Complete coverage path planning using reinforcement learning for Tetromino based cleaning and maintenance robot

Lakshmanan, Anirudh Krishna; Mohan, Rajesh Elara; Ramalingam, Balakrishnan; Le, Anh Vu; Veerajagadheswar, Prabakaran; Tiwari, Kamlesh; Ilyas, Muhammad

doi:10.1016/j.autcon.2020.103078

Cited by 114 publications

(79 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The rationale behind the proposed hTetro-Infi is explained based on conventional hTetro which is one of the existing tiling robots. The existing work on hTetro considered that hTetro can have only seven distinct shapes, and the shapes are 'O', 'T', 'Z', 'S', 'I', 'L' and 'J' [22]- [24]. The morphologies that are mimicked by the conventional hTetro is shown in Figure 2.…”

Section: Htetro-infi a Rationale Behind The Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

hTetro-Infi: A Reconfigurable Floor Cleaning Robot With Infinite Morphologies

Samarakoon

Muthugala

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The development of floor cleaning robots is an emerging area in robotics. Maximizing the area coverage is a foremost mission for a floor cleaning robot. Reconfigurable floor cleaning robots outperform floor cleaning robots with fixed morphology in the aspect of area coverage. A reconfigurable robot should be more flexible in changing its morphologies by considering the shapes of objects occupied in an environment to gain more coverage. Nevertheless, the state of the art methods of tiling robots considers only a limited number of morphologies for the reconfiguration, which is not sufficient to match the shape of an object. Therefore, this paper proposes a novel method to synthesize an appropriate morphology for a reconfigurable robot in accordance with the shape of an object. The proposed concept is named hTetro-Infi since it is not limited to a finite number of morphologies. The major novelty of the proposed concept overt the state of the art is the consideration of an infinite number of morphologies for the reconfiguration without sticking into a limited number of morphologies. Feedforward Neural Network (FNN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used for determining the hinge angle required for synthesizing a given morphology. Different configurations of FNNs and ANFISs were trained and evaluated to find the most suitable configurations. The area coverage performance of the proposed hTetro-Infi was compared against that of the state of the art methods of an existing class of tiling robots, which considers only a limited number of morphologies, through simulations. According to the statistical conclusions, the proposed hTetro-Infi is capable of significantly improving area coverage compared to an existing tiling-theory based floor cleaning robot. Furthermore, the area coverage improvement of hTetro-Infi is noteworthy. Therefore, the proposed concept is beneficial in improving the abilities of a reconfigurable cleaning robot. Real-world experiments with the hardware platform of the robot for evaluating the performance is expected to be conducted in the next phase of the work. Furthermore, consideration of hTetro-Infi for navigation through confined areas is proposed for future work. INDEX TERMS Adaptive neuro-fuzzy inference system, area coverage, feedfoward neural network, tiling robotic, floor cleaning robot, reconfigurable robot.

show abstract

Section: Htetro-infi a Rationale Behind The Proposed Methodsmentioning

confidence: 99%

“…In the previous work on tiling robots [18], [22]- [24] the robots are operated with only with a limited number of morphologies. Moreover, the existing area coverage algorithms for tiling robots consider a less number of morphologies for the reconfiguration.…”

Section: Introductionmentioning

confidence: 99%

hTetro-Infi: A Reconfigurable Floor Cleaning Robot With Infinite Morphologies

Samarakoon

Muthugala

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main goal of the complete coverage problem is to obtain the minimal number of waypoints which guides the agent around the scenario by covering every single zone. This is the problem addressed in [22] and [18] by using DQL algorithms. Furthermore, some authors are interested in the solution of non-homogeneous patrolling.…”

Section: Related Workmentioning

confidence: 99%

“…Many authors defined the environment in their coverage problems as a two dimension grid map with a representative cell resolution for every scenario. This assumption is adequate for many cases such as in [22] and [19], where the agent moves within a plane. Each cell is usually identified with a label with one of the following categories: visited, unvisited or obstacle [22].…”

Section: Related Workmentioning

confidence: 99%

A Deep Reinforcement Learning Approach for the Patrolling Problem of Water Resources Through Autonomous Surface Vehicles: The Ypacarai Lake Case

2020

View full text Add to dashboard Cite

“…Most of these ship hull cleaning activities focus on removing barnacles, paint, and rust, which are always seen as harmful for human operators and time-consuming tasks. The cleaning robots become popular in the model civilization; they are set to self-operate in both indoor [1], [2] and outdoor environments [3], [4]. By witnessing the evolution of robotization over the last few decades, the ship maintenance industry has shown great interest in deploying robots for hull cleaning tasks to reduce the risk of employing manual labor.…”

Section: Introductionmentioning

confidence: 99%

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

Veerajagadheswar

Kyaw

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

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. INDEX TERMS Benchmarking blasting quality, Hydro blasting, Paint stripping, Reconfigurable robotics, Robotics for ship maintenance industry.

show abstract

Complete coverage path planning using reinforcement learning for Tetromino based cleaning and maintenance robot

Cited by 114 publications

References 29 publications

hTetro-Infi: A Reconfigurable Floor Cleaning Robot With Infinite Morphologies

hTetro-Infi: A Reconfigurable Floor Cleaning Robot With Infinite Morphologies

A Deep Reinforcement Learning Approach for the Patrolling Problem of Water Resources Through Autonomous Surface Vehicles: The Ypacarai Lake Case

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

Contact Info

Product

Resources

About