A Real-Time Neuro-Symbolic Ethical Governor for Safe Decision Control in Autonomous Robotic Manipulation

TL;DR

This paper introduces a real-time neuro-symbolic ethical governor for autonomous robots, combining ethical reasoning, risk assessment, and override control to enhance safety and transparency in decision-making.

Contribution

It presents a novel neuro-symbolic framework integrating transformer-based ethical inference with probabilistic risk metrics for real-time safety supervision in robotic manipulation.

Findings

Demonstrates stable convergence and reliable ethical risk discrimination.

Improves safety-aware decision outcomes without compromising task efficiency.

Provides enhanced interpretability over purely data-driven methods.

Abstract

Ethical decision governance has become a critical requirement for autonomous robotic systems operating in human-centered and safety-sensitive environments. This paper presents a real-time neuro-symbolic ethical governor designed to enable risk-aware supervisory control in autonomous robotic manipulation tasks. The proposed framework integrates transformer-based ethical reasoning with a probabilistic ethical risk field formulation and a threshold-based override control mechanism. language-grounded ethical intent inference capability is learned from natural language task descriptions using a fine-tuned DistilBERT model trained on the ETHICS commonsense dataset. A continuous ethical risk metric is subsequently derived from predicted unsafe action probability, confidence uncertainty, and probabilistic variance to support adaptive decision filtering. The effectiveness of the proposed approach is validated through simulated autonomous robot-arm task scenarios involving varying levels of human proximity and operational hazard. Experimental results demonstrate stable model convergence, reliable ethical risk discrimination, and improved safety-aware decision outcomes without significant degradation of task execution efficiency. The proposed neuro-symbolic architecture further provides enhanced interpretability compared with purely data-driven safety filters, enabling transparent ethical reasoning in real-time control loops. The findings suggest that ethical decision governance can be effectively modeled as a dynamic supervisory risk layer for autonomous robotic systems, with potential applicability to broader cyber-physical and assistive robotics domains.