Visual navigation in cluttered environments requires robots to recover previously observed structure and infer obstacles and free space that remain occluded. We present a framework that combines temporal aggregation and occupancy completion in an evidential bird's-eye-view (BEV) representation predicted from short RGB sequences. A decoder adapts frozen VGGT-Omega features and combines historical residual proposals using cellwise weights and a learned no-update option. The BEV predictor produces a local map in the latest ego frame without depth or camera-pose inputs or explicit geometric warping. The evidential model treats observed free space separately and predicts occupancy with associated confidence across the remaining supported region. We train the predictor on simulated RGB sequences paired with complete and visibility-masked occupancy annotations. Our experiments evaluate navigation in simulation and on a wheeled robot, with additional demonstrations on quadruped and humanoid robots. In simulated sequential two-goal navigation, our system achieves 89.6% success, outperforming the strongest evaluated baseline by 32.5 percentage points. Across 60 wheeled-robot trials in 20 scenes, it achieves 73.3% success, compared with 33.3% for the strongest evaluated baseline.
Figures & tables
Fig. 2: Overview of the proposed framework. Frozen VGGT-Omega features from an RGB window are adapted into feature pyramids and frame memories. Historical residual proposals refine a latest-frame BEV anchor through cellwise selective fusion with a learned no-update option. Observation-aware evidential heads produce occupancy, spatial support, and confidence. Right: predicted occupancy with paths to example goals, planned path projections into the latest RGB view, and uncertainty 1−cj .
Fig. 3: Qualitative BEV comparison on a common 10×10 m grid. Rows (a)–(c) show Gibson, HM3D, and HSSD examples, respectively. We compare our method with VGGT-Omega, DiScene, SplatSSC, OccAnt-RGB, and OccAnt-RGBD. All methods use RGB observations; OccAnt-RGBD additionally receives depth. In the predicted maps, dark blue, blue-gray, and off-white denote occupied, free, and unknown cells, respectively.
Method
mIoU U
IoU O
mIoU G
CovG
Single image: 3.25×3.25 m
DiScene
43.21
97.28
32.02
100.00
SplatSSC
40.58
94.97
31.11
100.00
VGGT-Omega
42.62
53.12
44.26
13.06
OccAnt-RGB
32.40
44.88
33.88
39.14
OccAnt-RGBD
63.96
81.57
55.16
56.32
TABLE I: Occupancy Prediction Results
Fig. 4: Simulation navigation on two 1,000-task benchmarks: (a) hidden-goal navigation and (b) sequential navigation. Panel (a) reports SR and SPL; panel (b) reports SPL for goal A and goals A+B. SCPR uses each method’s successful episodes. Methods below the red dashed lines use depth sensors.
1ERA Lab, University of South Florida, Florida, USA · University of Maryland- College Park, College Park, Maryland · 2YES Lab, University of South Florida, Florida, USA