A robotized interior work process planning algorithm based on surface minimum coverage set

Interior finishing requires high labor intensity and finishing materials are harmful to workers during the processes, especially the one of wall surface disposal. In order to reduce labor costs and protect the health of workers, applying autonomous interior finishing robots in the wall surface disposal process will be a reasonable choice. In the application of an autonomous interior finishing robot, the path taken by the robot must be planned carefully considering that indoor environments can be very complicated. In addition, different from mobile manipulators, a mobile interior finishing robot has to access larger working space and be able to apply large force to the walls, ceilings. Thus they have to be used in a way similar to mobile crane. That is in order to guarantee stability, in each working station, mechanical stands will be released to support the platform. After finishing required processes, the stands have to be retrieved to move to the next working position. For an interior finishing robot working in this way, it needs to determine the optimal plan to minimize the times of working position change. In this paper, a method based on a minimal cover set of the planar surface is proposed for this purpose. With the derived robot moving plan with minimized steps, the whole moving sequence of the robotic interior finishing unit is determined with Genetic algorithm. The work area needed to be finished in each working position is then divided by using Voronoi graph.

[1]  Samir R. Das,et al.  Connected sensor cover: self-organization of sensor networks for efficient query execution , 2006, TNET.

[2]  Yehiel Rosenfeld,et al.  Interior Finishing Building Robot "TAMIR" , 1991 .

[3]  Atsuyuki Okabe,et al.  Spatial Tessellations: Concepts and Applications of Voronoi Diagrams , 1992, Wiley Series in Probability and Mathematical Statistics.

[4]  Volker Helm,et al.  Mobile robotic fabrication on construction sites: DimRob , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Liang Yan-chun.  Order Preserving of Gene Section for Solving Traveling Salesman Problems Using Genetic Algorithms , 2000 .

[6]  Wenhua Dou,et al.  A Coverage-Preserving Density Control Algorithm for Wireless Sensor Networks , 2004, ADHOC-NOW.

[7]  Zhou Tao.  TSP Problem Solution Based on Improved Genetic Algorithm , 2008, 2008 Fourth International Conference on Natural Computation.

[8]  G. Reinelt.  The traveling salesman: computational solutions for TSP applications , 1994 .

[9]  Göktürk Üçoluk.  Genetic Algorithm Solution of the TSP Avoiding Special Crossover and Mutation , 2002, Intell. Autom. Soft Comput..

[10]  Hongyi Wu,et al.  Grid-based approach for working node selection in wireless sensor networks , 2004, 2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577).

[11]  Mac Schwager,et al.  Adaptive Coordinating Construction of Truss Structures Using Distributed Equal-Mass Partitioning , 2014, IEEE Transactions on Robotics.

[12]  Himanshu Gupta,et al.  Connected sensor cover: self-organization of sensor networks for efficient query execution , 2003, IEEE/ACM Transactions on Networking.

[13]  Abraham Warszawski,et al.  Robot for Interior‐Finishing Works in Building: Feasibility Analysis , 1994 .

[14]  Wang Chun-hong,et al.  Selection-based genetic algorithm , 2007 .