Communication-Aware Heterogeneous Graph Learning for Decentralized Multi-Human Multi-Robot Task Allocation

Ziqin Yuan; Ruiqi Wang; Baijian Yang; Byung-Cheol Min

cs.ROSep 26, 2026

Communication-Aware Heterogeneous Graph Learning for Decentralized Multi-Human Multi-Robot Task Allocation

Authors: Ziqin Yuan, Ruiqi Wang, Baijian Yang, Byung-Cheol Min

Organizations: Purdue University, West Lafayette, IN, USA. · Indiana University Bloomington, Bloomington, IN, USA.

Abstract

Multi-human multi-robot (MH-MR) teams combine robotic autonomy with human expertise, but effective task allocation requires coordinating scarce, dynamically available human support with distributed robot execution. Limited robot-robot and human-robot communication further complicates this coupling by delaying information exchange and supervisory intervention. We introduce CommHG, a communication-aware heterogeneous graph learning framework for decentralized MH-MR task allocation. CommHG represents coupled human-robot-task interactions through local graphs conditioned on information availability and age. Learned communication actions enable robots to decide when and which operator to query, and when to share information with peers. Allocation and communication are jointly optimized through cooperative multi-agent reinforcement learning, allowing the team to acquire useful information while managing limited communication and supervisory resources. We also introduce a benchmark integrating heterogeneous humans and robots, dynamic tasks and operational states, and constrained robot-robot and bidirectional human-robot links. Experiments across heterogeneous teams with up to 16 robots, 6 humans, and 112 tasks show that CommHG improves timely weighted mission completion as coordination scale increases, outperforming the strongest baseline in the Large scenario.

Figures & tables

Panel of Figure 1 — Fig. 1 : Conceptual illustration of challenges in MH-MR coordination.

Fig. 2 : Overview of CommHG for decentralized MH-MR task allocation under limited communication. (a) Each decision maker uses its own state, public task attributes, received records, and local communication resources. (b) Typed encoders and relation-specific aggregation represent human supervision, robot execution, and task demand. Local graphs retain information availability and age. (c) Role-specific policies jointly learn task allocation, peer broadcasting, operator queries, and human supervisory allocation. Robots decide when and which human to query; humans decide which robot to assist. A centralized critic uses global state during PPO training, while execution relies on local observations. Actions affect the graph at subsequent decisions through locally observed changes and delivered messages.

Fig. 3 : Overview of the MH-MR benchmark 3D simulation environment.

Setting	Small	Medium	Large
Map side (m)	500	1000	2000
Tasks	22	56	112
Time limit (s)	600	1200	2400
UAVs / UGVs / operators	2 / 2 / 2	4 / 4 / 3	8 / 8 / 6

TABLE I : Simulation environment settings. Scenario-dependent settings are listed above the shared settings. Speed and proficiency pairs are ordered as (UAV, UGV). Proficiency is a service-time multiplier; lower values indicate faster operators on the corresponding robot type.

Fig. 4 : Mean TWCR (a) Baseline comparison across Small, Medium, and Large scenarios. (b) Ablations in the Medium scenario under increasing communication limitation. Numbers above bars indicate mean values.

Fig. 5 : Active querying in an execution sequence. R1 expects H1’s support for J2 (left), learns that H1 is assisting R2 (middle), and selects J1 for autonomous execution (right). Delivered information changes allocation without reallocating human support.

Explore similar work

FORMICA: Decision-Focused Learning for Communication-Free Multi-Robot Task Allocation
Feb 20, 2026Antonio Lopez, Jack Muirhead, Carlo PinciroliMulti-Robot Task Allocation Multi-Agent Systems
Dept. of Robotics Engineering, Worcester Polytechnic Institute, Worcester MA 01609, USA
Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation
May 25, 2026Alexander Apartsin, Yigal Meshulam, Yehudit ApersteinMulti-Robot Task Allocation Collaborative Filtering
Holon Institute of Technology, Holon, Israel. · Afeka Tel Aviv Academic College of Engineering, Tel Aviv, Israel
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 Systems
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

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 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

Explore similar work

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

Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation

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