Design and Learning-Based Control of an Autonomous Aerial Robot for Safe Physical Interaction with the Environment

DOI

10.2991/978-94-6239-750-7_58How to use a DOI?

Keywords

Smart Robots; Autonomous robotic system; Learning based control; physical interaction control

Abstract

Autonomous aerial robots capable of safe physical interaction with the environment are vital in inspection and maintenance of confined and contact-rich environments. Nevertheless, accurate near-surface control is still difficult because of aerodynamic-contact interaction, sensing errors and unmodeled dynamics. This paper introduces the design and control of the learning of an autonomous micro aerial robot through the safe interaction of its environment without depending on pre-specified system modeling. A Long Short-Term Memory (LSTM) neural network has been incorporated into a closed-loop control system and runs directly as a feedback control system with the quadrotor dynamics. As inputs, sequential distance tracking errors of onboard Time-of-Flight and inertial sensors are employed, which allows the controller to acquire temporal dependencies and patterns of disturbances during the near-wall flights. The suggested framework is carried out on a platform that is developed to be custom-made and tested with real-time experiments. The outcomes indicate the stability of distance control, fluent control behaviours, and sound performance in close-proximity work, which shows the success of learning-based control in physical interaction tasks.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sandeep Gupta
AU  - Anuj Nandanwar
AU  - Swati Singh
AU  - Narendra Kumar Dhar
AU  - Suvendu Samanta
AU  - Laxmidhar Behera
PY  - 2026
DA  - 2026/08/31
TI  - Design and Learning-Based Control of an Autonomous Aerial Robot for Safe Physical Interaction with the Environment
BT  - Proceedings of the International Conference on Advanced Design, Manufacturing, and Sustainable Energy Systems (ICADMSES 2026)
PB  - Atlantis Press
SP  - 808
EP  - 820
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-750-7_58
DO  - 10.2991/978-94-6239-750-7_58
ID  - Gupta2026
ER  -