Micro aerial vehicles (MAVs) enable rapid indoor 3D reconstruction for inspection and time-critical situational awareness, but must operate under strict flight-time budgets and safety constraints that require explicit return-to-home (RTH) feasibility with a conservative margin. We present a topology-first active reconstruction framework that decouples high-fidelity rendering from navigation. A dense 3D Gaussian Splatting (3DGS) map is optimized as the reconstruction target, while a lightweight Truncated Signed Distance Field (TSDF)/occupancy scaffold supports conservative collision checking and online construction of a sparse 3D Voronoi skeleton roadmap. Since directly extracting roadmaps from TSDF geometry can be unstable under noisy and incomplete online fusion, we validate nodes and edges using carved free-space consistency and dense visibility checks, which suppress behind-wall phantom structure and stabilize planning. Viewpoints are selected on the roadmap using a flight-time-budget-aware objective and a lightweight receding-horizon lookahead to improve non-myopic exploration behavior. We evaluate on photorealistic indoor simulation benchmarks (ReplicaCAD, Gibson, and HM3D), reporting reconstruction coverage/error, RTH success, and computational cost. Results demonstrate improved or competitive performance relative to recent GS-based baselines under identical flight-time budgets.
Figures & tables
Figure 1: Exploration and reconstruction of hazardous buildings must explicitly account for the return-to-home (RTH) constraint to ensure safe MAV recovery.
Figure 2: System Overview . Our proposed framework integrates Online 3D Gaussian Splatting (3DGS) for high-fidelity reconstruction with a Voronoi-based roadmap for efficient navigation. The Budgeted Next-Best-View (NBV) Planner dynamically balances information gain against remaining budget to ensure feasible, long-horizon exploration.
Figure 3: Free-space node injection. (a) Volumetric visualization of the explicitly carved free-space grid F in a wide-open environment. (b) The resulting 3D Voronoi roadmap, where orange segments show the raw Voronoi graph clustered near perimeter walls, and black segments show synthetically injected nodes and bridging edges that use F to safely reduce coverage gaps.
Figure 4: Qualitative 3DGS map snapshots over mission time, showing how the flight-time-aware planner first prioritizes rapid global exploration and later shifts toward local surface refinement as the time budget decreases.
Metric
Overall
Gibson
HM3D
Mean exploration time Texp (s)
124.6
110.5
188.2
Mean RTH time Trth (s)
20.3
17.8
31.3
Exploration fraction Texp/B (%)
79.3
79.4
78.4
RTH fraction Trth/B (%)
12.2
12.1
13.0
Other overhead (%) †
8.5
8.5
8.6
Table III: RTH budget utilization for Ours (w/ RTH) . Texp is the time spent exploring before the RTH trigger; Trth is the time spent returning home after the trigger.