Abstract
Autonomous robotic systems are increasingly deployed for mapping, monitoring, and inspection in complex and unstructured environments. However, most existing path planning approaches remain domain-specific (i.e., in the air, on land, or at sea), limiting their scalability and cross-platform applicability. This article presents OmniPlanner, a unified planning framework for autonomous exploration and inspection across aerial, ground, and underwater robots. The method integrates volumetric exploration and viewpoint-based inspection, alongside target reach behaviors within a single modular architecture, complemented by a platform abstraction layer that captures morphology-specific sensing, traversability and motion constraints. This enables the same planning strategy to generalize across distinct mobility domains with minimal retuning. The framework is validated through extensive simulation studies and field deployments in underground mines, industrial facilities, forests, submarine bunkers, and structured outdoor environments. Across these diverse scenarios, OmniPlanner demonstrates robust performance, consistent cross-domain generalization, and improved exploration and inspection efficiency compared to representative state-of-the-art baselines.
OmniPlanner Framework Overview
OmniPlanner combines a shared planning kernel with an embodiment adaptation layer, enabling the same framework to operate on aerial, ground, and underwater robots. The planning kernel supports uniform, Gaussian, and hybrid sampling together with incremental or batch graph construction. Robot-specific sensing, traversability, and motion constraints are handled by the adaptation layer, while the resulting graph supports volumetric exploration, viewpoint-based inspection, and target-reach behaviors.
Comparison with State-of-the-Art Methods
OmniPlanner is evaluated across its three core behaviors: volumetric exploration, visual inspection, and target reach. Each study uses behavior-specific state-of-the-art baselines under common initial conditions and environment settings. Exploration results are presented as videos, while inspection and target-reach comparisons are illustrated through the resulting paths and trajectories.
Exploration
OmniPlanner is evaluated against complementary state-of-the-art exploration planners covering local next-best-view and tree-based planning, frontier-guided exploration, hierarchical local-global reasoning, and dual-stage viewpoint selection. The aerial comparisons include NBVP [1], ERRT [2], FUEL [3], and GBPlanner 2.0 [4] in cave and confined ballast-water-tank environments. The ground comparison evaluates GBPlanner 2.0, TARE [5], and DSVP [6] in a mine environment, while the underwater comparison evaluates OmniPlanner against NBVP at a submarine crash-site.
Aerial robot: Multi-branch cave environment
Aerial robot: Single-branch cave environment
Aerial robot: Ballast water tank environment
Ground robot: Mine environment
Underwater robot: Submarine crash-site environment
Inspection
In an industrial pipe environment, OmniPlanner is compared with the specialized aerial coverage method FC-Planner [7]. The figure contrasts the inspection paths generated from a common starting location as both planners seek complete exterior-surface coverage.
Target Reach
In a large-scale underground tunnel, OmniPlanner is compared with the visibility-graph-based FAR Planner [8]. The figure shows both ground robots navigating from the same start to four sequential targets while discovering the environment online.
Field Deployments
OmniPlanner was validated through eight fully onboard autonomous deployments using aerial, ground, and underwater robots. The experiments span underground mines, a university campus, forests, a confined industrial tank, and underwater infrastructure, and evaluate volumetric exploration, visual inspection, and target-reach behaviors. The table summarizes the environment characteristics, mission behaviors, path lengths, and mission durations for each deployment.
Aerial Robot Field Deployments
Environment: Underground mine
Environment: Forest
Environment: Ballast water tank
Ground Robot Field Deployments
Environment: Underground mine
Environment: University campus
Environment: Forest (ground-aerial team)
Underwater Robot Field Deployments
Environment: Submarine bunker (exploration-only)
Environment: Submarine bunker (exploration-inspection)
BibTeX
@article{zacharia2026omniplanner,
title = {OmniPlanner: Universal Exploration and Inspection Path Planning Across Robot Morphologies},
author = {Zacharia, Angelos and Dharmadhikari, Mihir and Singh, Mohit and Alexis, Kostas},
journal = {arXiv preprint arXiv:2603.04284},
year = {2026},
url = {https://arxiv.org/abs/2603.04284}
}
Acknowledgements
This work was supported in part by the Research Council of Norway under Grant NCEI (No. 357451) and in part by the European Commission under the Horizon Europe Programme through Grants SYNERGISE (No. 101121321), AUTOASSESS (No. 101120732), SPEAR (No. 101119774), and DIGIFOREST (No. 101070405).
References
- A. Bircher, M. Kamel, K. Alexis, H. Oleynikova, and R. Siegwart, “Receding Horizon ‘Next-Best-View’ Planner for 3D Exploration,” in 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 1462–1468, 2016.
- B. Lindqvist, A. Patel, K. Löfgren, and G. Nikolakopoulos, “A Tree-Based Next-Best-Trajectory Method for 3-D UAV Exploration,” IEEE Transactions on Robotics, vol. 40, pp. 3496–3513, 2024.
- B. Zhou, Y. Zhang, X. Chen, and S. Shen, “FUEL: Fast UAV Exploration Using Incremental Frontier Structure and Hierarchical Planning,” IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 779–786, 2021.
- M. Kulkarni, M. Dharmadhikari, M. Tranzatto, S. Zimmermann, V. Reijgwart, P. De Petris, H. Nguyen, N. Khedekar, C. Papachristos, L. Ott, et al., “Autonomous Teamed Exploration of Subterranean Environments Using Legged and Aerial Robots,” in 2022 International Conference on Robotics and Automation (ICRA), pp. 3306–3313, IEEE, 2022.
- C. Cao, H. Zhu, H. Choset, and J. Zhang, “TARE: A Hierarchical Framework for Efficiently Exploring Complex 3D Environments,” in Robotics: Science and Systems, vol. 5, p. 2, 2021.
- H. Zhu, C. Cao, Y. Xia, S. Scherer, J. Zhang, and W. Wang, “DSVP: Dual-Stage Viewpoint Planner for Rapid Exploration by Dynamic Expansion,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7623–7630, IEEE, 2021.
- C. Feng, H. Li, M. Zhang, X. Chen, B. Zhou, and S. Shen, “FC-Planner: A Skeleton-Guided Planning Framework for Fast Aerial Coverage of Complex 3D Scenes,” in 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 8686–8692, IEEE, 2024.
- F. Yang, C. Cao, H. Zhu, J. Oh, and J. Zhang, “FAR Planner: Fast, Attemptable Route Planner Using Dynamic Visibility Update,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9–16, 2022.