MonoForce: Self-supervised Learning of Physics-informed Model for Predicting Robot-terrain Interaction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00376785" target="_blank" >RIV/68407700:21230/24:00376785 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/IROS58592.2024.10801353" target="_blank" >https://doi.org/10.1109/IROS58592.2024.10801353</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IROS58592.2024.10801353" target="_blank" >10.1109/IROS58592.2024.10801353</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MonoForce: Self-supervised Learning of Physics-informed Model for Predicting Robot-terrain Interaction

Popis výsledku v původním jazyce

While autonomous navigation of mobile robots on rigid terrain is a well-explored problem, navigating on deformable terrain such as tall grass or bushes remains a challenge. To address it, we introduce an explainable, physicsaware and end-to-end differentiable model which predicts the outcome of robot-terrain interaction from camera images, both on rigid and non-rigid terrain. The proposed MonoForce model consists of a black-box module which predicts robotterrain interaction forces from onboard cameras, followed by a white-box module, which transforms these forces and a control signals into predicted trajectories, using only the laws of classical mechanics. The differentiable white-box module allows backpropagating the predicted trajectory errors into the black-box module, serving as a self-supervised loss that measures consistency between the predicted forces and groundtruth trajectories of the robot. Experimental evaluation on a public dataset and our data has shown that while the prediction capabilities are comparable to state-of-the-art algorithms on rigid terrain, MonoForce shows superior accuracy on nonrigid terrain such as tall grass or bushes. To facilitate the reproducibility of our results, we release both the code and datasets.

Název v anglickém jazyce

MonoForce: Self-supervised Learning of Physics-informed Model for Predicting Robot-terrain Interaction

Popis výsledku anglicky

While autonomous navigation of mobile robots on rigid terrain is a well-explored problem, navigating on deformable terrain such as tall grass or bushes remains a challenge. To address it, we introduce an explainable, physicsaware and end-to-end differentiable model which predicts the outcome of robot-terrain interaction from camera images, both on rigid and non-rigid terrain. The proposed MonoForce model consists of a black-box module which predicts robotterrain interaction forces from onboard cameras, followed by a white-box module, which transforms these forces and a control signals into predicted trajectories, using only the laws of classical mechanics. The differentiable white-box module allows backpropagating the predicted trajectory errors into the black-box module, serving as a self-supervised loss that measures consistency between the predicted forces and groundtruth trajectories of the robot. Experimental evaluation on a public dataset and our data has shown that while the prediction capabilities are comparable to state-of-the-art algorithms on rigid terrain, MonoForce shows superior accuracy on nonrigid terrain such as tall grass or bushes. To facilitate the reproducibility of our results, we release both the code and datasets.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)

ISBN

979-8-3503-7770-5

ISSN

2153-0858

e-ISSN

2153-0866

Počet stran výsledku

8

Strana od-do

12896-12903

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Abu Dhabi

Datum konání akce

14. 10. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001433985300697