Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation-Reference-Cited by-同舟云学术

Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation

Published:2023-07-16 Issue:4 Volume:12 Page:104
ISSN:2218-6581
Container-title:Robotics
language:en
Short-container-title:Robotics

Author:

Staroverov Aleksei¹²³^ORCID,Muravyev Kirill²^ORCID,Yakovlev Konstantin²^ORCID,Panov Aleksandr I.¹²^ORCID

Affiliation:

1. AIRI, 105064 Moscow, Russia

2. Federal Research Center for Computer Science and Control of Russian Academy of Sciences, 119333 Moscow, Russia

3. Moscow Institute of Physics and Technology, 141707 Dolgoprudny, Russia

Abstract

In recent years, Embodied AI has become one of the main topics in robotics. For the agent to operate in human-centric environments, it needs the ability to explore previously unseen areas and to navigate to objects that humans want the agent to interact with. This task, which can be formulated as ObjectGoal Navigation (ObjectNav), is the main focus of this work. To solve this challenging problem, we suggest a hybrid framework consisting of both not-learnable and learnable modules and a switcher between them—SkillFusion. The former are more accurate, while the latter are more robust to sensors’ noise. To mitigate the sim-to-real gap, which often arises with learnable methods, we suggest training them in such a way that they are less environment-dependent. As a result, our method showed top results in both the Habitat simulator and during the evaluations on a real robot.

Funder

Ministry of Science and Higher Education of the Russian Federation

Publisher

MDPI AG

Subject

Artificial Intelligence,Control and Optimization,Mechanical Engineering

Link

https://www.mdpi.com/2218-6581/12/4/104/pdf

Reference44 articles.

1. Wijmans, E., Kadian, A., Morcos, A., Lee, S., Essa, I., Parikh, D., Savva, M., and Batra, D. (2019). DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames. arXiv.

2. Chaplot, D.S., Gandhi, D., Gupta, S., Gupta, A., and Salakhutdinov, R. (2020). Learning to Explore using Active Neural SLAM. arXiv.

3. Shacklett, B., Wijmans, E., Petrenko, A., Savva, M., Batra, D., Koltun, V., and Fatahalian, K. (2021, January 3–7). Large Batch Simulation for Deep Reinforcement Learning. Proceedings of the International Conference on Learning Representations (ICLR), Virtual Event.

4. Batra, D., Gokaslan, A., Kembhavi, A., Maksymets, O., Mottaghi, R., Savva, M., Toshev, A., and Wijmans, E. (2020). ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects. arXiv.

5. Visual Navigation for Mobile Robots: A Survey;Ortiz;J. Intell. Robot. Syst.,2008