MTG: Mapless Trajectory Generator with Traversability Coverage for Outdoor Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Jing, Gao, Peng, Xiao, Xuesu, Sathyamoorthy, Adarsh Jagan, Elnoor, Mohamed, Lin, Ming C., Manocha, Dinesh
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910351894773760
author Liang, Jing
Gao, Peng
Xiao, Xuesu
Sathyamoorthy, Adarsh Jagan
Elnoor, Mohamed
Lin, Ming C.
Manocha, Dinesh
author_facet Liang, Jing
Gao, Peng
Xiao, Xuesu
Sathyamoorthy, Adarsh Jagan
Elnoor, Mohamed
Lin, Ming C.
Manocha, Dinesh
contents We present a novel learning-based trajectory generation algorithm for outdoor robot navigation. Our goal is to compute collision-free paths that also satisfy the environment-specific traversability constraints. Our approach is designed for global planning using limited onboard robot perception in mapless environments while ensuring comprehensive coverage of all traversable directions. Our formulation uses a Conditional Variational Autoencoder (CVAE) generative model that is enhanced with traversability constraints and an optimization formulation used for the coverage. We highlight the benefits of our approach over state-of-the-art trajectory generation approaches and demonstrate its performance in challenging and large outdoor environments, including around buildings, across intersections, along trails, and off-road terrain, using a Clearpath Husky and a Boston Dynamics Spot robot. In practice, our approach results in a 6% improvement in coverage of traversable areas and an 89% reduction in trajectory portions residing in non-traversable regions. Our video is here: https://youtu.be/3eJ2soAzXnU
format Preprint
id arxiv_https___arxiv_org_abs_2309_08214
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MTG: Mapless Trajectory Generator with Traversability Coverage for Outdoor Navigation
Liang, Jing
Gao, Peng
Xiao, Xuesu
Sathyamoorthy, Adarsh Jagan
Elnoor, Mohamed
Lin, Ming C.
Manocha, Dinesh
Robotics
We present a novel learning-based trajectory generation algorithm for outdoor robot navigation. Our goal is to compute collision-free paths that also satisfy the environment-specific traversability constraints. Our approach is designed for global planning using limited onboard robot perception in mapless environments while ensuring comprehensive coverage of all traversable directions. Our formulation uses a Conditional Variational Autoencoder (CVAE) generative model that is enhanced with traversability constraints and an optimization formulation used for the coverage. We highlight the benefits of our approach over state-of-the-art trajectory generation approaches and demonstrate its performance in challenging and large outdoor environments, including around buildings, across intersections, along trails, and off-road terrain, using a Clearpath Husky and a Boston Dynamics Spot robot. In practice, our approach results in a 6% improvement in coverage of traversable areas and an 89% reduction in trajectory portions residing in non-traversable regions. Our video is here: https://youtu.be/3eJ2soAzXnU
title MTG: Mapless Trajectory Generator with Traversability Coverage for Outdoor Navigation
topic Robotics
url https://arxiv.org/abs/2309.08214