Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

State-of-the-art in Robot Learning for Multi-Robot Collaboration: A Comprehensive Survey

Bin Wu, C Steve Suh

TL;DR

The paper surveys the state-of-the-art in robot learning for multi-robot collaboration (MRC), addressing how coordinated learning can be achieved across heterogeneous agents. It builds a bridge between human/animal learning paradigms and silicon-based methods, detailing reinforcement learning ($RL$), imitation learning ($IL$), transfer learning ($TL$), causal inference learning ($CIL$), ensemble learning ($EL$), and meta-learning within MRC. The authors discuss technical challenges—data efficiency, generalization, and communication constraints—and illustrate applications in warehousing, search-and-rescue, environmental monitoring, and precision agriculture, supported by quantitative analyses across eight dimensions. They highlight future directions, including integrating large language models for planning, employing causal inference for interpretability, and pursuing energy-efficient designs to enable scalable, real-world deployments.

Abstract

With the continuous breakthroughs in core technology, the dawn of large-scale integration of robotic systems into daily human life is on the horizon. Multi-robot systems (MRS) built on this foundation are undergoing drastic evolution. The fusion of artificial intelligence technology with robot hardware is seeing broad application possibilities for MRS. This article surveys the state-of-the-art of robot learning in the context of Multi-Robot Cooperation (MRC) of recent. Commonly adopted robot learning methods (or frameworks) that are inspired by humans and animals are reviewed and their advantages and disadvantages are discussed along with the associated technical challenges. The potential trends of robot learning and MRS integration exploiting the merging of these methods with real-world applications is also discussed at length. Specifically statistical methods are used to quantitatively corroborate the ideas elaborated in the article.

State-of-the-art in Robot Learning for Multi-Robot Collaboration: A Comprehensive Survey

TL;DR

The paper surveys the state-of-the-art in robot learning for multi-robot collaboration (MRC), addressing how coordinated learning can be achieved across heterogeneous agents. It builds a bridge between human/animal learning paradigms and silicon-based methods, detailing reinforcement learning (), imitation learning (), transfer learning (), causal inference learning (), ensemble learning (), and meta-learning within MRC. The authors discuss technical challenges—data efficiency, generalization, and communication constraints—and illustrate applications in warehousing, search-and-rescue, environmental monitoring, and precision agriculture, supported by quantitative analyses across eight dimensions. They highlight future directions, including integrating large language models for planning, employing causal inference for interpretability, and pursuing energy-efficient designs to enable scalable, real-world deployments.

Abstract

With the continuous breakthroughs in core technology, the dawn of large-scale integration of robotic systems into daily human life is on the horizon. Multi-robot systems (MRS) built on this foundation are undergoing drastic evolution. The fusion of artificial intelligence technology with robot hardware is seeing broad application possibilities for MRS. This article surveys the state-of-the-art of robot learning in the context of Multi-Robot Cooperation (MRC) of recent. Commonly adopted robot learning methods (or frameworks) that are inspired by humans and animals are reviewed and their advantages and disadvantages are discussed along with the associated technical challenges. The potential trends of robot learning and MRS integration exploiting the merging of these methods with real-world applications is also discussed at length. Specifically statistical methods are used to quantitatively corroborate the ideas elaborated in the article.
Paper Structure (26 sections, 4 equations, 8 figures, 1 table)

This paper contains 26 sections, 4 equations, 8 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. DEFINITION AND SCOPE
  3. Multi-robot Systems
  4. Multi-robot Cooperation
  5. Robot Learning
  6. Robot Learning in MRC
  7. Learning Method
  8. Carbon-based vs. Silicon-based
  9. Classical Conditioning
  10. Operant Conditioning
  11. Observational Learning
  12. Cognitive Learning
  13. Socialcultural Learning
  14. Affective Learning
  15. Reinforcement Learning
  16. ...and 11 more sections

Figures (8)

  • Figure 1: Single robot vs multi-robot interaction decision framework
  • Figure 2: Sub-problems of multi-robot systems
  • Figure 3: Robot learning in the context of MRS: applications and challenges
  • Figure 4: Mapping of human/animal learning methods to machine learning methods
  • Figure 5: Evaluation of six robot learning methods across eight dimensions
  • ...and 3 more figures