Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

2026-03-05

AI Summary

This work addresses the semantic blindness of traditional safety control methods—such as control barrier functions—which apply uniform avoidance strategies to all obstacles and struggle in complex, dynamic environments. To overcome this limitation, the authors propose a semantic environment modeling framework that fuses multi-sensor point clouds, visual instance segmentation, and persistent object tracking. Building upon this representation, they design a multi-layer safety filter modulated by Poisson safety functions and Laplacian-guided fields. This approach uniquely unifies high-level semantic understanding with low-level safety control, introducing semantic-aware safety margins and multi-agent navigation conventions. The resulting framework enables legged robots to perform context-aware, safe navigation in semantically rich and dynamically evolving environments.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Security and privacy of machine learning and AI applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around obstacles regardless of contextual significance. This limitation leads to the uniform treatment of all obstacles, despite their differing semantic meanings. We present Safe-SAGE (Social-Semantic Adaptive Guidance for Safe Engagement), a unified framework that bridges the gap between high-level semantic understanding and low-level safety-critical control through a Poisson safety function (PSF) modulated using a Laplace guidance field. Our approach perceives the environment by fusing multi-sensor point clouds with vision-based instance segmentation and persistent object tracking to maintain up-to-date semantics beyond the camera's field of view. A multi-layer safety filter is then used to modulate system inputs to achieve safe navigation using this semantic understanding of the environment. This safety filter consists of both a model predictive control layer and a control barrier function layer. Both layers utilize the PSF and flux modulation of the guidance field to introduce varying levels of conservatism and multi-agent passing norms for different obstacles in the environment. Our framework enables legged robots to safely navigate semantically rich, dynamic environments with context-dependent safety margins.

Problem

• semantic blindness
• safety-critical control
• context-dependent safety
• obstacle semantics
• social navigation

Innovation

• Semantic-aware safety
• Poisson safety function
• Laplace guidance field
• Multi-layer safety filter
• Legged robot navigation