Adaptive Repulsive Pheromone Clustering for Foraging Robot Swarms

Noosaga Placements

• Multi Robot Systemssubfield95%
  The paper focuses on coordination of a robot swarm for foraging, a core topic in multi-robot systems.
  Swarm robotics is a research field that explores the coordination of multiple simple and autonomous robots to perform complex tasks in a decentralized waywe propose the Adaptive Repulsive Pheromone Cluster algorithm (ARPC), an algorithm that can rapidly identify and eliminate locations that no longer justify exploration
• Bio-Inspired and Swarm Roboticsframework95%
  The paper is explicitly about bio-inspired swarm robotics, building on ant foraging behavior.
  The Central Place Foraging Algorithm (CPFA) is a bio-inspired swarm robotics method that captures the group foraging dynamics of desert harvester antswe propose the Adaptive Repulsive Pheromone Cluster algorithm (ARPC), a bio-inspired method
• Behavior-Based and Reactive Approachesframework80%
  The algorithm uses reactive behaviors and decentralized coordination typical of behavior-based approaches.
  The robot controller is a finite state machine that governs the transitions between traveling, searching, surveying, and returningrobots deposit repulsive pheromone waypoints to mark previously explored locations
• Roboticssubfield70%
  The work is situated in robotics and uses bio-inspired algorithms, aligning with the broader AI robotics subfield.
  The Central Place Foraging Algorithm (CPFA) is a bio-inspired swarm robotics methodARPC targets a core practical challenge: enabling large teams to coordinate exploration with a single collaborative generated map of negative information
• Behavior-Based and Reactive Roboticsframework70%
  The robots use reactive behaviors like random walk and pheromone following, characteristic of behavior-based mobile robotics.
  robots search for resources using random walkFollow a pheromone trail left by another robot
• Mobile Roboticssubfield60%
  The robots are mobile and the algorithm involves navigation and exploration in an environment.
  robots lay down repulsive pheromones along their paths to mark and subsequently avoid already explored regionsThe robot travels to this target and performs a spiral search of radius τ

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.

Paper Context