Autonomous UAV-Quadruped Docking in Complex Terrains via Active Posture Alignment and Constraint-Aware Control

2025-09-25

AI Summary

Addressing the challenges of unstable landing platforms caused by dynamic posture variations of quadrupedal robots on complex terrain and high-precision autonomous docking in GPS-denied environments, this paper proposes a docking method integrating active torso stabilization and constraint-aware control. Key contributions include: (1) an HIM-HA model to actively suppress quadruped torso disturbances; (2) a three-stage docking strategy that synergistically combines nonsingular fast terminal sliding mode control (NFTSMC) with logarithmic barrier functions, ensuring finite-time convergence while respecting visual and kinematic constraints; and (3) a safety-horizon verification mechanism to guarantee closed-loop safety. Simulation and real-world experiments demonstrate stable docking on unstructured terrains—including steps ≥17 cm and slopes ≥30°—with pose estimation errors within ±3 cm and ±2°. The approach significantly enhances robustness and practicality for heterogeneous robot collaboration.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Autonomous docking between Unmanned Aerial Vehicles (UAVs) and ground robots is essential for heterogeneous systems, yet most existing approaches target wheeled platforms whose limited mobility constrains exploration in complex terrains. Quadruped robots offer superior adaptability but undergo frequent posture variations, making it difficult to provide a stable landing surface for UAVs. To address these challenges, we propose an autonomous UAV-quadruped docking framework for GPS-denied environments. On the quadruped side, a Hybrid Internal Model with Horizontal Alignment (HIM-HA), learned via deep reinforcement learning, actively stabilizes the torso to provide a level platform. On the UAV side, a three-phase strategy is adopted, consisting of long-range acquisition with a median-filtered YOLOv8 detector, close-range tracking with a constraint-aware controller that integrates a Nonsingular Fast Terminal Sliding Mode Controller (NFTSMC) and a logarithmic Barrier Function (BF) to guarantee finite-time error convergence under field-of-view (FOV) constraints, and terminal descent guided by a Safety Period (SP) mechanism that jointly verifies tracking accuracy and platform stability. The proposed framework is validated in both simulation and real-world scenarios, successfully achieving docking on outdoor staircases higher than 17 cm and rough slopes steeper than 30 degrees. Supplementary materials and videos are available at: https://uav-quadruped-docking.github.io.

Problem

• Enabling UAV docking on posture-varying quadruped robots in complex terrains
• Achieving stable landing without GPS using active torso stabilization
• Ensuring finite-time convergence under FOV constraints during close-range tracking

Innovation

• Active torso stabilization via deep reinforcement learning
• Constraint-aware controller with finite-time error convergence
• Three-phase docking strategy with safety verification mechanism