Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dynamic Subgoal based Path Formation and Task Allocation: A NeuroFleets Approach to Scalable Swarm Robotics

Robinroy Peter, Lavanya Ratnabala, Eugene Yugarajah Andrew Charles, Dzmitry Tsetserukou

TL;DR

This work tackles exploration and navigation in unknown environments using scalable swarm robotics. It introduces a decentralized, subgoal-based path formation framework augmented by a light-signal–driven task allocation to curb traffic and collisions in large swarms. The method combines a finite-state machine, local communication, and two heuristic path optimizations, demonstrating improved resource efficiency and faster path formation compared with A*. Results in Argos simulations show average resource reductions of $61.93\%$, with 40\% of paths shorter than A* and $87.5\%$ of paths formed faster when task allocation is used. The approach promises robust, scalable swarm navigation with potential extensions to real robots and learning-based optimization for real-time adaptation in dynamic environments.

Abstract

This paper addresses the challenges of exploration and navigation in unknown environments from the perspective of evolutionary swarm robotics. A key focus is on path formation, which is essential for enabling cooperative swarm robots to navigate effectively. We designed the task allocation and path formation process based on a finite state machine, ensuring systematic decision-making and efficient state transitions. The approach is decentralized, allowing each robot to make decisions independently based on local information, which enhances scalability and robustness. We present a novel subgoal-based path formation method that establishes paths between locations by leveraging visually connected subgoals. Simulation experiments conducted in the Argos simulator show that this method successfully forms paths in the majority of trials. However, inter-collision (traffic) among numerous robots during path formation can negatively impact performance. To address this issue, we propose a task allocation strategy that uses local communication protocols and light signal-based communication to manage robot deployment. This strategy assesses the distance between points and determines the optimal number of robots needed for the path formation task, thereby reducing unnecessary exploration and traffic congestion. The performance of both the subgoal-based path formation method and the task allocation strategy is evaluated by comparing the path length, time, and resource usage against the A* algorithm. Simulation results demonstrate the effectiveness of our approach, highlighting its scalability, robustness, and fault tolerance.

Dynamic Subgoal based Path Formation and Task Allocation: A NeuroFleets Approach to Scalable Swarm Robotics

TL;DR

This work tackles exploration and navigation in unknown environments using scalable swarm robotics. It introduces a decentralized, subgoal-based path formation framework augmented by a light-signal–driven task allocation to curb traffic and collisions in large swarms. The method combines a finite-state machine, local communication, and two heuristic path optimizations, demonstrating improved resource efficiency and faster path formation compared with A*. Results in Argos simulations show average resource reductions of , with 40\% of paths shorter than A* and of paths formed faster when task allocation is used. The approach promises robust, scalable swarm navigation with potential extensions to real robots and learning-based optimization for real-time adaptation in dynamic environments.

Abstract

This paper addresses the challenges of exploration and navigation in unknown environments from the perspective of evolutionary swarm robotics. A key focus is on path formation, which is essential for enabling cooperative swarm robots to navigate effectively. We designed the task allocation and path formation process based on a finite state machine, ensuring systematic decision-making and efficient state transitions. The approach is decentralized, allowing each robot to make decisions independently based on local information, which enhances scalability and robustness. We present a novel subgoal-based path formation method that establishes paths between locations by leveraging visually connected subgoals. Simulation experiments conducted in the Argos simulator show that this method successfully forms paths in the majority of trials. However, inter-collision (traffic) among numerous robots during path formation can negatively impact performance. To address this issue, we propose a task allocation strategy that uses local communication protocols and light signal-based communication to manage robot deployment. This strategy assesses the distance between points and determines the optimal number of robots needed for the path formation task, thereby reducing unnecessary exploration and traffic congestion. The performance of both the subgoal-based path formation method and the task allocation strategy is evaluated by comparing the path length, time, and resource usage against the A* algorithm. Simulation results demonstrate the effectiveness of our approach, highlighting its scalability, robustness, and fault tolerance.
Paper Structure (12 sections, 3 equations, 10 figures, 4 tables)

This paper contains 12 sections, 3 equations, 10 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methodology
  4. Environment Setup
  5. Task Allocation Strategy
  6. Local Communication Protocol
  7. Subgoal-Based Path Formation
  8. Path Formation Strategies
  9. Sensors and Actuators of Robots
  10. Evaluation and Comparisons
  11. Conclusion and Future Work
  12. Acknowledgements

Figures (10)

  • Figure 1: Illustration of dynamic swarm pathway creation in the Argos simulator: (a) Formation of three subgoals. (b) Completion of subgoal paths. (c) Final optimized path after two heuristic optimization steps.
  • Figure 2: Physical robot. (a) S-bot. (b) Custom design physical rr-bot.
  • Figure 3: Robot start (blue) and goal (pink) points in various Argos simulation environments (8m x 4m): (a) Open. (b) Obstacle. (c) Complex obstacle.
  • Figure 4: Finite state machine diagram for subgoal-driven path formation with task-allocation.
  • Figure 5: Color dynamics of a robot across various operational states: (a) Exploring (black). (b) Return to nest (cyan). (c) Subgoal (red). (d) 1st Optimization (blue), (e) 2nd Optimization (red-yellow). (f) Goal founder (dashed magenta). (g) Recovery (magenta). (h) Decision-making (intensive magenta). (i) Resting (white).
  • ...and 5 more figures