Optimization Complete Area Coverage by Reconfigurable hTrihex Tiling Robot

Abstract

Completed area coverage planning (CACP) plays an essential role in various fields of robotics, such as area exploration, search, rescue, security, cleaning, and maintenance. Tiling robots with the ability to change their shape is a feasible solution to enhance the ability to cover predefined map areas with flexible sizes and to access the narrow space constraints. By dividing the map into sub-areas with the same size as the changeable robot shapes, the robot can plan the optimal movement to predetermined locations, transform its morphologies to cover the specific area, and ensure that the map is completely covered. The optimal navigation planning problem, including the least changing shape, shortest travel distance, and the lowest travel time while ensuring complete coverage of the map area, are solved in this paper. To this end, we propose the CACP framework for a tiling robot called hTrihex with three honeycomb shape modules. The robot can shift its shape into three different morphologies ensuring coverage of the map with a predetermined size. However, the ability to change shape also raises the complexity issues of the moving mechanisms. Therefore, the process of optimizing trajectories of the complete coverage is modeled according to the Traveling Salesman Problem (TSP) problem and solved by evolutionary approaches Genetic Algorithm (GA) and Ant Colony Optimization (ACO). Hence, the costweight to clear a pair of waypoints in the TSP is defined as the required energy shift the robot between the two locations. This energy corresponds to the three operating processes of the hTrihex robot: transformation, translation, and orientation correction. The CACP framework is verified both in the simulation environment and in the real environment. From the experimental results, proposed CACP capable of generating the Pareto-optimal outcome that navigates the robot from the goal to destination in various workspaces, and the algorithm could be adopted to other tiling robot platforms with multiple configurations.

Hornbill: A Self-Evaluating Hydro-Blasting Reconfigurable Robot for Ship Hull Maintenance

“…In order to achieve autonomous propagation, it is critical to obtain an accurate robot's position on the hull surface. Conventional approaches estimating the global position of the robot are Lidar based simultaneous localization and mapping SLAM [24] and visual SLAM [25] and sensor fusion localization [26] and feature tracking [27]. These methods derive the features of objects inside the working environment to estimate the global location.…”

Coverage Path Planning for Decomposition Reconfigurable Grid-Maps Using Deep Reinforcement Learning Based Travelling Salesman Problem

“…C OVERAGE Path Planning (CPP) algorithms have been applied to several robotics applications in real-world such as floor-cleaning robots [1], [2], underwater operations [3], agricultural robots [4], tiling robotics [5]- [7], ship hull cleaning [8], benchmarking for inspection [9] and pavement sweeping [10], [11] to name a few. CPP describes an approach designed to determine a path that passes through all the workspace points while avoiding obstacles.…”

Multi-Objective Genetic Algorithm-Based Autonomous Path Planning for Hinged-Tetro Reconfigurable Tiling Robot

“…An inter-reconfigurable robot consists of a congregation of homogeneous or heterogeneous modules and forms a variety of morphologies through assembly and disassembly process. Examples include chain-type systems like Tetriamond [13], CONRO [14], hTetro-Infi [15], hTrihex [16], Crystal [17], and M-Lattice [18]; as well as hybridtype robots like M-TRAN [19].…”