快約 600 倍。本研究利用空間安全評估模型來檢測機器手臂移動軌跡的安全性，當發生碰撞時，擷取出碰撞路徑中的三組機械手臂組態，個別利用最佳化方法－牛頓法（Newton’s Method）尋找出新的修正組態，最後利用機器手臂的控制指令將新的修正組態進行串聯，使機器手臂順利的避開障礙物。

Advancement in industry 4.0 is increasing in recent days, as human workers cannot achieve high productivity levels alone. As a result, the concept of human-robot collaboration, HRC, is proposed. Human workers collaborating with robots is not the future. Robots conduct laborious and repetitive tasks, while humans do the work that requires experience. However, traditional robots have no ability to communicate with their human partners which results in injuries to humans. The traditional methods of obstacle avoidance in robotics with interference detection, which calculates the possibility of interference between robots and obstacles. Nevertheless, this method comes with high computational complexity and is time consuming
In this research, a model is proposed to assess safety by determining the interaction between the robotic arm and the obstacle within its workspace in advance. Instead of using the conventional interference detection method, this safety model was constructed using a random forest regressor. The method we suggest is 600 times faster than the conventional method.In order to choose a path with the least chance of collapsing,Acquire the status of the robotic arm and apply the Newton method to each dataset respectively, and get the modified moving trajectory with zero probability of collision.Apply the outcome trajectory to the controller and the robotic arm can perform collision avoidance.

[1] D. Han, H. Nie, J. Chen, M. Chen, Dynamic obstacle avoidance for manipulators using distance calculation and discrete detection, Robotics and computer-integrated manufacturing, 49, 98-104, 2018.
[2] A. Ajoudani, A. M. Zanchettin, S. Ivaldi, A. Albu-Schäffer, K. Kosuge, O. Khatib, Progress and prospects of the human–robot collaboration, Autonomous Robots, 42(5), 957-975, 2018.
[3] J. T. C. Tan, F. Duan, R. Kato, T. Arai, Man-Machine Interface for Human-Robot Collaborative Cellular Manufacturing System, International Journal of Automation Technology, 3(6), 760-767, 2009.
[4] V. Villani, F. Pini, F. Leali, C. Secchi, Survey on human–robot collaboration in industrial settings: Safety, intuitive interfaces and applications, Mechatronics, 55, 248-266, 2018.
[5] G. Michalos, S. Makris, P. Tsarouchi, T. Guasch, D. Kontovrakis, G. Chryssolouris, Design considerations for safe human-robot collaborative workplaces, Procedia CIrP, 37, 248-253, 2015.
[6] A. M. Zanchettin, N. M. Ceriani, P. Rocco, H. Ding, B. Matthias, Safety in human-robot collaborative manufacturing environments: Metrics and control, IEEE Transactions on Automation Science and Engineering, 13(2), 882-893, 2015.
[7] J. Borenstein, Y. Koren, Real-time obstacle avoidance for fast mobile robots in cluttered environments, Proceedings., IEEE International Conference on Robotics and Automation, 572-577, 1990.
[8] J. Borenstein, Y. Koren, Real-time obstacle avoidance for fast mobile robots, IEEE Transactions on systems, Man, and Cybernetics, 19(5), 1179-1187, 1989.
[9] M. Nascimento, P. Vicente, A. Bernardino, 2D Visual Servoing meets Rapidly-exploring Random Trees for collision avoidance, 2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 227-232, 2020.
[10] K. Wei, B. Ren, A method on dynamic path planning for robotic manipulator autonomous obstacle avoidance based on an improved RRT algorithm, Sensors, 18(2), 571, 2018.
[11] P. Vadakkepat, K. C. Tan, W. Ming-Liang, Evolutionary artificial potential fields and their application in real time robot path planning, Proceedings of the 2000 congress on evolutionary computation. CEC00 (Cat. No. 00TH8512), 256-263, 2000.
[12] A. K. Guruji, H. Agarwal, D. Parsediya, Time-efficient A* algorithm for robot path planning, Procedia Technology, 23, 144-149, 2016.
[13] J. J. Kuffner, S. M. LaValle, RRT-connect: An efficient approach to single-query path planning, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No. 00CH37065), 995-1001, 2000.
[14] S. Secil, M. Ozkan, Minimum distance calculation using skeletal tracking for safe human-robot interaction, Robotics and Computer-Integrated Manufacturing, 73, 102253, 2022.
[15] O. Khatib, Real-time obstacle avoidance for manipulators and mobile robots, Autonomous robot vehicles, 396-404, Springer, 1986.
[16] Artificial Potential Fields, URL: https://www.guyuehome.com/11044.
[17] L. Zhou, W. Li, Adaptive artificial potential field approach for obstacle avoidance path planning, 2014 Seventh International Symposium on Computational Intelligence and Design, 429-432, 2014.
[18] A. Javaid, Understanding Dijkstra's algorithm, Available at SSRN 2340905, 2013.
[19] Dijkstra's algorithm, URL: https://zhuanlan.zhihu.com/p/429697098.
[20] H. Wang, Y. Yu, Q. Yuan, Application of Dijkstra algorithm in robot path-planning, 2011 second international conference on mechanic automation and control engineering, 1067-1069, 2011.
[21] Z. Nie, H. Zhao, Research on robot path planning based on Dijkstra and Ant colony optimization, 2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), 222-226, 2019.
[22] G.-Z. Tan, H. He, S. Aaron, Global optimal path planning for mobile robot based on improved Dijkstra algorithm and ant system algorithm, Journal of Central South University of Technology, 13(1), 80-86, 2006.
[23] P. E. Hart, N. J. Nilsson, B. Raphael, A formal basis for the heuristic determination of minimum cost paths, IEEE transactions on Systems Science and Cybernetics, 4(2), 100-107, 1968.
[24] A* search algorithm, URL: https://www.guyuehome.com/6560.
[25] C. Wang, L. Wang, J. Qin, Z. Wu, L. Duan, Z. Li, M. Cao, X. Ou, X. Su, W. Li, Path planning of automated guided vehicles based on improved A-Star algorithm, 2015 IEEE International Conference on Information and Automation, 2071-2076, 2015.
[26] L. E. Kavraki, P. Svestka, J.-C. Latombe, M. H. Overmars, Probabilistic roadmaps for path planning in high-dimensional configuration spaces, IEEE transactions on Robotics and Automation, 12(4), 566-580, 1996.
[27] K. Belghith, F. Kabanza, L. Hartman, R. Nkambou, Anytime dynamic path-planning with flexible probabilistic roadmaps, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006., 2372-2377, 2006.
[28] F. Yan, Y.-S. Liu, J.-Z. Xiao, Path planning in complex 3D environments using a probabilistic roadmap method, International Journal of Automation and computing, 10(6), 525-533, 2013.
[29] R. Bohlin, L. E. Kavraki, Path planning using lazy PRM, Proceedings 2000 ICRA. Millennium conference. IEEE international conference on robotics and automation. Symposia proceedings (Cat. No. 00CH37065), 521-528, 2000.
[30] H. Akbaripour, E. Masehian, Semi-lazy probabilistic roadmap: a parameter-tuned, resilient and robust path planning method for manipulator robots, The International Journal of Advanced Manufacturing Technology, 89(5), 1401-1430, 2017.
[31] S. M. LaValle, J. J. Kuffner, Rapidly-Exploring Random Trees: Progress and Prospects: Steven M. LaValle, Iowa State University, A James J. Kuffner, Jr., University of Tokyo, Tokyo, Japan, Algorithmic and Computational Robotics, 303-307, 2001.
[32] X. Wang, X. Luo, B. Han, Y. Chen, G. Liang, K. Zheng, Collision-free path planning method for robots based on an improved rapidly-exploring random tree algorithm, Applied Sciences, 10(4), 1381, 2020.
[33] P. Zhang, C. Xiong, W. Li, X. Du, C. Zhao, Path planning for mobile robot based on modified rapidly exploring random tree method and neural network, International Journal of Advanced Robotic Systems, 15(3), 1729881418784221, 2018.
[34] C.-B. Moon, W. Chung, Kinodynamic planner dual-tree RRT (DT-RRT) for two-wheeled mobile robots using the rapidly exploring random tree, IEEE Transactions on industrial electronics, 62(2), 1080-1090, 2014.
[35] L. Bottou, Stochastic gradient descent tricks, Neural networks: Tricks of the trade, 421-436, Springer, 2012.
[36] 林照益, 基於障礙物佔據建模及軌跡可靠度優化的機械手臂路徑規劃, 國立臺灣科技大學 碩博士論文.
[37] TCR6-V900 Operating Manual.
[38] Random Forest, URL: https://pcnow.cc/p/3ROmN3be52.html.
[39] Regression Model Evaluation Index, URL: https://blog.csdn.net/qq_32623363/article/details/113272790.
[40] Lagrange Multiplier, URL: https://zh.wikipedia.org/zh-tw/%E6%8B%89%E6%A0%BC%E6%9C%97%E6%97%A5%E4%B9%98%E6%95%B0.
[41] Newton's method, URL: https://zh.wikipedia.org/zh-tw/%E7%89%9B%E9%A1%BF%E6%B3%95.