Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Clement, Mihaela-Larisa, Farsang, Mónika, Resch, Felix, Stanusoiu, Mihai-Teodor, Grosu, Radu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909900023529472
author Clement, Mihaela-Larisa
Farsang, Mónika
Resch, Felix
Stanusoiu, Mihai-Teodor
Grosu, Radu
author_facet Clement, Mihaela-Larisa
Farsang, Mónika
Resch, Felix
Stanusoiu, Mihai-Teodor
Grosu, Radu
contents Autonomous agents that rely purely on perception to make real-time control decisions require efficient and robust architectures. In this work, we demonstrate that augmenting RGB input with depth information significantly enhances our agents' ability to predict steering commands compared to using RGB alone. We benchmark lightweight recurrent controllers that leverage the fused RGB-D features for sequential decision-making. To train our models, we collect high-quality data using a small-scale autonomous car controlled by an expert driver via a physical steering wheel, capturing varying levels of steering difficulty. Our models were successfully deployed on real hardware and inherently avoided dynamic and static obstacles, under out-of-distribution conditions. Specifically, our findings reveal that the early fusion of depth data results in a highly robust controller, which remains effective even with frame drops and increased noise levels, without compromising the network's focus on the task.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16711
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents
Clement, Mihaela-Larisa
Farsang, Mónika
Resch, Felix
Stanusoiu, Mihai-Teodor
Grosu, Radu
Robotics
Computer Vision and Pattern Recognition
Machine Learning
Autonomous agents that rely purely on perception to make real-time control decisions require efficient and robust architectures. In this work, we demonstrate that augmenting RGB input with depth information significantly enhances our agents' ability to predict steering commands compared to using RGB alone. We benchmark lightweight recurrent controllers that leverage the fused RGB-D features for sequential decision-making. To train our models, we collect high-quality data using a small-scale autonomous car controlled by an expert driver via a physical steering wheel, capturing varying levels of steering difficulty. Our models were successfully deployed on real hardware and inherently avoided dynamic and static obstacles, under out-of-distribution conditions. Specifically, our findings reveal that the early fusion of depth data results in a highly robust controller, which remains effective even with frame drops and increased noise levels, without compromising the network's focus on the task.
title Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents
topic Robotics
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.16711