KinoUAV improves drone navigation safety and stability with kinodynamic modeling

KinoUAV: A Benchmark for Safe and Stable UAV Vision-Language Navigation with Kinodynamic Modeling

Computer Vision and Pattern Recognition

Summary

Flying drones safely and smoothly is hard because current methods don’t always consider how drones move and turn. The authors created KinoUAV, a system that plans drone paths while thinking about speed, acceleration, and safe distance to obstacles. It uses special labels to know how much free space is around, so drones avoid crashes and move more steadily. Their experiments show this approach helps drones find targets more successfully with fewer collisions and less erratic movement.

What this means in practice

  • For drone delivery teams: Enable drones to navigate safely and smoothly in complex environments by planning trajectories under kinodynamic and safety constraints.
  • For agricultural uav operators: Support remote sensing drones with improved autonomous flight paths that reduce collisions and stabilize motion for better crop monitoring.

Authors

Chenyao Yang, Peijin Wang, Yingchao Feng, Wenhui Diao

Abstract

Unmanned aerial vehicles (UAVs) have recently emerged as important remote sensing platforms, and UAV navigation has shown great potential in remote sensing applications. However, existing methods do not explicitly incorporate kinodynamic modeling or safety distances into trajectory generation, resulting in high absolute yaw rates, frequent collisions, and low navigation success rates, which limit safety and motion stability. To address this challenge, we introduce KinoUAV, a kinodynamic benchmark comprising a dataset and KinoUAV-Agent. First, we develop a hierarchical kinodynamic trajectory generation pipeline that drives UAV through acceleration actions. It uses waypoint chains from global planning and generates trajectories segment by segment under velocity, acceleration, and jerk constraints, reducing oscillations and improving trajectory stability. Furthermore, we introduce directional free-space distance (DFD) labels into the constructed dataset to describe the available clearance for safe motion decisions. The proposed KinoUAV-Agent predicts DFDs and uses them to generate safe actions, decoupling perception from action decision-making. This design enables autonomous obstacle avoidance and improves navigation safety. The benchmark incorporates the proposed Cruise-Seek task, in which the UAV first enters the target region and then searches for the target, reducing the difficulty of target search and improving navigation success. Experiments on KinoUAV show that KinoUAV-Agent outperforms existing methods, achieving the highest success rate while maintaining lower absolute yaw rates and collision rates. These results demonstrate the effectiveness of kinodynamic modeling for safe and stable UAV navigation.