A Comparison of Various Approaches to Reinforcement Learning Algorithms for Multi-robot Box Pushing

Rahimi, Mehdi; Gibb, Spencer; Shen, Yantao; La, Hung Manh

doi:10.1007/978-3-030-04792-4_6

Cited by 18 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The region-growing curriculum is also applied for multi-robot object transportation (lines 6-7). Using the Q single -network with a probability of ψ, each robot can take approaching and transport actions from the beginning (lines [12][13][14][15]. With the help of the actions by Q single -network, multiple robots can train their network Q multi (lines [16][17][18][19][20].…”

Section: Single-to Multi-robot Curriculummentioning

confidence: 99%

“…They showed that the performance of single-agent Q-learning was better than that of team Q-learning due to the lack of sufficient random actions. Rahimi et al [ 13 ] compared single and multi-robot cases with RL-based approaches. They showed that the performance of cooperative box-pushing could be improved by frequent Q-table updates.…”

Section: Related Workmentioning

confidence: 99%

“…The DRL has been proven to be applied to various mobile robotics fields, such as collision avoidance, object transportation, multi-robot navigation, and social navigation [9][10][11]. Among them, DRL-based object transportation techniques have attracted attention from many researchers because DRL can solve tricky issues of conventional methods [12][13][14]. Using the DRL algorithm, robots can learn how to transport an object to a goal without preliminary knowledge.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Eoh

Park

2021

Sensors

View full text Add to dashboard Cite

This paper presents a cooperative object transportation technique using deep reinforcement learning (DRL) based on curricula. Previous studies on object transportation highly depended on complex and intractable controls, such as grasping, pushing, and caging. Recently, DRL-based object transportation techniques have been proposed, which showed improved performance without precise controller design. However, DRL-based techniques not only take a long time to learn their policies but also sometimes fail to learn. It is difficult to learn the policy of DRL by random actions only. Therefore, we propose two curricula for the efficient learning of object transportation: region-growing and single- to multi-robot. During the learning process, the region-growing curriculum gradually extended to a region in which an object was initialized. This step-by-step learning raised the success probability of object transportation by restricting the working area. Multiple robots could easily learn a new policy by exploiting the pre-trained policy of a single robot. This single- to multi-robot curriculum can help robots to learn a transporting method with trial and error. Simulation results are presented to verify the proposed techniques.

show abstract

Section: Single-to Multi-robot Curriculummentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Eoh

Park

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Multi-sensor data retrieval for cloud robotic systems is a multiple, cooperative, real-time task (Wang et al, 2015). Multiple mobile robots push boxes together, which is a single, cooperative, real-time task (Rahimi et al, 2019). For the multiagent warehouse system, the task is single, individual, realtime.…”

Section: Multi-agent Task Allocationmentioning

confidence: 99%

HGHA: task allocation and path planning for warehouse agents

Liu

Han

Wang

et al. 2021

View full text Add to dashboard Cite

Purpose With the rapid development of e-commerce, logistics demand is increasing day by day. The modern warehousing with a multi-agent system as the core comes into being. This paper aims to study the task allocation and path-planning (TAPP) problem as required by the multi-agent warehouse system. Design/methodology/approach The TAPP problem targets to minimize the makespan by allocating tasks to the agents and planning collision-free paths for the agents. This paper presents the Hierarchical Genetic Highways Algorithm (HGHA), a hierarchical algorithm combining optimization and multi-agent path-finding (MAPF). The top-level is the genetic algorithm (GA), allocating tasks to agents in an optimized way. The lower level is the so-called highways local repair (HLR) process, avoiding the collisions by local repairment if and only if conflicts arise. Findings Experiments demonstrate that HGHA performs faster and more efficient for the warehouse scenario than max multi-flow. This paper also applies HGHA to TAPP instances with a hundred agents and a thousand storage locations in a customized warehouse simulation platform with MultiBots. Originality/value This paper formulates the multi-agent warehousing distribution problem, TAPP. The HGHA based on hierarchical architecture solves the TAPP accurately and quickly. Verifying the HGHA by the large-scale multi-agent simulation platform MultiBots.

show abstract

“…23,24 Reinforcement learning has been implemented cooperatively in a variety of ways for multiagent environments, such as a GridWorld 25,26 and box pushing. 27 Although all of these use for consensus, movement control, and reinforcement learning that are good in their own right, this article aims to make a more intelligent hybrid system.…”

Section: Introduction Motivationmentioning

confidence: 99%

Consensus, cooperative learning, and flocking for multiagent predator avoidance

Young

2020

International Journal of Advanced Robotic Systems

Self Cite

View full text Add to dashboard Cite

Multiagent coordination is highly desirable with many uses in a variety of tasks. In nature, the phenomenon of coordinated flocking is highly common with applications related to defending or escaping from predators. In this article, a hybrid multiagent system that integrates consensus, cooperative learning, and flocking control to determine the direction of attacking predators and learns to flock away from them in a coordinated manner is proposed. This system is entirely distributed requiring only communication between neighboring agents. The fusion of consensus and collaborative reinforcement learning allows agents to cooperatively learn in a variety of multiagent coordination tasks, but this article focuses on flocking away from attacking predators. The results of the flocking show that the agents are able to effectively flock to a target without collision with each other or obstacles. Multiple reinforcement learning methods are evaluated for the task with cooperative learning utilizing function approximation for state-space reduction performing the best. The results of the proposed consensus algorithm show that it provides quick and accurate transmission of information between agents in the flock. Simulations are conducted to show and validate the proposed hybrid system in both one and two predator environments, resulting in an efficient cooperative learning behavior. In the future, the system of using consensus to determine the state and reinforcement learning to learn the states can be applied to additional multiagent tasks.

show abstract

A Comparison of Various Approaches to Reinforcement Learning Algorithms for Multi-robot Box Pushing

Cited by 18 publications

References 9 publications

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning

HGHA: task allocation and path planning for warehouse agents

Consensus, cooperative learning, and flocking for multiagent predator avoidance

Contact Info

Product

Resources

About