SafeNav: Safe Path Navigation using Landmark Based Localization in a GPS-denied Environment

TL;DR

This work tackles navigation in GPS-denied battlefield environments by combining landmark-based localization (LanBLoc) with a Battlefield Motion Model (BMM) and EKF to estimate trajectories, and introduces SafeNav-CHull and SafeNav-Centroid with a Risk-Aware RRT* planner to minimize hazard exposure. LanBLoc-BMM(EKF) demonstrates superior ADE, FDE, and AWRS on real-trajectory data, confirming robust localization and safe path tracking without GPS. The SafeNav variants show a strong balance between accuracy, safety, and computation, with SafeNav-Centroid delivering the shortest, least-risk trajectories and SafeNav-CHull offering faster computation. The proposed framework advances autonomous battlefield navigation by leveraging landmark cues, non-GPS motion modeling, and risk-aware planning to enhance operational effectiveness and safety.

Abstract

In battlefield environments, adversaries frequently disrupt GPS signals, requiring alternative localization and navigation methods. Traditional vision-based approaches like Simultaneous Localization and Mapping (SLAM) and Visual Odometry (VO) involve complex sensor fusion and high computational demand, whereas range-free methods like DV-HOP face accuracy and stability challenges in sparse, dynamic networks. This paper proposes LanBLoc-BMM, a navigation approach using landmark-based localization (LanBLoc) combined with a battlefield-specific motion model (BMM) and Extended Kalman Filter (EKF). Its performance is benchmarked against three state-of-the-art visual localization algorithms integrated with BMM and Bayesian filters, evaluated on synthetic and real-imitated trajectory datasets using metrics including Average Displacement Error (ADE), Final Displacement Error (FDE), and a newly introduced Average Weighted Risk Score (AWRS). LanBLoc-BMM (with EKF) demonstrates superior performance in ADE, FDE, and AWRS on real-imitated datasets. Additionally, two safe navigation methods, SafeNav-CHull and SafeNav-Centroid, are introduced by integrating LanBLoc-BMM(EKF) with a novel Risk-Aware RRT* (RAw-RRT*) algorithm for obstacle avoidance and risk exposure minimization. Simulation results in battlefield scenarios indicate SafeNav-Centroid excels in accuracy, risk exposure, and trajectory efficiency, while SafeNav-CHull provides superior computational speed.

Figures (5)

• Figure 1: A battlefield environment cluttered with landmark clusters, obstacles, and hazard components. The safe path buffer starting from centroid cluster 4 and ending at the centroid of cluster 3 indicates a risk-free zone, guides the moving entity safely in avoiding obstacles, and minimizes risk exposure.
• Figure 2: An Overview of Safe Path Navigation Framework for GPS-denied Environment using Battlefield Motion Model (BMM), Extended Kalman Filter (EKF), and safety-checking algorithms (CHull and Centroid).
• Figure 3: Comparison of Weighted Risk Exposure of EKF-based Algorithms. Fig \ref{['wrs-comparisions']}.1(a) and \ref{['wrs-comparisions']}.1(b) show the overall WRS performance of four localization algorithms while using EKF and PF, respectively. The Fig \ref{['wrs-comparisions']}.2(a),\ref{['wrs-comparisions']}.2(b),\ref{['wrs-comparisions']}.2(c) and \ref{['wrs-comparisions']}.2(d) shows the individual comparison of weighted risk score(WRS) for EFK and PF integration across each of the four localization algorithms.
• Figure 4: Showing Safe Path Navigation using SafeNav-Chull and RAw-RRT* in three different path types obtained from the combination of different landmark clusters and starting points that guide to the common destination (cluster 3). Fig. \ref{['safe_path_chull']} (a) shows the path type 1 (P1) from the centroid of cluster 6 to cluster 3. Fig. \ref{['safe_path_chull']} (b) shows the path type 2 from cluster 4 to cluster 3, and Fig. \ref{['safe_path_chull']} (c) shows the path type 3 (P3) from cluster 7 to cluster 3. The color coding on each path type represents the convex hull of the path segments. The actual and observed trajectories of moving entities within each path type are shown by red and blue lines, respectively.
• Figure 5: Showing Safe Path Navigation using SafeNav-Centroid and RAw-RRT* in three different path types obtained from the combination of different landmark clusters and starting points that guide to the common destination (cluster 3). Fig. \ref{['safe_path_centroid']} (a) shows the path type 1(P1) from the centroid of cluster 6 to cluster 3. Fig. \ref{['safe_path_centroid']} (b) shows the path type 2 from cluster 4 to cluster 3 and Fig. \ref{['safe_path_centroid']} (c) shows the path type 3 (P3) from cluster 7 to cluster 3. The actual and observed trajectories of moving entities within each path type are shown by red and blue lines, respectively.