Embedding Autonomous Agents in Resource-Constrained Robotic Platforms

2026-01-07

arXiv.org

AI Summary

This work addresses the challenge of enabling efficient autonomous decision-making on resource-constrained embedded devices by deploying, for the first time, a high-level agent reasoning mechanism based on AgentSpeak onto a compact two-wheeled robotic platform. The agent operates without external intervention, performing localized reasoning and decision-making using real-time sensor data to accomplish a maze exploration task. Experimental results demonstrate that the agent successfully solves the maze within 287 reasoning cycles (59 seconds), achieving per-decision latency below 1 millisecond—well within the stringent timing requirements of dynamic environments. These findings validate the feasibility and efficiency of the agent-based paradigm in embedded systems, highlighting its potential for real-time autonomous operation under severe computational constraints.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Many embedded devices operate under resource constraints and in dynamic environments, requiring local decision-making capabilities. Enabling devices to make independent decisions in such environments can improve the responsiveness of the system and reduce the dependence on constant external control. In this work, we integrate an autonomous agent, programmed using AgentSpeak, with a small two-wheeled robot that explores a maze using its own decision-making and sensor data. Experimental results show that the agent successfully solved the maze in 59 seconds using 287 reasoning cycles, with decision phases taking less than one millisecond. These results indicate that the reasoning process is efficient enough for real-time execution on resource-constrained hardware. This integration demonstrates how high-level agent-based control can be applied to resource-constrained embedded systems for autonomous operation.

Problem

• autonomous agents
• resource-constrained platforms
• embedded systems
• real-time decision-making
• robotic autonomy

Innovation

• autonomous agents
• resource-constrained embedded systems
• AgentSpeak
• real-time reasoning
• robotic autonomy