OPAL: Omnidirectional Path-efficient Aerial 3D expLoration
2026-05-25 • Robotics
Robotics
AI summaryⓘ
The authors introduce OPAL, a method for drones to explore unknown spaces by turning fully around at decision points instead of planning long routes all at once. They test different versions of OPAL, some using AI language models to help decide where to go next. While OPAL takes more time because of the turning, it uses less computing power and helps the drone travel shorter distances overall. The team also shows that changing how far the drone looks around can balance travel distance and exploration speed. Real-world tests with a drone showed OPAL can reduce travel distance by up to 25% compared to another method called FALCON.
autonomous explorationfrontier selectionyaw rotationaerial 3D mappinglarge language modelsvision-language modelstravel distanceexploration timerobot mappingdrone navigation
Authors
Yoga Satwik Chappidi, Avideh Zakhor
Abstract
Autonomous exploration is critical for robot mapping unknown environments. Desirable characteristics of exploration algorithms include compute efficiency and small traversed distance during the exploration process. Motivated by these, we present Omnidirectional Path-efficient Aerial 3D expLoration (OPAL), an exploration framework centered on deliberate 360-degree yaw rotation at ambiguous branch points rather than compute-heavy global tour planning. We devise multiple variants of OPAL to determine the frontier-selection strategy once the yaw pan is completed. One variant is model-free, while others use large language models (LLMs) or vision-language models (VLMs). We characterize the performance of these variants while varying the vicinity search radius to include frontiers in the selection process. Through simulations we find that although the time-consuming in-place yaw rotation increases total exploration time relative to more computationally complex baselines such as EDEN and FALCON, OPAL is computationally simpler and achieves shorter travel distances and higher coverage-versus-distance area under the curve. We also show that adjusting the frontier-selection search radius enables a tradeoff between travel distance and total exploration time. We verify our results on a Modal AI drone in two indoor environments by comparing OPAL against FALCON, and find that the traveled distance for a variant of OPAL to be as much as 25% lower than FALCON.