Adaptive Repulsive Pheromone Clustering for Foraging Robot Swarms

Carlos Pena-Caballero; Constantine Tarawneh; Qi Lu

cs.ROAug 17, 2026

Adaptive Repulsive Pheromone Clustering for Foraging Robot Swarms

Authors: Carlos Pena-Caballero, Constantine Tarawneh, Qi Lu

Organizations: The University of Texas Rio Grande Valley, Edinburg, TX, USA

Abstract

The Central Place Foraging Algorithm (CPFA) combines site fidelity, pheromone-guided navigation, and uninformed random search to enable decentralized resource collection in robot swarms. However, CPFA often revisits previously explored regions while leaving other areas insufficiently searched, reducing efficiency as resources become scarce. In this paper, we propose Adaptive Repulsive Pheromone Clustering (ARPC), a bio-inspired method in which robots deposit repulsive pheromone waypoints to mark previously explored locations. These waypoints are clustered around the nest to estimate low-value search regions, allowing robots to be redirected toward likely unvisited areas. By integrating the exploitation of known resources with systematic avoidance of redundant exploration, ARPC improves search diversity and resource discovery efficiency. Extensive simulations in ARGoS across varying arena sizes, resource densities, and clustered, random, and power-law spatial distributions demonstrate that ARPC consistently outperforms CPFA and the Grid-Based CPFA (GPFA). In particular, ARPC yields significant gains during both early discovery (10%) and late-stage (up to 60%) collection, where conventional methods typically degrade. These results indicate that ARPC provides a scalable and robust strategy for large-scale heterogeneous swarm foraging environments.

Figures & tables

Figure 1: The flow chart of an individual robot’s behavior and states in the CPFA; additions to the algorithm for ARPC are shown in red.

Panel of Figure 2 — Figure 2: Example ARGoS simulations conducted in a 10 $\times$ 10 m arena. Panel (a) shows the baseline setup, in which robots explore the environment and gather resources. The robots lay down repulsive pheromones (yellow dots), which later coalesce into clusters (magenta); green dots indicate the individual locations that contribute to each cluster. Panels (b - i) present an entire simulation run.

Experiments	I	II	III
Arena Size (meter)	14 × 14	14 × 14	8 × 8, 10 × 10, 12 × 12 14 × 14, 16 × 16
# of Resources	16, 32, 48, 64, 80	48	48
# of Robots	16	16	16
# of Runs	50	50	50
Resource Distributions	Clustered Powerlaw Random	Clustered Powerlaw Random	Random

Table 1: Consolidated Experimental Configurations

Panel of Figure 3 — Figure 3: Experiment I: cumulative time (s) needed to collect 100% of the resources. All experiments are performed in a 14 $\times$ 14 m arena containing 16, 32, 48, 64, or 80 resources.

Panel of Figure 4 — Figure 4: Experiment II: time (s) to reach each 10% resource-collection milestones (10%, 20%, …, 100%) in a 14 $\times$ 14 arena containing 48 resources, evaluated under three spatial resource distributions: (a) clustered, (b) power-law, and (c) random.

Config	GPFA (80% $\rightarrow$ 90%)	ARPC (80% $\rightarrow$ 90%)	GPFA (90% $\rightarrow$ 100%)	ARPC (90% $\rightarrow$ 100%)	Endgame Improvement
Cluster	394.0	269.3	680.7	593.8	+12.78%
Powerlaw	313.7	276.9	774.8	1021.1	$-$ 31.79%
Random	298.6	284.0	900.8	703.7	+21.89%

Table 2: Duration of the Final Collection Phases (Seconds)

Figure 5: Experiment III: cumulative completion time (s) to collect 100% of resources across different square arena sizes (8 $\times$ 8 to 16 $\times$ 16).

Swarm Robotics

Swarm robotics studies how groups of robots coordinate through local sensing, communication, and interaction to accomplish shared tasks.

See all 99 papers

A Visitation Grid for Complete Coverage Foraging in Robot Swarms
May 21, 2026Qi Arturo Gonzalez, Yifeng Gao, Li Zhang +1Multi-Robot Systems Swarm Robotics
Department of Computer Science The University of Texas Rio Grande Valley, Texas, United States
LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging
May 2, 2026Peihan Li, Joanna Gutierrez, Fabian Hernandez +2Swarm Robotics Language Model-Based Control
Drexel University, Philadelphia, PA 19104, USA · The University of Texas Rio Grande Valley, Edinburg, Texas 78541, USA
SPACE: Swarm Pheromone Fields for Adaptive Collision-Aware Exploration
Jun 28, 2026Haohua Que, Haojia Gao, Mingkai Liu +3Robot Collision Avoidance Swarm Robotics
Department of Electronic Engineering, Tsinghua University, Beijing, China. · Tsinghua Shenzhen International Graduate School (SIGS), Tsinghua University, Shenzhen, China. · School of Software and Microelectronics, Peking University, Beijing, China.

May 21, 2026J/K move · Enter open · S save

A Visitation Grid for Complete Coverage Foraging in Robot Swarms

Qi Arturo Gonzalez, Yifeng Gao, Li Zhang, Qi Lu

Department of Computer Science The University of Texas Rio Grande Valley, Texas, United States

Multi-Robot Systems Swarm Robotics Multi-Robot Exploration Multi-Robot Coordination

Open paper AskPDF arXiv

The complete collection of sparse resources in large, unknown environments remains a challenging problem for autonomous robot swarms. Previous studies have shown that a substantial portion of total mission time is consumed during the final stage of collection, where only a small fraction of randomly scattered resources remain. Consequently, many existing swarm foraging algorithms (search and collection) focus on collecting most resources within a limited time window, rather than improving end-stage efficiency for collecting all resources. We propose a grid-based stochastic foraging strategy that explicitly reduces redundant visits and accelerates late-stage collection. The unknown search area is partitioned into a grid map, which is maintained by a lightweight central server. To maintain scalability, both robots and the server operate within limited memory and computational constraints. The server updates the grid-level visitation counts based on robot-reported locations, producing a global estimate of the exploration density. For each new foraging trip, a robot selects its next search area from a local 3 X 3 neighborhood of grids probabilistically with the lowest visitation count, thus biasing exploration toward under-visited regions while maintaining stochasticity. Extensive simulation experiments demonstrate that the proposed strategy consistently outperforms the canonical centrally placed baseline foraging algorithm (CPFA). Compared to CPFA, the proposed method reduces the total collection time by up to 33% and improves collection efficiency by more than 48% during the final stage of the mission. These results indicate that the proposed strategy is robust, flexible, and scalable for near-complete and complete resource collection in robot swarms and can serve as a general enhancement for stochastic swarm foraging methods under limited onboard resources.

Abstract

Swarm Robotics

Explore similar work

A Visitation Grid for Complete Coverage Foraging in Robot Swarms

LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging

SPACE: Swarm Pheromone Fields for Adaptive Collision-Aware Exploration