Coordinated Area Partitioning Method by Autonomous Agents for Continuous Cooperative Tasks

Abstract

Abstract:We describe a method for decentralized task/area partitioning for coordination in cleaning/sweeping domains with learning to identify the easy-to-dirty areas. Ongoing advances in computer science and robotics have led to applications for covering large areas that require coordinated tasks by multiple control programs including robots. Our study aims at coordination and cooperation by multiple agents, and we discuss it using an example of the cleaning tasks to be performed by multiple agents with potentially different performances and capabilities. We then developed a method for partitioning the target area on the basis of their performances in order to improve the overall efficiency through their balanced collective efforts. Agents, i.e., software for controlling devices and robots, autonomously decide in a cooperative manner how the task/area is partitioned by taking into account the characteristics of the environment and the differences in agents' software capability and hardware performance. During this partitioning process, agents also learn the locations of obstacles and the probabilities of dirt accumulation that express what areas are easy to be dirty. Experimental evaluation showed that even if the agents use different algorithms or have the batteries with different capacities resulting in different performances, and even if the environment is not uniform such as different locations of easy-to-dirty areas and obstacles, the proposed method can adaptively partition the task/area among the agents with the learning of the probabilities of dirt accumulations. Thus, agents with the proposed method can keep the area clean effectively and evenly.

Hybrid Partition-Based Patrolling Scheme for Maritime Area Patrol with Multiple Cooperative Unmanned Surface Vehicles

“…Portugal et al [1] thought that the local patrolling path in graph partitions could be improved by minimizing the longest local path. Sea et al [15,16] presented a decentralized partitioning method for cleaning tasks of multiple agents under the grid environment. Sugiyama et al [17] designed different visit frequencies for all purposes in the patrolling area and applied divisional cooperation to achieve the patrol tasks.…”

“…Randomly Choose N targets as the initial centroids 3: repeat 4: For each target, select the nearest centroid as its partition 5: Reset the centroids to the weighted center of all targets in each partition by (16) 6: until convergence 7: for n = 1 to N do 8:…”

Equitable persistent coverage of non-convex environments with graph-based planning

“…Complete coverage was guaranteed in Kapoutsis et al (2017), with a specifically tailored, optimality-preserving, technique. In the work of Sea et al (2017), the features of online obstacle and decay learning were added to a decentralized partitioning of the target area on the basis of the robot performance. The main difference of our approach with respect to these solutions is that the resulting partition is equitable in terms of the robots' workload.…”

Path planning and search effectiveness of USV based on underwater target scattering model

“…In 2016, Sugiyama et al [3] discussed the problem of continuous collaborative patrol search for access points with different frequencies, but the method did not consider the problem of region delimitation. In 2017, Sea et al [4,5] proposed a balanced load region partitioning method for continuous collaborative tasks in the field of robotics, which is an important reference for the study of multi-USV task assignment problems. In 2020, Liu et al [6] proposed the use of a collaborative search algorithm based on reinforcement learning and probabilistic maps, which can explore environmental information more effectively through probabilistic maps.…”