Optimizing the coverage path planning (CPP) in robotics has become essential to accomplish efficient coverage applications. This work presents a novel approach to solve the CPP problem in large complex environments based on the Travelling Salesman Problem (TSP) and Deep Reinforcement Learning (DRL) leveraging the grid-based maps. The proposed algorithm applies the cellular decomposition methods to decompose the environment and generate the coverage path by recursively solving each decomposed cell formulated as TSP. A solution to TSP is determined by training Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) layers using Reinforcement Learning (RL). We validated the proposed method by systematically benchmarked with other conventional methods in terms of path length, execution time, and overlapping rate under four different map layouts with various obstacle density. The results depict that the proposed method outperforms all considered parameters than the conventional schemes. Moreover, simulation experiments demonstrate that the proposed approach is scalable to the larger grid-maps and guarantees complete coverage with efficiently generated coverage paths.

Planning the energy-efficient and collision-free paths for reconfigurable robots in complex environments is more challenging than conventional fixed-shaped robots due to their flexible degrees of freedom while navigating through tight spaces. This article presents a novel algorithm, energy-efficient batch informed trees* (BIT*) for reconfigurable robots, which incorporates BIT*, an informed, anytime sampling-based planner, with the energy-based objectives that consider the energy cost for robot’s each reconfigurable action. Moreover, it proposes to improve the direct sampling technique of informed RRT* by defining an $L^2$ greedy informed set that shrinks as a function of the state with the maximum admissible estimated cost instead of shrinking as a function of the current solution, thereby improving the convergence rate of the algorithm. Experiments were conducted on a tetromino hinged-based reconfigurable robot as a case study to validate our proposed path planning technique. The outcome of our trials shows that the proposed approach produces energy-efficient solution paths, and outperforms existing techniques on simulated and real-world experiments.

Applying the automation in covering the areas entirely eases manual jobs in various domestic fields such as site investigation, search, rescue, security, cleaning, and maintenance. A self-reconfigurable robot with adjustable dimensions is a viable answer to improve the coverage percentage for predefined map areas. However, the shape-shifting of this robot class also adds to the complexity of locomotion components and the need for an optimal complete coverage strategy for this new type of robot. The typical complete coverage route, including the least times of shape-shifting, the shortest navigation route, and the minimum travel time, is presented in the article. By splitting the map into the sub-areas similar to the self-reconfigurable robot's available shapes, the robot can design the ideal tileset and optimal navigation strategies to cover the workspace. To this end, we propose a Complete Tileset Energy-Aware Coverage Path Planning (CTPP) framework for a tiling self-reconfigurable robot named hRombo with four rhombus-shaped modules. The robot can reconfigure its base structure into seven distinct forms by activating the servo motors to drive the three robot hinges connecting robot modules. The problem of optimal path planning assisting the proposed hRombo robot to clear optimally all predefined tiles within the arbitrary workspace is considered a classic Travel Salesman Problem (TSP), and this TSP is solved by the reinforcement learning (RL) approach. The RL's reward function and action space are based on robot kinematic and the required energies, including transformation, translation, and orientation actions, to move the robot inside the workspace. The CTPP for the hRombo robot is validated with conventional complete coverage methods in simulation and real workspace conditions. The results showed that the CTPP is suitable for producing Pareto plans that enable robots to navigate from source to target in different workspaces with the least consumed energy and time among considered methods.

One of the critical challenges in deploying the cleaning robots is the completion of covering the entire area. Current tiling robots for area coverage have fixed forms and are limited to cleaning only certain areas. The reconfigurable system is the creative answer to such an optimal coverage problem. The tiling robot’s goal enables the complete coverage of the entire area by reconfiguring to different shapes according to the area’s needs. In the particular sequencing of navigation, it is essential to have a structure that allows the robot to extend the coverage range while saving energy usage during navigation. This implies that the robot is able to cover larger areas entirely with the least required actions. This paper presents a complete path planning (CPP) for hTetran, a polyabolo tiled robot, based on a TSP-based reinforcement learning optimization. This structure simultaneously produces robot shapes and sequential trajectories whilst maximizing the reward of the trained reinforcement learning (RL) model within the predefined polyabolo-based tileset. To this end, a reinforcement learning-based travel sales problem (TSP) with proximal policy optimization (PPO) algorithm was trained using the complementary learning computation of the TSP sequencing. The reconstructive results of the proposed RL-TSP-based CPP for hTetran were compared in terms of energy and time spent with the conventional tiled hypothetical models that incorporate TSP solved through an evolutionary based ant colony optimization (ACO) approach. The CPP demonstrates an ability to generate an ideal Pareto optima trajectory that enhances the robot’s navigation inside the real environment with the least energy and time spent in the company of conventional techniques.

Maintenance of ship hull involves routine tasks during dry-docking that includes inspection, paint stripping, and re-painting. Among those, paint stripping is always seen as harmful for human operators and a time-consuming task. To reduce human risk, cost, and environmental cleanliness, the shipping maintenance industries started using robotic solutions. However, most of such robotic systems cannot operate fully autonomous since it requires human in the loop to monitor the cleaning efficiency. To this end, a novel autonomous self-evaluating hull cleaning robot called Hornbill is presented in this paper. The proposed robot is capable of navigating autonomously on the hull surface and perform water jet blasting to strip off the paint coating. The robot is also enabled with a Deep Convolutional Neural Network (DCNN) based self-evaluating scheme that benchmarks cleaning efficiency. We evaluated the proposed robot’s performance by conducting experimental trials on a metal plate under three different paint coatings. While performing the paint stripping task in every experimental trial, the self-evaluating scheme would generate the heat map that depicts the plate’s cleanliness. The results indicate that the proposed self-evaluating system could successfully generate high accurate cleanliness heat maps in all considered scenarios, which simplifies the checkup process for paint inspectors.