An Ontology-driven Dynamic Knowledge Base for Uninhabited Ground Vehicles

TL;DR

The paper addresses the limitation of Uninhabited Ground Vehicles (UGVs) relying on static a priori information, which hampers situational awareness in dynamic environments. It proposes Dynamic Contextual Mission Data (DCMD), an ontology-driven dynamic knowledge base that fuses near-real-time multimodal data with mission-contextual updates at the tactical edge, implemented on a four-UGV team. Key contributions include an ontology-based DCMD representation using BFO/CCO with RO Core relations, an on-board knowledge base in TypeDB, and a data-processing pipeline (image acquisition, YOLOv11-based detection, depth localization, identity/hazard assessment via Bayesian Network inference) that yields machine-actionable, coordinated updates. Experimental results in a lab town scenario show DCMD updates linking detections to a priori records, enabling hazard verification and successful mission completion, thereby enhancing SA and autonomous decision-making at the tactical edge. Overall, the work demonstrates practical mechanisms for real-time, semantically rich knowledge updates enabling coordinated UGV operations under uncertainty.

Abstract

In this paper, the concept of Dynamic Contextual Mission Data (DCMD) is introduced to develop an ontology-driven dynamic knowledge base for Uninhabited Ground Vehicles (UGVs) at the tactical edge. The dynamic knowledge base with DCMD is added to the UGVs to: support enhanced situation awareness; improve autonomous decision making; and facilitate agility within complex and dynamic environments. As UGVs are heavily reliant on the a priori information added pre-mission, unexpected occurrences during a mission can cause identification ambiguities and require increased levels of user input. Updating this a priori information with contextual information can help UGVs realise their full potential. To address this, the dynamic knowledge base was designed using an ontology-driven representation, supported by near real-time information acquisition and analysis, to provide in-mission on-platform DCMD updates. This was implemented on a team of four UGVs that executed a laboratory based surveillance mission. The results showed that the ontology-driven dynamic representation of the UGV operational environment was machine actionable, producing contextual information to support a successful and timely mission, and contributed directly to the situation awareness.

Figures (11)

• Figure 1: DCMD concept
• Figure 2: On-platform DCMD concept implementation for UGVs mission
• Figure 3: Bayesian Network inference model for object and hazard identification.
• Figure 4: Subset of the overall schema for objects of interest identified (rectangles for entities, ellipses for attributes, and diamonds for relations).
• Figure 5: On-board dynamic knowledge bases and their information flows among a team of four UGVs and RCC. The communication among the agents used a Wireless Local Area Network (WLAN) architecture, in which each agent and the RCC wirelessly connect to a central Wireless Access Point (WAP). Color coding of the DCMD in each knowledge base reflects the role-specific contextual information associated with each agent.