Perception-Aware Autonomous Exploration in Feature-Limited Environments

Moji Shi; Rajitha de Silva; Hang Yu; Riccardo Polvara; Marija Popović

cs.ROMar 16, 2026

Perception-Aware Autonomous Exploration in Feature-Limited Environments

Authors: Moji Shi, Rajitha de Silva, Hang Yu, Riccardo Polvara, Marija Popović

Organizations: MAVLab, TU Delft, Netherlands · Lincoln Center for Autonomous Systems (L-CAS), School of Engineering and Physical Sciences, University of Lincoln, UK

Abstract

Autonomous exploration in unknown environments typically relies on onboard state estimation for localisation and mapping. Existing exploration methods primarily maximise coverage efficiency, but often overlook that visual-inertial odometry (VIO) performance strongly depends on the availability of robust visual features. As a result, exploration policies can drive a robot into feature-sparse regions where tracking degrades, leading to odometry drift, corrupted maps, and mission failure. We propose a hierarchical perception-aware exploration framework for a stereo-equipped unmanned aerial vehicle (UAV) that explicitly couples exploration progress with feature observability. Our approach (i) associates each candidate frontier with an expected feature quality using a global feature map, and prioritises visually informative subgoals, and (ii) optimises a continuous yaw trajectory along the planned motion to maintain stable feature tracks. We evaluate our method in simulation across environments with varying texture levels and in real-world indoor experiments with largely textureless walls. Compared to baselines that ignore feature quality and/or do not optimise continuous yaw, our method maintains more reliable feature tracking, reduces odometry drift, and achieves on average 30% higher coverage before the odometry error exceeds specified thresholds.

Figures & tables

Fig. 1: Our approach for perception-aware exploration applied on a UAV. (a) Odometry trajectory during an exploration task (blue arrows); arrow headings indicate the planned yaw angle. (b) Corresponding camera view. Our method maintains reliable feature tracking during exploration.

Fig. 2: Our perception-aware exploration framework. Two key components are frontier selector and perception-aware trajectory optimisation.

Fig. 3: Our frontier selector. Frontier voxels are clustered by proximity, and candidate viewpoints are sampled from known free space to observe the frontiers. Visual features are overlaid, where blue intensity indicates feature quality: textured obstacles yield more and higher-quality features than textureless surfaces. Our selector prefers bottom-left viewpoints, which are farther from the current UAV position but provide stronger feature support than closer viewpoints.

Fig. 4: Our yaw angle trajectory optimisation procedure. Dashed field of view sectors represent the waypoint yaws $\{\psi_{j}\}$ and arrows with different colours show covisible feature sets $\{\mathcal{F}_{j}\}$ . The zoomed-in view shows the calculation of the relative angular velocity. For any point on trajectory, we decompose the velocity $\dot{\mathbf{p}_{j}}(t)$ in the direction of the feature vectors $\mathbf{f}_{i}-\mathbf{p}_{j}(t)$ and the perpendicular direction, expecting the yaw rate to compensate the relative angular velocity.

Fig. 6: Frame-averaged spatial distribution of tracked visual features in the image plane during exploration. The axes show the pixel coordinates $(u,v)$ . For each frame, we build a 2D histogram of tracked feature locations and then average the histogram over time across the entire exploration run; colour indicates the normalised mean feature count per bin.

Fig. 7: Number of tracked visual features per frame during exploration. The $x$ -axis shows normalised exploration progress, defined as the explored free-space volume divided by the total explored volume at run completion. The $y$ -axis reports the number of features successfully tracked per frame. Solid lines show the mean over $10$ runs; shaded areas indicate one standard deviation.

Method	High-Texture Map Exploration Rate			Medium-Texture Map Exploration Rate			Low-Texture Map Exploration Rate
Method	1.0 m	2.0 m	3.0 m	1.0 m	2.0 m	3.0 m	1.0 m	2.0 m	3.0 m
Ours	0.913 $\pm$ 0.065	0.913 $\pm$ 0.065	0.924 $\pm$ 0.049	0.888 $\pm$ 0.070	0.928 $\pm$ 0.044	0.928 $\pm$ 0.044	0.326 $\pm$ 0.169	0.427 $\pm$ 0.126	0.470 $\pm$ 0.139
FUEL	0.728 $\pm$ 0.291	0.846 $\pm$ 0.207	0.868 $\pm$ 0.182	0.651 $\pm$ 0.311	0.731 $\pm$ 0.257	0.802 $\pm$ 0.175	0.224 $\pm$ 0.078	0.271 $\pm$ 0.100	0.317 $\pm$ 0.128
FUEL + PA Frontier	0.815 $\pm$ 0.085	0.828 $\pm$ 0.058	0.828 $\pm$ 0.058	0.667 $\pm$ 0.147	0.771 $\pm$ 0.093	0.771 $\pm$ 0.093	0.321 $\pm$ 0.202	0.337 $\pm$ 0.206	0.325 $\pm$ 0.203
LA	0.234 $\pm$ 0.094	0.235 $\pm$ 0.093	0.235 $\pm$ 0.093	0.202 $\pm$ 0.093	0.220 $\pm$ 0.082	0.239 $\pm$ 0.093	0.142 $\pm$ 0.064	0.162 $\pm$ 0.071	0.176 $\pm$ 0.087
LA + PA Frontier	0.023 $\pm$ 0.005	0.023 $\pm$ 0.005	0.023 $\pm$ 0.005	0.048 $\pm$ 0.020	0.048 $\pm$ 0.020	0.048 $\pm$ 0.020	0.052 $\pm$ 0.033	0.053 $\pm$ 0.034	0.054 $\pm$ 0.035

TABLE I: Success exploration rate (expressed as mean

\pm

std dev) under different odometry error thresholds (

1.0\,\mathrm{m}

2.0\,\mathrm{m}

3.0\,\mathrm{m}

) on environments ordered by texture richness (High

\rightarrow

Low). Best per column in bold .

Fig. 8: Exploration process in Medium-Texture map. Blue and green lines indicate the odometry and ground-truth pose. Blue arrows indicate yaw angles. Our perception-aware approach enables looking at known features (bottom-left).

Fig. 9: Feature tracking comparison for ablation study. Brighter colours indicate a higher number of tracked features in the image plane. Removing either key component reduces feature intensity, indicating degraded feature tracking.

Method	Low-Texture Map Exploration Rate
Method	1.0 m	2.0 m	3.0 m
Ours	0.326 $\pm$ 0.169	0.427 $\pm$ 0.126	0.470 $\pm$ 0.139
Ours w/o PA Frontier	0.162 $\pm$ 0.123	0.185 $\pm$ 0.131	0.209 $\pm$ 0.130
Ours w/o Yaw Optim.	0.300 $\pm$ 0.057	0.368 $\pm$ 0.047	0.404 $\pm$ 0.059

TABLE II: Exploration success rate comparison for ablation study under different odometry error thresholds. Best in bold .

Map	Mean total feature number	Mean error (m)
Sparse Layout	519.7	1.0188
Dense Layout	969.3	0.8204

TABLE III: Results across two real-world layouts.

Fig. 10: Real-world experiment results in Dense Layout . (a) Part of the exploration process from top-down view. White arrows show the camera directions. (b) Camera field of view. Orange denotes visual features currently tracked by the UAV, and white denotes other obstacles. (c) Global feature map overlaid on the occupancy map: feature quality is colour-coded (blue: low score, red: high score), illustrating that high-quality features concentrate on textured obstacles.

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

Semantic-Aware Autonomous Exploration for UAVs in Unknown Indoor Environments
Jun 21, 2026Duc-Thien Nguyen, Ngoc Minh Do, Xiem HoangVan +1Robot Navigation Informative Path Planning
University of Engineering and Technology, Vietnam National University, 10000, Hanoi, Vietnam. · School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, 923-1211, Ishikawa, Japan.
UNSEEN: Uncertainty-aware Navigation via Sparse Estimation in Unknown Environments
Jun 18, 2026Tommaso Faraci, Marco Camurri, Daniele Fontanelli +1Belief-Space Planning Simultaneous Localization and Mapping
University of Trento, Italy
Palm-sized Omnidirectional Vision-Based UAV Exploration with Sparse Topological Map Guidance
May 8, 2026Zirui Wang, Xinjia Luo, Haotian Sun +3Robot Navigation UAV Navigation
Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen, 518055, China

Jun 21, 2026J/K move · Enter open · S save

Semantic-Aware Autonomous Exploration for UAVs in Unknown Indoor Environments

Duc-Thien Nguyen, Ngoc Minh Do, Xiem HoangVan, Thanh Nguyen Canh

University of Engineering and Technology, Vietnam National University, 10000, Hanoi, Vietnam. · School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, 923-1211, Ishikawa, Japan.

Robot Navigation Informative Path Planning UAV Navigation Sampling-Based Motion Planning

Open paper AskPDF arXiv

Autonomous exploration in unknown environments requires unmanned aerial vehicles (UAVs) to efficiently generate informative trajectories while simultaneously constructing accurate maps. Although many existing exploration methods rely on geometric information, they often lack semantic awareness, resulting in suboptimal exploration efficiency and limited environmental understanding. To address this limitation, this paper proposes a semantic-aware exploration framework that adds semantic information to a roadmap-based exploration strategy. The proposed method builds on the Dynamic Exploration Planner (DEP), which incrementally constructs a Probabilistic Roadmap (PRM), and augments this roadmap with a semantic layer. A semantic reward function is introduced to prioritize regions containing meaningful objects and structures, enabling the UAV to focus on areas with higher information value. Furthermore, the roadmap is continuously updated to support efficient frontier selection and path planning during exploration. The proposed framework is implemented in ROS Noetic and Gazebo using an RGB-D sensor for simultaneous acquisition of geometric and semantic information. Experimental results in multiple simulated environments demonstrate that the proposed approach achieves exploration coverage rates between 90% and 94% while reducing exploration time and travel distance compared with conventional geometry-based exploration methods.

Abstract

UAV Navigation

Explore similar work

Semantic-Aware Autonomous Exploration for UAVs in Unknown Indoor Environments

UNSEEN: Uncertainty-aware Navigation via Sparse Estimation in Unknown Environments

Palm-sized Omnidirectional Vision-Based UAV Exploration with Sparse Topological Map Guidance