What does this research mean for the field?

A modular autonomy stack integrating lidar-IMU odometry, exploration planning, and real-time object detection enables effective robotic artifact localization in structured subterranean environments, though performance significantly degrades in steep or cluttered terrains. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop and evaluate a modular autonomy stack for autonomous underground exploration, object detection, and localization across diverse simulated subterranean environments.

September 3, 2026Konya Journal of Engineering SciencesOpen Access

Autonomous Robotic Exploration and Artifact Localization in Subterranean Environments

View Full Paper

Ask AI

Bookmark

Authors

KBKieran Bagot MKMuhammed Zahid KarakusakIstanbul Medipol University HKHasan KivrakEskişehir Osmangazi University

Discussion

Member takes

Implication

Simulation study demonstrates modular robotic exploration and artifact localization across subterranean environments, indicating high urban accuracy but degraded coverage in steep, cluttered terrain.

Key Points

To develop and evaluate a modular autonomy stack for autonomous underground exploration, object detection, and localization across diverse simulated subterranean environments.
Integrated LIO-SAM for lidar-inertial odometry, GBPlanner2 coupled with a pure-pursuit path tracker for exploration planning, and YOLOv3 for real-time visual artifact detection with depth-based localization.
Evaluated the modular autonomy stack across three virtual simulated circuits representing cave, tunnel, and urban environments to quantify exploration coverage, odometry drift, and detection error.
The autonomy stack achieved its highest performance in the urban circuit, localizing multiple target artifacts with low horizontal odometry drift.
System exploration coverage and reliability degraded substantially in steep or cluttered subterranean terrains due to sensor observability limits and path collision-checking failures.

Cite This Study

Bagot et al. (2026) studied this question.

synapsesocial.com/papers/6a9935a0636c6408cfa7dff9 https://doi.org/10.36306/konjes.1766861

View Full Paper

Ask AI

Bookmark

Implication

Simulation study demonstrates modular robotic exploration and artifact localization across subterranean environments, indicating high urban accuracy but degraded coverage in steep, cluttered terrain.

Autonomous Robotic Exploration and Artifact Localization in Subterranean Environments

Discussion

Member takes

Implication

Key Points

Cite This Study

Autonomous Robotic Exploration and Artifact Localization in Subterranean Environments

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider