MR-SimExCoverage: Multi-robot Simultaneous Exploration and Coverage

Nair, Vishnu G.; Guruprasad, K. R.

doi:10.1016/j.compeleceng.2020.106680

Cited by 15 publications

(30 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[20] At present, the main implementation methods of multi-robot coverage path planning can be divided into map decomposition and collaborative operations. [21][22][23][24][25] Zheng et al proposed a hybrid algorithm based on the combination of the initial position partitioning algorithm and the two-pass algorithm for map prescanning and map MI coverage path planning. [26] Li et al first proposed an exact Dubins multi-robot coverage path planning (EDM) algorithm based on mixed linear integer programming (MILP) and a heuristic approximate credit-based Dubins multirobot coverage path planning (CDM) algorithm to deal with the coverage missions in different scenes.…”

Section: Introductionmentioning

confidence: 99%

“…At present, the main implementation methods of multi‐robot coverage path planning can be divided into map decomposition and collaborative operations. [ 21–25 ] Zheng et al. proposed a hybrid algorithm based on the combination of the initial position partitioning algorithm and the two‐pass algorithm for map pre‐scanning and map MI coverage path planning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Algorithm of Complete Coverage Path Planning for Deep‐Sea Mining Vehicle Clusters Based on Reinforcement Learning

Xing,

Wang,

Liu

2024

Advcd Theory and Sims

View full text Add to dashboard Cite

This paper proposes a deep reinforcement learning algorithm to achieve complete coverage path planning for deep‐sea mining vehicle clusters. First, the mining vehicles and the deep‐sea mining environment are modeled. Then, this paper implements a series of algorithm designs and optimizations based on Deep Q Networks (DQN). The map fusion mechanism can integrate the grid matrix data from multiple mining vehicles to get the state matrix of the complete environment. In this paper, a preprocessing method for the state matrix is also designed to provide suitable training data for the neural network. The reward function and action selection mechanism of the algorithm are also optimized according to the requirements of cluster cooperative operation. Furthermore, the algorithm uses distance constraints to prevent the entanglement of underwater hoses. To improve the training efficiency of the neural network, the algorithm filters and extracts training samples for training through the sample quality score. Considering the requirement of cluster complete coverage mission, this paper introduces Long Short‐Term Memory (LSTM) based on the neural network to achieve a better training effect. After completing the above optimization and design, the algorithm proposed in this paper is verified through simulation experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Algorithm of Complete Coverage Path Planning for Deep‐Sea Mining Vehicle Clusters Based on Reinforcement Learning

Xing,

Wang,

Liu

2024

Advcd Theory and Sims

View full text Add to dashboard Cite

show abstract

“…In these approaches, the robots first select a sub-area generated by the cellular decomposition algorithm (e.g. Voronoi partition [5]) to explore, and then the robot sweeps the entire sub-area along a planned path calculated by the coverage path planning methods [6] for coverage. However, addressing exploration and coverage tasks separately may lead to sub-optimal solutions and increased computational cost, consequently limiting overall task performance.…”

Section: Introductionmentioning

confidence: 99%

Cooperative Search Strategy of Multi-UAVs Based on Reinforcement Learning

Zhao¹,

Cui

Hao³

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

In the tasks of multi-robot collaborative area search, we propose the unified approach for simultaneous mapping for sensing more targets (exploration) while searching and locating the targets (coverage). Specifically, we implement a hierarchical multi-agent reinforcement learning algorithm to decouple task planning from task execution. The role concept is integrated into the upper-level task planning for role selection, which enables robots to learn the role based on the state status from the upperview. Besides, an intelligent role switching mechanism enables the role selection module to function between two timesteps, promoting both exploration and coverage interchangeably. Then the primitive policy learns how to plan based on their assigned roles and local observation for sub-task execution. The welldesigned experiments show the scalability and generalization of our method compared with state-of-the-art approaches in the scenes with varying complexity and number of robots.

show abstract

“…Each robot is then assigned an individual cell to cover, eliminating the need for continuous communication with other robots. Voronoi partitioning or its variants [25,27,32,[34][35][36]38] are commonly used for dividing the workspace. However, most literature performs partitioning based on the initial positions of the robots, which may be less efficient without an optimal initial deployment scheme.…”

Section: Introductionmentioning

confidence: 99%

Robust Online Multi-robot Simultaneous Exploration and Coverage Path Planning

Nair,

2023

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, a robust online Multi-robot Simultaneous exploration and coveragepath planning problem is presented. The entire workspace is initially partitionedusing the Manhattan Voronoi partitioning method, and the robots execute Multi-Robot Simultaneous Exploration and Coverage (MRSimExCoverage) using theSpanning Tree Coverage (STC) algorithm and cover the workspace. Once the robot(s) failure is detected the uncovered portions of the Voronoi cell of the failedrobot will be shared between other eligible robots or a replacement strategy,ifavailable, is performed. Simulation experiments within the V-rep environment isused to demonstrate and validate the performance of the proposed algorithm.Though the authors used the STC algorithm for path planning for the purposeof demonstration, any suitable coverage algorithm may be used.

show abstract

MR-SimExCoverage: Multi-robot Simultaneous Exploration and Coverage

Cited by 15 publications

References 12 publications

An Algorithm of Complete Coverage Path Planning for Deep‐Sea Mining Vehicle Clusters Based on Reinforcement Learning

An Algorithm of Complete Coverage Path Planning for Deep‐Sea Mining Vehicle Clusters Based on Reinforcement Learning

Cooperative Search Strategy of Multi-UAVs Based on Reinforcement Learning

Robust Online Multi-robot Simultaneous Exploration and Coverage Path Planning

Contact Info

Product

Resources

About