Perception-aware Exploration for Consumer-grade UAVs

2025-11-18

AI Summary

To address computational, sensor, and communication limitations of consumer-grade drones (e.g., DJI Mini 3 Pro), this work proposes a lightweight multi-UAV collaborative autonomous exploration framework. Methodologically, it introduces a perception-guided viewpoint selection mechanism that jointly incorporates depth estimability assessment and motion constraints for safe trajectory planning; further, it establishes a semi-distributed communication architecture enabling dynamic task allocation and VIO-compatible collaborative exploration. The key contribution is the first adaptation of state-of-the-art multi-UAV exploration paradigms to resource-constrained consumer platforms. Extensive simulations validate stable, safe exploration and high-fidelity 3D mapping with 2–6 drones under limited onboard computation and narrow communication bandwidth—demonstrating significantly improved hardware practicality and algorithm deployment feasibility.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Computer Vision: Multi-modal Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

In our work, we extend the current state-of-the-art approach for autonomous multi-UAV exploration to consumer-level UAVs, such as the DJI Mini 3 Pro. We propose a pipeline that selects viewpoint pairs from which the depth can be estimated and plans the trajectory that satisfies motion constraints necessary for odometry estimation. For the multi-UAV exploration, we propose a semi-distributed communication scheme that distributes the workload in a balanced manner. We evaluate our model performance in simulation for different numbers of UAVs and prove its ability to safely explore the environment and reconstruct the map even with the hardware limitations of consumer-grade UAVs.

Problem

• Extends autonomous UAV exploration to consumer-grade drones
• Proposes viewpoint selection and trajectory planning under motion constraints
• Develops semi-distributed communication for balanced multi-UAV workload

Innovation

• Extends autonomous UAV exploration to consumer-grade drones
• Uses viewpoint pairs for depth estimation and trajectory planning
• Implements semi-distributed communication for balanced workload