Saved in:
Bibliographic Details
Main Authors: Sadek, Assem, Bono, Guillaume, Chidlovskii, Boris, Baskurt, Atilla, Wolf, Christian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13800
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929223282720768
author Sadek, Assem
Bono, Guillaume
Chidlovskii, Boris
Baskurt, Atilla
Wolf, Christian
author_facet Sadek, Assem
Bono, Guillaume
Chidlovskii, Boris
Baskurt, Atilla
Wolf, Christian
contents Navigation has been classically solved in robotics through the combination of SLAM and planning. More recently, beyond waypoint planning, problems involving significant components of (visual) high-level reasoning have been explored in simulated environments, mostly addressed with large-scale machine learning, in particular RL, offline-RL or imitation learning. These methods require the agent to learn various skills like local planning, mapping objects and querying the learned spatial representations. In contrast to simpler tasks like waypoint planning (PointGoal), for these more complex tasks the current state-of-the-art models have been thoroughly evaluated in simulation but, to our best knowledge, not yet in real environments. In this work we focus on sim2real transfer. We target the challenging Multi-Object Navigation (Multi-ON) task and port it to a physical environment containing real replicas of the originally virtual Multi-ON objects. We introduce a hybrid navigation method, which decomposes the problem into two different skills: (1) waypoint navigation is addressed with classical SLAM combined with a symbolic planner, whereas (2) exploration, semantic mapping and goal retrieval are dealt with deep neural networks trained with a combination of supervised learning and RL. We show the advantages of this approach compared to end-to-end methods both in simulation and a real environment and outperform the SOTA for this task.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13800
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Object Navigation in real environments using hybrid policies
Sadek, Assem
Bono, Guillaume
Chidlovskii, Boris
Baskurt, Atilla
Wolf, Christian
Robotics
Artificial Intelligence
Navigation has been classically solved in robotics through the combination of SLAM and planning. More recently, beyond waypoint planning, problems involving significant components of (visual) high-level reasoning have been explored in simulated environments, mostly addressed with large-scale machine learning, in particular RL, offline-RL or imitation learning. These methods require the agent to learn various skills like local planning, mapping objects and querying the learned spatial representations. In contrast to simpler tasks like waypoint planning (PointGoal), for these more complex tasks the current state-of-the-art models have been thoroughly evaluated in simulation but, to our best knowledge, not yet in real environments. In this work we focus on sim2real transfer. We target the challenging Multi-Object Navigation (Multi-ON) task and port it to a physical environment containing real replicas of the originally virtual Multi-ON objects. We introduce a hybrid navigation method, which decomposes the problem into two different skills: (1) waypoint navigation is addressed with classical SLAM combined with a symbolic planner, whereas (2) exploration, semantic mapping and goal retrieval are dealt with deep neural networks trained with a combination of supervised learning and RL. We show the advantages of this approach compared to end-to-end methods both in simulation and a real environment and outperform the SOTA for this task.
title Multi-Object Navigation in real environments using hybrid policies
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2401.13800