KIO-planner: Attention-Guided Single-Stage Motion Planning with Dual Mapping for UAV Navigation

2026-05-19

AI Summary

This work addresses the high collision risk and trajectory irregularity faced by drones navigating dense obstacle environments, stemming from mapping latency and local minima in traditional planners as well as the difficulty of end-to-end methods in modeling fine-grained geometric and dynamical constraints. To overcome these challenges, the authors propose an attention-guided, single-stage motion planning framework that integrates Convolutional Block Attention Modules (CBAM) into the perception backbone and introduces a novel dual-mapping mechanism in deep pixel space. This mechanism jointly encodes deterministic geometric safety barriers and physical boundary activations, enabling rapid generation of safe, smooth trajectories without requiring global map fusion. Experimental results demonstrate that the system supports agile flight up to 3.0 m/s in high-fidelity simulation, achieves a low inference latency of 24 ms, reduces control cost by 28.4%, and improves the worst-case minimum obstacle clearance from 0.48 m to 0.76 m.

Abstract

Autonomous UAV flight in confined, wall-dense environments requires low-latency and reliable motion planning under strict safety constraints. Traditional optimization-based planners suffer from mapping latency and easily fall into local minima when navigating through dense structural obstacles. Meanwhile, existing end-to-end learning methods struggle to extract fine-grained geometric features from raw depth images and lack hard kinodynamic constraints, leading to unpredictable collisions near walls. To address these issues, we propose KIO-planner, an attention-guided single-stage trajectory planning framework. First, we integrate a Convolutional Block Attention Module (CBAM) into the perception backbone to adaptively focus on critical structural edges and traversable space. Second, we introduce a novel Dual Mapping mechanism--comprising physical bounds activation and a deterministic Geometric Safety Shield in the depth-pixel space--to enforce kinodynamic feasibility and collision-free flight without global map fusion. Extensive high-fidelity simulated experiments demonstrate that KIO-planner enables highly agile navigation at speeds up to 3.0 m/s. Compared to the state-of-the-art baseline, KIO-planner achieves lower inference latency (approximately 24 ms) and generates significantly smoother trajectories, reducing control cost by 28.4%. Most notably, our Dual Mapping substantially increases the worst-case safety margin, measured by minimum distance to obstacles, from 0.48 m to 0.76 m, ensuring fast, smooth, and safer navigation in highly constrained environments.

Problem

• motion planning
• UAV navigation
• kinodynamic constraints
• collision avoidance
• dense environments

Innovation

• attention-guided planning
• single-stage motion planning
• dual mapping
• geometric safety shield
• kinodynamic constraints