Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lekkala, Kiran, Liu, Chen, Itti, Laurent
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2310.18847
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917620628848640
author Lekkala, Kiran
Liu, Chen
Itti, Laurent
author_facet Lekkala, Kiran
Liu, Chen
Itti, Laurent
contents Sim2Real transfer has gained popularity because it helps transfer from inexpensive simulators to real world. This paper presents a novel system that fuses components in a traditional World Model into a robust system, trained entirely within a simulator, that Zero-Shot transfers to the real world. To facilitate transfer, we use an intermediary representation that is based on \textit{Bird's Eye View (BEV)} images. Thus, our robot learns to navigate in a simulator by first learning to translate from complex \textit{First-Person View (FPV)} based RGB images to BEV representations, then learning to navigate using those representations. Later, when tested in the real world, the robot uses the perception model that translates FPV-based RGB images to embeddings that were learned by the FPV to BEV translator and that can be used by the downstream policy. The incorporation of state-checking modules using \textit{Anchor images} and Mixture Density LSTM not only interpolates uncertain and missing observations but also enhances the robustness of the model in the real-world. We trained the model using data from a Differential drive robot in the CARLA simulator. Our methodology's effectiveness is shown through the deployment of trained models onto a real-world Differential drive robot. Lastly we release a comprehensive codebase, dataset and models for training and deployment (\url{https://sites.google.com/view/value-explicit-pretraining}).
format Preprint
id arxiv_https___arxiv_org_abs_2310_18847
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bird's Eye View Based Pretrained World model for Visual Navigation
Lekkala, Kiran
Liu, Chen
Itti, Laurent
Robotics
Machine Learning
Sim2Real transfer has gained popularity because it helps transfer from inexpensive simulators to real world. This paper presents a novel system that fuses components in a traditional World Model into a robust system, trained entirely within a simulator, that Zero-Shot transfers to the real world. To facilitate transfer, we use an intermediary representation that is based on \textit{Bird's Eye View (BEV)} images. Thus, our robot learns to navigate in a simulator by first learning to translate from complex \textit{First-Person View (FPV)} based RGB images to BEV representations, then learning to navigate using those representations. Later, when tested in the real world, the robot uses the perception model that translates FPV-based RGB images to embeddings that were learned by the FPV to BEV translator and that can be used by the downstream policy. The incorporation of state-checking modules using \textit{Anchor images} and Mixture Density LSTM not only interpolates uncertain and missing observations but also enhances the robustness of the model in the real-world. We trained the model using data from a Differential drive robot in the CARLA simulator. Our methodology's effectiveness is shown through the deployment of trained models onto a real-world Differential drive robot. Lastly we release a comprehensive codebase, dataset and models for training and deployment (\url{https://sites.google.com/view/value-explicit-pretraining}).
title Bird's Eye View Based Pretrained World model for Visual Navigation
topic Robotics
Machine Learning
url https://arxiv.org/abs/2310.18847