Complex Autonomous UAV Task Execution and Decision-Making With s(CASP)

2026-06-22

AI Summary

This work addresses the challenges of safety, explainability, and adaptability faced by autonomous drones in dynamic environments, particularly when task failure or insufficient information hinders effective adjustment. The paper proposes a symbolic, state-centric agent based on s(CASP) Answer Set Programming, applied for the first time in a high-fidelity Unreal Engine 5 simulation environment to execute multi-step autonomous behaviors—including navigation, search, detection, spraying, transportation, and inspection. By integrating commonsense reasoning with constraint solving, the approach enables dynamic re-planning without retraining and supports multi-task coordination through the VECSR-A architecture. Experimental results demonstrate that the system guarantees correctness, offers strong explainability, and achieves real-time adaptability in complex scenarios, significantly enhancing autonomous decision-making performance in safety-critical missions.

Abstract

Autonomous unmanned aerial vehicles (UAVs) must operate safely in dynamic environments and adapt to changing mission conditions. Although deep learning approaches have shown strong performance for navigation and perception, they are often difficult to explain, verify, and modify for safety-critical tasks. We propose a symbolic state-centered UAV agent using the s(CASP) answer set programming system, enabling autonomous task execution with constraint-based commonsense reasoning in a high-fidelity Unreal Engine 5 environment. We fully implement prior work on the VECSR-A system to support multi-step autonomous behaviors including navigation, search, debris detection, precision spraying, object transport, and inspection. The UAV reasons over environmental and spatial constraints, dynamically revising plans when tasks fail or data is insufficient. Because decisions are based on commonsense reasoning, they are guaranteed to be correct and explainable. We evaluate the feasibility of s(CASP) for UAV control in realistic simulated missions. Results show that our framework enables explainable, adaptive autonomy without retraining, handling complex constraint-aware decisions and dynamic task reevaluation.

Problem

• Autonomous UAV
• Explainable AI
• Dynamic Environments
• Safety-Critical Tasks
• Task Adaptation

Innovation

• s(CASP)
• explainable autonomy
• commonsense reasoning
• constraint-based planning
• symbolic AI