Robot-Task Suitability in Heterogeneous Multi-Robot Task Allocation

Daniel Weiner; Raj Korpan

cs.ROOct 20, 2026

Robot-Task Suitability in Heterogeneous Multi-Robot Task Allocation

Authors: Daniel Weiner, Raj Korpan

Organizations: The Graduate Center, City University of New York (CUNY), New York, NY, USA · Hunter College and The Graduate Center, City University of New York (CUNY), New York, NY, USA

Abstract

Heterogeneous multi-robot task allocation depends on estimates of how suitable individual robots are for candidate tasks, yet suitability can be defined in substantially different ways. We compare ten deterministic methods and two LLM-based variants spanning rule-based, similarity-based, requirement-oriented, fuzzy, and semantic approaches. Using common robot and task profiles, we compare how the methods score and rank candidate robots, identify feasibility, and select a top robot, while examining how these outcomes change with team composition, scale, spatial context, capability uncertainty, and task representation. The methods frequently disagree despite operating on identical scenarios. Generic similarity measures can violate properties expected under a one-sided requirement-satisfaction interpretation of suitability, while LLM-based scoring introduces additional stochastic and linguistic sensitivity. These results show that robot--task suitability should be treated as an explicit modeling choice whose assumptions, robustness, and decision-level consequences should be considered before allocation.

Figures & tables

Fig. 1: Effects of (a) between-archetype heterogeneity, (b) within-archetype variation, (c) robot count, (d) task count, (e) robot-to-task ratio, and (f) map size. Colored curves show mean best-task suitability; the black curve shows mean cross-method top-robot agreement.

Method	Mean absolute score change	Score correlation	Top-robot stability (%)
Loose	.0098	.983	86.4
Balanced	.0181	.937	85.6
Strict	.0055	.953	90.2
Euclidean	.0028	.984	65.0
Cosine	.0119	.977	68.7
Jaccard	.0088	.982	71.9

TABLE I: Robustness to

20\%

capability perturbation

Task type	Mean absolute error	Mean per-task Spearman $\rho$	Exact top-robot agreement (%)	Strict zero- valued pairs (%)
Assembly	.252	.711	37.3	100.0
Debris	.271	.589	25.5	93.6
Delivery	.224	.568	37.6	52.0
Excavate	.287	.533	34.1	94.3
Item elevation	.267	.705	43.2	86.9
Lay bricks	.240	.428	18.5	76.9

TABLE II: Task-dependent deterministic agreement

Original vs. Paraphrase
Comparison	Mean entry std. dev.	Mean MAE	Matrix Pearson $r$	Mean task Spearman $\rho$	Top-robot agreement (%)
Scalar repeatability	.074	.082	.882	.840	85.3
Structured repeatability	.041	.049	.795	.742	62.2
Scalar	–	.092	.882	.848	63.0
Structured	–	.072	.822	.669	40.0
Structured Gemini vs. deterministic methods

TABLE III: Gemini repeatability, semantic robustness, and deterministic-method agreement

Multi-Robot Task Allocation

Multi-robot task allocation assigns work across robot teams while balancing capabilities, costs, timing, and coordination constraints.

See all 111 papers

FORMICA: Decision-Focused Learning for Communication-Free Multi-Robot Task Allocation
Feb 20, 2026Antonio Lopez, Jack Muirhead, Carlo PinciroliMulti-Robot Task Allocation Multi-Agent Resource Allocation
Dept. of Robotics Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA
Dynamic Multi-Robot Task Allocation under Uncertainty and Communication Constraints: A Game-Theoretic Approach
Apr 13, 2026Maria G. Mendoza, Pan-Yang Su, Bryce L. Ferguson +1Multi-Robot Task Allocation Multi-Agent Resource Allocation
Department of Mechanical Engineering, University of California, Berkeley, Berkeley, CA, United States · Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA, United States · Thayer School of Engineering, Dartmouth College, Hanover, NH, United States
MORPH: Self-Organising Multi-Robot Task Allocation via Neuroplasticity-Inspired Adaptive Topology
Sep 26, 2026Xuezhi Niu, Didem Gürdür BrooMulti-Robot Task Allocation Multi-Agent Resource Allocation
Department of Information Technology, Uppsala University, 751 05 Uppsala, Sweden

Feb 20, 2026J/K move · Enter open · S save

FORMICA: Decision-Focused Learning for Communication-Free Multi-Robot Task Allocation

Antonio Lopez, Jack Muirhead, Carlo Pinciroli

Dept. of Robotics Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA

Multi-Robot Task Allocation Multi-Agent Resource Allocation Multi-Agent Systems Decision-Focused Learning

Open paper AskPDF arXiv

Most multi-robot task allocation methods rely on communication to resolve conflicts and reach consistent assignments. In environments with limited bandwidth, degraded infrastructure, or adversarial interference, existing approaches degrade sharply. We introduce a learning-based framework that achieves high-quality task allocation without any robot-to-robot communication. The key idea is that robots coordinate implicitly by predicting teammates' bids: if each robot can anticipate competition for a task, it can adjust its choices accordingly. Our method predicts bid distributions to correct systematic errors in analytical mean-field approximations. While analytical predictions assume idealized conditions (uniform distributions, known bid functions), our learned approach adapts to task clustering and spatial heterogeneity. Inspired by Smart Predict-then-Optimize (SPO), we train predictors end-to-end to minimize Task Allocation Regret rather than prediction error. To scale to large swarms, we develop a mean-field approximation where each robot predicts the distribution of competing bids rather than individual bids, reducing complexity from

O(NT)

O(T)

. We call our approach FORMICA: Field-Oriented Regret-Minimizing Implicit Coordination Algorithm. Experiments show FORMICA substantially outperforms a natural analytical baseline. In scenarios with 16 robots and 64 tasks, our approach improves system reward by 17% and approaches the optimal MILP solution. When deployed on larger scenarios (256 robots, 4096 tasks), the same model improves performance by 7%, demonstrating strong generalization. Training requires only 21 seconds on a laptop, enabling rapid adaptation to new environments.

Abstract

Multi-Robot Task Allocation

Explore similar work

FORMICA: Decision-Focused Learning for Communication-Free Multi-Robot Task Allocation

Dynamic Multi-Robot Task Allocation under Uncertainty and Communication Constraints: A Game-Theoretic Approach

MORPH: Self-Organising Multi-Robot Task Allocation via Neuroplasticity-Inspired Adaptive Topology