Omni-IGN: Onboard Image-Goal Navigation for Drones with Omnidirectional Vision

Zichen Yan; Rui Huang; Shenao Wang; Yucong Wang; Nuthasith Gerdpratoom; Lin Zhao

cs.ROOct 27, 2026

Omni-IGN: Onboard Image-Goal Navigation for Drones with Omnidirectional Vision

Authors: Zichen Yan, Rui Huang, Shenao Wang, Yucong Wang, Nuthasith Gerdpratoom, Lin Zhao

Organizations: Department of Electrical and Computer Engineering, National University of Singapore, Singapore.

Abstract

Image-goal navigation (ImageNav) requires an agent to reach a location specified by a goal image in an unknown environment. For drones, this task demands exploration, goal- directed navigation, and collision avoidance under limited onboard computing resources. Existing aerial ImageNav methods are built on single-view observations, requiring additional rotation and exploration to search for goal-relevant cues outside the field of view. In this paper, we present Omni-IGN, a fully onboard ImageNav system that integrates quad-fisheye perception, an attention-based reinforcement learning (RL) policy, and a collision-aware safety layer. The policy adaptively fuses goal-relevant features across multiple views to provide directional guidance for continuous navigation. The quad-fisheye RGB images support both ImageNav and obstacle avoidance without a dedicated depth sensor. On Habitat benchmarks, Omni-IGN achieves the best performance among continuous-action baselines. Moreover, flight tests in IsaacSim validate the effectiveness of integrating learning-based depth estimation with the action safety layer for collision avoidance. Finally, real-world experiments demonstrate zero-shot sim-to-real transfer without any fine-tuning or external localization. The code and model checkpoints will be released upon acceptance.

Figures & tables

Panel of Figure 1 — Fig. 1: System design and data flow of Omni-IGN. The drone is equipped with a Jetson Orin NX 16G onboard computer, an OAK-4P-New quad-fisheye camera rig, and a Livox Mid-360s LiDAR. Rectified images from the four fisheye cameras are fed to the RL navigation policy, while overlapping views between the front camera and its left and right neighbors are used for stereo depth estimation and obstacle avoidance. The velocity command passes through a safety layer before being sent to the flight controller. Meanwhile, LiDAR provides state estimates required for closed-loop control.

Fig. 2: Overview of the navigation model. The RGB image from each direction is stacked with the target image and encoded by a shared ResNet. The resulting per-view features are adaptively fused by a self-attention module and passed to a GRU together with the previous action. The actor-critic head then predicts continuous actions.

Fig. 3: Stereo depth estimation pipeline. (a) Fisheye images are frame-synchronized and captured at 30 Hz. (b) The front camera forms two stereo pairs, $\mathcal{P}_{1}=(C_{2},C_{1})$ and $\mathcal{P}_{2}=(C_{2},C_{3})$ , with the left and right cameras, respectively. Each pair is rectified into aligned pinhole images. (c) Fast-FoundationStereo produces disparity maps $D_{1}$ and $D_{2}$ for both pairs. (d) The disparity maps are converted to depth and stitched together, then reduced over the central $90^{\circ}$ FoV to a 16-bin range scan for collision prediction.

Fig. 4: Stereo rectification of the quad-fisheye views. (a) Rectified frame construction for the two stereo pairs. For $\mathcal{P}_{1}$ , $C_{1}$ and $C_{2}$ supply the left and right rectified views, respectively. (b) Real fisheye observations and their rectified views for $\mathcal{P}_{1}$ . The dashed curves in the fisheye images are mapped to aligned image rows.

Fig. 5: Action safety layer based on estimated depth for collision avoidance.

Fig. 6: Comparison experiments between Omni-IGN and single-view baseline on the same episodes from HM3D, Gibson, and MP3D. Left: navigation trajectories on the top-down map. Right: the goal image, the single-view and panoramic-view observations at the endpoint.

Method	Backbone	Sensor(s)	Action Space	SPL( $\uparrow$ )	SR( $\uparrow$ )
ZER [ 14 ]	ResNet9	RGB	Discrete	21.6%	29.2%
OVRL-V2 [ 15 ]	ViT-Base	RGB	Discrete	58.7%	82.0%
FGPrompt [ 16 ]	ResNet9	RGB	Discrete	66.5%	90.4%
Mem-Aug [ 21 ]	ResNet18	4 RGB	Discrete	56.0%	69.0%
VGM [ 20 ]	ResNet18	4 RGB	Discrete	64.0%	76.0%
TSGM [ 10 ]	ResNet18	4 RGB	Discrete	67.2%	81.1%

TABLE I: Comparison with SOTA methods on Gibson.

Methods	Action Space	MP3D		HM3D
Methods	Action Space	SPL( $\uparrow$ )	SR( $\uparrow$ )	SPL( $\uparrow$ )	SR( $\uparrow$ )
ZER [ 14 ]	Discrete	$10.8\%$	$14.6\%$	$6.3\%$	$9.6\%$
TSGM [ 10 ]	Discrete	$47.3\%$	$58.0\%$	$46.9\%$	$64.1\%$
FGPrompt (1-RGB)	Discrete	$50.4\%$	$77.6\%$	$49.6\%$	$76.1\%$
FGPrompt (1-RGB)	Continuous	$22.9\%$	$59.4\%$	$20.1\%$	$56.5\%$
SIGN [ 4 ]	Continuous	$35.0\%$	$65.4\%$	$30.9\%$	$64.5\%$

TABLE II: Cross-domain evaluation on MP3D and HM3D.

Fig. 7: Reliability test in the IsaacSim pole environment. (a) The layout of the pole environment. (b) Flight trajectories for each start-end pair, with collision cases marked in red. (c) Stereo-based depth estimation at the location marked by the red star in (b). Top: left and right RGB views of the front-left and front-right stereo pairs and their estimated depth. Bottom: the two depth maps are stitched and cropped to form the range scan.

	Navigation			Depth Error (m)
Pair	SR( $\uparrow$ )	SPL( $\uparrow$ )	Correction Rate(%)	Mean( $\downarrow$ )	Max( $\downarrow$ )
S1-E1	10/10	0.93	30.4	0.17	1.13
S1-E2	10/10	0.96	14.0	0.10	0.80
S1-E3	10/10	0.91	28.8	0.17	1.09
S2-E1	10/10	0.99	18.1	0.13	1.04
S2-E2	10/10	0.94	23.5	0.13	1.00

TABLE III: Reliability test of collision avoidance and depth estimation over 90 flights in IsaacSim.

Panel of Figure 11 — Fig. 8: Evolution of view-attention weights during two real-world ImageNav flights in the Lab. Panels (I-a) and (II-a) show the trajectories and goal images. (I-b) and (II-b) show the four camera views and normalized attention scores at five sampled steps. (I-c) and (II-c) show the attention distributions over time. Red boxes highlight the view with the highest attention score.

Fig. 9: Evolution of view attention during a real-world ImageNav flight in a cluttered office. Attention is broadly distributed during exploration and becomes increasingly focused on the forward view during the final approach.

Fig. 10: Real-world stereo depth estimation in the lab and office environments. The left, forward, and right RGB views are shown together with the corresponding stitched stereo depth predictions.

UAV Navigation

Unmanned aerial vehicle (UAV) navigation develops methods for locating and guiding drones safely through known, unknown, and changing environments.

See all 272 papers

AION: Aerial Indoor Object-Goal Navigation Using Dual-Policy Reinforcement Learning
Jan 22, 2026Zichen Yan, Yuchen Hou, Shenao Wang +3RL for Robotics Aerial Robotics
Department of Electrical and Computer Engineering, National University of Singapore, Singapore.
AirDreamer: Generalist Drone Navigation with World Models
Jun 2, 2026Zian Liu, Andong Yang, Chunkai Yang +3RL for Robotics World Models for Robotics
Institute for AI Industry Research, Tsinghua University, Beijing, China. · Department of Electronic Engineering, Tsinghua University, Beijing, China. · School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China.
Fly360: Omnidirectional Obstacle Avoidance within Drone View
Mar 6, 2026Xiangkai Zhang, Dizhe Zhang, WenZhuo Cao +5UAV Navigation Robot Collision Avoidance
Institute of Automation Chinese Academy of Sciences, Beijing, China · Insta360 Research, Shenzhen, China · Wuhan University,Wuhan, China.

Jan 22, 2026J/K move · Enter open · S save

AION: Aerial Indoor Object-Goal Navigation Using Dual-Policy Reinforcement Learning

Zichen Yan, Yuchen Hou, Shenao Wang, Yichao Gao+2

Department of Electrical and Computer Engineering, National University of Singapore, Singapore.

RL for Robotics Aerial Robotics Vision-Based Robot Control Object-Goal Navigation

Open paper AskPDF arXiv

Object-Goal Navigation (ObjectNav) requires an agent to autonomously explore an unknown environment and navigate toward target objects specified by a semantic label. While prior work has primarily studied zero-shot ObjectNav under 2D locomotion, extending it to aerial platforms with 3D locomotion capability remains underexplored. Aerial robots offer superior maneuverability and search efficiency, but also introduce new challenges in spatial perception, dynamic control, and safety assurance. In this paper, we propose AION for vision-based aerial ObjectNav without relying on external localization or global maps. AION is an end-to-end dual-policy reinforcement learning (RL) framework that decouples exploration and goal-reaching behaviors into two specialized policies. We evaluate AION on the AI2-THOR benchmark and further assess its real-time performance in IsaacSim using high-fidelity drone models. Experimental results show that AION achieves superior performance across comprehensive evaluation metrics in exploration, navigation efficiency, and safety. The project is available at https://github.com/Zichen-Yan/AION.

Abstract

UAV Navigation

Explore similar work

AION: Aerial Indoor Object-Goal Navigation Using Dual-Policy Reinforcement Learning

AirDreamer: Generalist Drone Navigation with World Models

Fly360: Omnidirectional Obstacle Avoidance within Drone View