| This Paper:Browse 514 Download 0 |
码上扫一扫！ |
| Sequencing of multi‑robot behaviors using reinforcement learning |
| PietroPierpaoli,ThinhT.Doan,JustinRomberg,MagnusEgerstedt |
|
|
| (1 School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA;2 Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24061, USA;3 Samueli School of Engineering, University of California, Irvine, CA 92697, USA) |
|
| 摘要: |
| Given a collection of parameterized multi-robot controllers associated with individual behaviors designed for particular
tasks, this paper considers the problem of how to sequence and instantiate the behaviors for the purpose of completing a
more complex, overarching mission. In addition, uncertainties about the environment or even the mission specifications
may require the robots to learn, in a cooperative manner, how best to sequence the behaviors. In this paper, we approach this
problem by using reinforcement learning to approximate the solution to the computationally intractable sequencing problem,
combined with an online gradient descent approach to selecting the individual behavior parameters, while the transitions
among behaviors are triggered automatically when the behaviors have reached a desired performance level relative to a task
performance cost. To illustrate the effectiveness of the proposed method, it is implemented on a team of differential-drive
robots for solving two different missions, namely, convoy protection and object manipulation. |
| 关键词: Multi-robot systems · Reinforcement learning · Distributed control |
| DOI：https://doi.org/10.1007/s11768-021-00069-5 |
|
| 基金项目:This work was supported by the Army Research Lab (No. DCIST CRA W911NF-17-2-0181). |
|
| Sequencing of multi‑robot behaviors using reinforcement learning |
| Pietro Pierpaoli,Thinh T. Doan,Justin Romberg,Magnus Egerstedt |
| (1 School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA;2 Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24061, USA;3 Samueli School of Engineering, University of California, Irvine, CA 92697, USA) |
| Abstract: |
| Given a collection of parameterized multi-robot controllers associated with individual behaviors designed for particular
tasks, this paper considers the problem of how to sequence and instantiate the behaviors for the purpose of completing a
more complex, overarching mission. In addition, uncertainties about the environment or even the mission specifications
may require the robots to learn, in a cooperative manner, how best to sequence the behaviors. In this paper, we approach this
problem by using reinforcement learning to approximate the solution to the computationally intractable sequencing problem,
combined with an online gradient descent approach to selecting the individual behavior parameters, while the transitions
among behaviors are triggered automatically when the behaviors have reached a desired performance level relative to a task
performance cost. To illustrate the effectiveness of the proposed method, it is implemented on a team of differential-drive
robots for solving two different missions, namely, convoy protection and object manipulation. |
| Key words: Multi-robot systems · Reinforcement learning · Distributed control |
