Multiple robots task allocation for cleaning a large public space

Though existing social robots can already be used in a variety of applications, there are technical limitations to their use, especially outside the laboratory, and humans do not fully trust or recognize them. Considering these problems, a method to make humans accept a robot’s suggestion more easily was investigated. An idea called “sequential persuasion” was developed to use multiple robots distant from each other to deliver small messages, rather than a single robot for the entire interaction. To experimentally validate this concept, a field experiment was performed on a university campus. Two bottles of hand sanitizer were placed in one of the entrances to a building, and their usage was observed under three different conditions: no robot, one robot, and three robots. As people passed through the entrance corridor, the robots promoted the usage of the hand sanitizers. After several days of testing, it was found that the usage increased progressively from no robot to one robot to three robots, indicating that the number of robots influenced the behavior of the humans.

Download Full-text

Game theory-based negotiation for multiple robots task allocation

Robotica ◽

10.1017/s0263574713000192 ◽

2013 ◽

Vol 31 (6) ◽

pp. 923-934 ◽

Cited By ~ 26

Author(s):

Rongxin Cui ◽

Ji Guo ◽

Bo Gao

Keyword(s):

Game Theory ◽

Task Allocation ◽

Optimal Solution ◽

Multiple Robots ◽

Negotiation Strategy ◽

Contract Net ◽

Initial Task ◽

The Game Theory ◽

Task Reallocation ◽

Negotiation Mechanism

SUMMARYThis paper investigates task allocation for multiple robots by applying the game theory-based negotiation approach. Based on the initial task allocation using a contract net-based approach, a new method to select the negotiation robots and construct the negotiation set is proposed by employing the utility functions. A negotiation mechanism suitable for the decentralized task allocation is also presented. Then, a game theory-based negotiation strategy is proposed to achieve the Pareto-optimal solution for the task reallocation. Extensive simulation results are provided to show that the task allocation solutions after the negotiation are better than the initial contract net-based allocation. In addition, experimental results are further presented to show the effectiveness of the approach presented.

Download Full-text

Cooperative Multi-Robot Task Allocation with Reinforcement Learning

Applied Sciences ◽

10.3390/app12010272 ◽

2021 ◽

Vol 12 (1) ◽

pp. 272

Author(s):

Bumjin Park ◽

Cheongwoong Kang ◽

Jaesik Choi

Keyword(s):

Reinforcement Learning ◽

Task Allocation ◽

Decision Process ◽

Large Scale ◽

Heuristic Methods ◽

Learning Method ◽

Multiple Robots ◽

Markov Decision ◽

Robot Task ◽

Multi Robot

This paper deals with the concept of multi-robot task allocation, referring to the assignment of multiple robots to tasks such that an objective function is maximized. The performance of existing meta-heuristic methods worsens as the number of robots or tasks increases. To tackle this problem, a novel Markov decision process formulation for multi-robot task allocation is presented for reinforcement learning. The proposed formulation sequentially allocates robots to tasks to minimize the total time taken to complete them. Additionally, we propose a deep reinforcement learning method to find the best allocation schedule for each problem. Our method adopts the cross-attention mechanism to compute the preference of robots to tasks. The experimental results show that the proposed method finds better solutions than meta-heuristic methods, especially when solving large-scale allocation problems.

Download Full-text