Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Autonomous Docking of Multi-Rotor UAVs on Blimps under the Influence of Wind Gusts

Pascal Goldschmid, Aamir Ahmad

TL;DR

The paper tackles autonomous docking of multi-rotor UAVs onto wind-susceptible blimps, a scenario critical for extending mission lifetimes. It combines a data-driven Temporal Convolutional Network to predict blimp gust responses with a Model Predictive Controller that plans collision-free trajectories, aided by a Corridor Enhanced Tangential Hull for close-range obstacle avoidance and gust-detection to revoke the corridor when safety requires. Key contributions include the TCN-based gust prediction framework, the CETH-based collision avoidance mechanism, and EKF-based docking-port localization, all validated in simulation and via real-world tests with a virtual blimp. The approach offers a practical path to reliable wind-aware aerial docking, enabling extended UAV operation and data/battery offloading on blimps, with public code to foster further research.

Abstract

Multi-rotor UAVs face limited flight time due to battery constraints. Autonomous docking on blimps with onboard battery recharging and data offloading offers a promising solution for extended UAV missions. However, the vulnerability of blimps to wind gusts causes trajectory deviations, requiring precise, obstacle-aware docking strategies. To this end, this work introduces two key novelties: (i) a temporal convolutional network that predicts blimp responses to wind gusts, enabling rapid gust detection and estimation of points where the wind gust effect has subsided; (ii) a model predictive controller (MPC) that leverages these predictions to compute collision-free trajectories for docking, enabled by a novel obstacle avoidance method for close-range manoeuvres near the blimp. Simulation results show our method outperforms a baseline constant-velocity model of the blimp significantly across different scenarios. We further validate the approach in real-world experiments, demonstrating the first autonomous multi-rotor docking control strategy on blimps shown outside simulation. Source code is available here https://github.com/robot-perception-group/multi_rotor_airship_docking.

Autonomous Docking of Multi-Rotor UAVs on Blimps under the Influence of Wind Gusts

TL;DR

The paper tackles autonomous docking of multi-rotor UAVs onto wind-susceptible blimps, a scenario critical for extending mission lifetimes. It combines a data-driven Temporal Convolutional Network to predict blimp gust responses with a Model Predictive Controller that plans collision-free trajectories, aided by a Corridor Enhanced Tangential Hull for close-range obstacle avoidance and gust-detection to revoke the corridor when safety requires. Key contributions include the TCN-based gust prediction framework, the CETH-based collision avoidance mechanism, and EKF-based docking-port localization, all validated in simulation and via real-world tests with a virtual blimp. The approach offers a practical path to reliable wind-aware aerial docking, enabling extended UAV operation and data/battery offloading on blimps, with public code to foster further research.

Abstract

Multi-rotor UAVs face limited flight time due to battery constraints. Autonomous docking on blimps with onboard battery recharging and data offloading offers a promising solution for extended UAV missions. However, the vulnerability of blimps to wind gusts causes trajectory deviations, requiring precise, obstacle-aware docking strategies. To this end, this work introduces two key novelties: (i) a temporal convolutional network that predicts blimp responses to wind gusts, enabling rapid gust detection and estimation of points where the wind gust effect has subsided; (ii) a model predictive controller (MPC) that leverages these predictions to compute collision-free trajectories for docking, enabled by a novel obstacle avoidance method for close-range manoeuvres near the blimp. Simulation results show our method outperforms a baseline constant-velocity model of the blimp significantly across different scenarios. We further validate the approach in real-world experiments, demonstrating the first autonomous multi-rotor docking control strategy on blimps shown outside simulation. Source code is available here https://github.com/robot-perception-group/multi_rotor_airship_docking.

Paper Structure

This paper contains 40 sections, 18 equations, 8 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Aerial Docking
  4. Learning of Blimp Trajectories
  5. Temporal Convolutional Networks
  6. Model Predictive Control
  7. Methodology
  8. Problem Statement
  9. Overview of our Proposed Method
  10. Wind Gust Definition
  11. Blimp Gust Response Prediction using a Temporal Convolutional Network
  12. Wind Gust Detection
  13. Collision-free Trajectory Planning using a Model Predictive Controller (MPC)
  14. Collision Avoidance
  15. Repulsive Force Model
  16. ...and 25 more sections

Figures (8)

  • Figure 1: Illustration of our approach. A multi-rotor UAV approaches a docking port mounted on a virtual blimp (white). The blimp is protected by a no-fly zone (red) enhanced with a cone shaped approach corridor (green). A collision-free trajectory is planned (yellow line) considering the predicted trajectory of the blimp (grey line) under the influence of wind gusts.
  • Figure 2: No-fly zone around the blimp.
  • Figure 3: System overview, colored light green are components relying on existing work, colored dark green are components containing contributions of this work that are explained in closer detail.
  • Figure 4: Illustration of the corridor-enhanced tangential hull method.
  • Figure 5: Design of the docking port in simulation. AprilTags are used for relative localization.
  • ...and 3 more figures