Who Went Where When on the Lunar Surface: Forensic Trajectory Analysis to Identify Byzantine Rovers

2026-10-01

AI Summary

This study addresses the challenge of trajectory reconstruction failure in shared multi-lunar-rover environments, where Byzantine-adversarial rovers forge data and conventional methods relying on individual measurement robustness are deceived by internally consistent falsified observations. To overcome this limitation, this work proposes an attribution-aware trajectory estimation framework that shifts the paradigm from per-measurement robustness to holistic rover trustworthiness inference. By integrating sparse telemetry fusion, statistical consistency testing, and credible subset search, the method precisely eliminates malicious observations and reconstructs authentic trajectories via pose graph optimization. Simulation and real-world analog experiments demonstrate that the proposed approach accurately identifies adversarial rovers and achieves significantly superior trajectory reconstruction accuracy compared to existing baselines.

Abstract

Future planetary surface missions are likely to involve multiple independently operated rovers sharing the same deployment region, raising the need to verify compliance with operational constraints such as Lunar Safety Zones. Because continuous in-situ observability is rarely available, such verification requires post-hoc reconstruction of rover trajectories from sparse telemetry, including odometry, pose priors, and relative inter-rover detections. We introduce the problem of forensic trajectory analysis for non-cooperative planetary rovers in the presence of Byzantine agents: rovers that provide miscalibrated or deliberately falsified measurements to support an incorrect trajectory. We show that standard outlier-robust pose graph optimisation methods are vulnerable in this setting, because Byzantine rovers can generate measurements that are internally consistent and numerous enough to make truthful incriminating measurements appear as outliers. To address this, we propose an attribution-aware trajectory estimation method that reasons over rover credibility rather than individual measurement validity. The method evaluates candidate credible rover subsets by comparing the statistical consistency of their internal and boundary relative detections against provided priors, and then estimates trajectories using only measurements attributed to credible agents. Across synthetic simulations and real planetary-analogue trajectory data, the proposed method identifies Byzantine rovers and produces significantly more accurate trajectory estimates than existing robust pose graph optimisation baselines.

Problem

• Forensic Trajectory Analysis
• Byzantine Rovers
• Pose Graph Optimisation
• Planetary Surface Missions
• Non-cooperative Agents

Innovation

• Forensic Trajectory Analysis
• Byzantine Agents
• Attribution-aware Estimation
• Pose Graph Optimization
• Credibility Reasoning