Benchmarking Visual-Inertial Odometry in Subterranean Environments Under Sensor Degradation, Miscalibration, and Dynamic Occlusion

arXiv:2609.18628 · cs.RO · Submitted 2026-09-16 · Read on arXiv

cs.RO

Submitted: 2026-09-16

Updated: 2026-09-16

Terminology

• Calibration — 16× in this paper · explained in 7 episodes
• Robustness — 14× in this paper · explained in 5 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Benchmarking — 9× in this paper · explained in 3 episodes
• Consistency — 8× in this paper · explained in 3 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Redundancy — 5× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Visual-Inertial Odometry — 4× in this paper
• Absolute Trajectory Error — 2× in this paper
• Alignment — 2× in this paper · explained in 1 episode
• Bundle Adjustment — 2× in this paper
• Factor Graph Optimization — 2× in this paper
• Extended Kalman Filter — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Root Mean Square Error — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors
• Benchmarking SLAM Algorithms in the Cloud: The SLAM Hive Benchmarking Suite

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving