Self-Supervised Path Planning in UAV-aided Wireless Networks based on Active Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Krayani, Ali, Khan, Khalid, Marcenaro, Lucio, Marchese, Mario, Regazzoni, Carlo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914722274607104
author Krayani, Ali
Khan, Khalid
Marcenaro, Lucio
Marchese, Mario
Regazzoni, Carlo
author_facet Krayani, Ali
Khan, Khalid
Marcenaro, Lucio
Marchese, Mario
Regazzoni, Carlo
contents This paper presents a novel self-supervised path-planning method for UAV-aided networks. First, we employed an optimizer to solve training examples offline and then used the resulting solutions as demonstrations from which the UAV can learn the world model to understand the environment and implicitly discover the optimizer's policy. UAV equipped with the world model can make real-time autonomous decisions and engage in online planning using active inference. During planning, UAV can score different policies based on the expected surprise, allowing it to choose among alternative futures. Additionally, UAV can anticipate the outcomes of its actions using the world model and assess the expected surprise in a self-supervised manner. Our method enables quicker adaptation to new situations and better performance than traditional RL, leading to broader generalizability.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13827
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Supervised Path Planning in UAV-aided Wireless Networks based on Active Inference
Krayani, Ali
Khan, Khalid
Marcenaro, Lucio
Marchese, Mario
Regazzoni, Carlo
Robotics
Machine Learning
Signal Processing
This paper presents a novel self-supervised path-planning method for UAV-aided networks. First, we employed an optimizer to solve training examples offline and then used the resulting solutions as demonstrations from which the UAV can learn the world model to understand the environment and implicitly discover the optimizer's policy. UAV equipped with the world model can make real-time autonomous decisions and engage in online planning using active inference. During planning, UAV can score different policies based on the expected surprise, allowing it to choose among alternative futures. Additionally, UAV can anticipate the outcomes of its actions using the world model and assess the expected surprise in a self-supervised manner. Our method enables quicker adaptation to new situations and better performance than traditional RL, leading to broader generalizability.
title Self-Supervised Path Planning in UAV-aided Wireless Networks based on Active Inference
topic Robotics
Machine Learning
Signal Processing
url https://arxiv.org/abs/2403.13827