Graph Theory-Based Approach to Accomplish Complete Coverage Path Planning Tasks for Reconfigurable Robots

Abstract

Extensive studies regarding complete coverage problems have been conducted, but a few tackle scenarios where the mobile robot is equipped with reconfigurable modules. The reconfigurability of these robots creates opportunities to develop new navigation strategies with higher dexterity; however, it also simultaneously adds in constraints to the direction of movements. This paper aims to develop a valid navigation strategy that allows tetromino-based self-reconfigurable robots to perform complete coverage tasks. To this end, a novel graph theory-based model to simulate the workspace coverage and make use of dynamic programming technique for optimal path searching and adaptive robot morphology shifting algorithms is proposed. Moreover, the influence of algorithms starting variables on workspace coverage outcome is analyzed thoughtfully in this paper. The simulation results showed that the proposed method is capable of generating navigation paths throughout the workspace, which ensures complete workspace coverage while minimizing the total number of actions performed by the robot.INDEX TERMS Complete coverage path planning, self-reconfigurable robots, graph theory, dynamic programming, Dijkstra algorithm.

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

“…PP problem is modeled differently in reconfigurable robots and in fixed morphology robots. For fixed-morphology robots, exhaustive search such as Dijkstra and A* algorithms are commonly utilized to solve global PP problems; on the other hand, Ant Colony Optimization (ACO) [20], Particle Swarm Optimization (PSO) [21], Neural Network [22], Motion Planning [23], Path Tracking [24], Graph theory [25] and Genetic Algorithm (GA) [26] have been implemented to solve local PP problems. Among the existing PP methods, GA has shown its strength in convenient modeling, easy implementation, and practical problem solving [27] due to its flexibility to perform optimization without prior information [28], and its ability to explore the solution space [29], which hinges on the advantages of both deterministic and probabilistic schemes to improve solutions using operators like crossover and mutation [30].…”

Reinforcement Learning-Based Energy-Aware Area Coverage for Reconfigurable hRombo Tiling Robot

“…Other techniques can slip the map equally based on each sub-region complexity, such as the isolated method used in Morse [17] work. A number of different methods combine the use of graph theory [18], and high-order observers-based LQ control scheme [19]. The other common and popular methods are the standard grid-based probability assignment proposed by Moravec and Elfes [20] and Choset [21].…”

Motion planner for a Tetris-inspired reconfigurable floor cleaning robot

“…There are numerous algorithms proposed towards realizing grid-based coverage such as wavefront algorithm, 13 spanning tree technique, 14 hexagonal grid decomposition, 15 and graph theory-based coverage. 16 Xu 17 presented a graph-based CPP technique, in which he considers the mapped area as a graph and applies robot motion planning to reach every coordinate point in the graph. In recent years, several 3-D area coverage techniques have been proposed and validated in the context of service robots.…”