Invisible Servoing: a Visual Servoing Approach with Return-Conditioned Latent Diffusion

Bishoy Gerges, Barbara Bazzana, Nicolò Botteghi, Youssef Aboudorra, Antonio Franchi

Research output: Working paperPreprintAcademic

77 Downloads (Pure)

Abstract

In this paper, we present a novel visual servoing (VS) approach based on latent Denoising Diffusion Probabilistic Models (DDPMs). Opposite to classical VS methods, the proposed approach allows reaching the desired target view, even when the target is initially not visible. This is possible thanks to the learning of a latent representation that the DDPM uses for planning and a dataset of trajectories encompassing target-invisible initial views. The latent representation is learned using a Cross-Modal Variational Autoencoder, and used to estimate the return for conditioning the trajectory generation of the DDPM. Given the current image, the DDPM generates trajectories in the latent space driving the robotic platform to the desired visual target. The approach is applicable to any velocity-based controlled platform. We test our method with simulated and real-world experiments using generic multi-rotor Uncrewed Aerial Vehicles (UAVs). A video of our experiments can be found at https://youtu.be/yu-aTxqceOA.
Original languageEnglish
PublisherArXiv.org
DOIs
Publication statusPublished - 20 Sept 2024

Keywords

  • cs.RO

Fingerprint

Dive into the research topics of 'Invisible Servoing: a Visual Servoing Approach with Return-Conditioned Latent Diffusion'. Together they form a unique fingerprint.
  • Invisible Servoing: A Visual Servoing Approach with Return-Conditioned Latent Diffusion

    Gerges, B., Bazzana, B., Botteghi, N., Aboudorra, Y. & Franchi, A., 2025, 2025 International Conference on Unmanned Aircraft Systems, ICUAS 2025. Piscataway, NJ: IEEE, p. 52-59 8 p. (International Conference on Unmanned Aircraft Systems (ICUAS); vol. 2025).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    4 Downloads (Pure)

Cite this