RECORD
Learning to Dynamically Coordinate Multi-Robot Teams in Graph Attention Networks
Robotics · Submitted 4 Dec 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We show that our network-based policy finds at least twice as many solutions over prior state-of-the-art methods in all testing scenarios.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Increasing interest in integrating advanced robotics within manufacturing has spurred a renewed concentration in developing real-time scheduling solutions to coordinate human-robot collaboration in this environment. Traditionally, the problem of scheduling agents to complete tasks with temporal and spatial constraints has been approached either with exact algorithms, which are computationally intractable for large-scale, dynamic coordination, or approximate methods that require domain experts to craft heuristics for each application. We seek to overcome the limitations of these conventional methods by developing a novel graph attention network formulation to automatically learn features of scheduling problems to allow their deployment. To learn effective policies for combinatorial optimization problems via machine learning, we combine imitation learning on smaller problems with deep Q-learning on larger problems, in a non-parametric framework, to allow for fast, near-optimal scheduling of robot teams. We show that our network-based policy finds at least twice as many solutions over prior state-of-the-art methods in all testing scenarios.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Increasing interest in integrating advanced robotics within manufacturing has spurred a renewed concentration in developing real-time scheduling solutions to coordinate human-robot collaboration in this environment. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | Traditionally, the problem of scheduling agents to complete tasks with temporal and spatial constraints has been approached either with exact algorithms, which are computationally intractable for large-scale, dynamic coordination, or approximate methods that require domain experts to craft heuristics for each application. | background 0.84 | 0.04 | 0.02 | asserted 1.00 |
| s2 | We seek to overcome the limitations of these conventional methods by developing a novel graph attention network formulation to automatically learn features of scheduling problems to allow their deployment. | contribution 0.94 | 0.51 | 0.05 | asserted 0.53 |
| s3 | To learn effective policies for combinatorial optimization problems via machine learning, we combine imitation learning on smaller problems with deep Q-learning on larger problems, in a non-parametric framework, to allow for fast, near-optimal scheduling of robot teams. | method 0.99 | 0.93 | 0.09 | asserted 0.96 |
| s4 | We show that our network-based policy finds at least twice as many solutions over prior state-of-the-art methods in all testing scenarios. | result 1.00 | 0.96 | 0.80 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Increasing interest in integrating advanced robotics within manufacturing has spurred a renewed concentration in developing real-time scheduling solutions to coordinate human-robot collaboration in this environment. Traditionally, the problem of scheduling agents to complete tasks with temporal and spatial constraints has been approached either with exact algorithms, which are computationally intractable for large-scale, dynamic coordination, or approximate methods that require domain experts to craft heuristics for each application. We seek to overcome the limitations of these conventional methods by developing a novel graph attention network formulation to automatically learn features of scheduling problems to allow their deployment. To learn effective policies for combinatorial optimization problems via machine learning, we combine imitation learning on smaller problems with deep Q-learning on larger problems, in a non-parametric framework, to allow for fast, near-optimal scheduling of robot teams. We show that our network-based policy finds at least twice as many solutions over prior state-of-the-art methods in all testing scenarios.
Human review
How the literature uses it
2 arXiv papers cite this in 5 sentences
What it cites · 1 sentence without a confident label
Uses the method or tool of 1 paper
-
We set $γ$ = 0.95 and use Adam optimizer [ref] through training.
Adam: A Method for Stochastic Optimization · RESULTS AND DISCUSSION · 1.00
Cites as background 1 paper
-
To address these limitations, we consider recent advances in graph neural networks (GNN) that extend deep neural networks to handle arbitrarily-structured data [ref] .
Graph Neural Networks: A Review of Methods and Applications · RELATED WORK · 0.84
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.