CoChat

Towards Generalization in Target-Driven Visual Navigation by Using Deep Reinforcement Learning

Open access
Devo, Alessandro, Mezzetti, Giacomo, Costante, Gabriele, Fravolini, Mario L., Valigi, Paolo · 2020 · IEEE Transactions on Robotics
Cited by 107

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Abstract

Among the main challenges in robotics, target-driven visual navigation has gained increasing interest in recent years. In this task, an agent has to navigate in an environment to reach a user specified target, only through vision. Recent fruitful approaches rely on deep reinforcement learning, which has proven to be an effective framework to learn navigation policies. However, current state-of-the-art methods require to retrain, or at least fine-tune, the model for every new environment and object. In real scenarios, this operation can be extremely challenging or even dangerous. For these reasons, we address generalization in target-driven visual navigation by proposing a novel architecture composed of two networks, both exclusively trained in simulation. The first one has the objective of exploring the environment, while the other one of locating the target. They are specifically designed to work together, while separately trained to help generalization. In this article, we test our agent in both simulated and real scenarios, and validate its generalization capabilities through extensive experiments with previously unseen goals and unknown mazes, even much larger than the ones used for training.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tro.2020.2994002

Cites

24 of 24 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 22

  1. 10.1109/ICCV.2017.60 · DOI · Paper page
  2. levine, 2016, End-to-end training of deep visuomotor policies, J Mach Learn Res, 17, 1334
  3. 10.1109/IROS.2018.8594249 · DOI
  4. 10.1109/ICRA.2019.8793493 · DOI · Paper page
  5. 10.1109/LRA.2019.2930426 · DOI
  6. 10.1023/A:1007634325138 · DOI
  7. mnih, 2015, Human-level control through deep reinforcement learning, Nature, 518, 529, 10.1038/nature14236 · DOI · Paper page
  8. 10.1109/70.88137 · DOI · Paper page
  9. 10.1109/21.44033 · DOI · Paper page
  10. 10.1177/0278364919887447 · DOI · Paper page
  11. 10.1109/IROS.2018.8593720 · DOI · Paper page
  12. sutton, 2018, Reinforcement Learning An Introduction
  13. greydanus, 0, Visualizing and understanding Atari agents, Proc Int Conf Mach Learn, 1787
  14. 10.1109/ICRA.2018.8460655 · DOI · Paper page
  15. 10.1109/CVPR.2017.769 · DOI · Paper page
  16. 10.1109/LRA.2020.2965857 · DOI
  17. 10.1109/ICRA.2017.7989385 · DOI · Paper page
  18. 10.1109/TRO.2018.2878318 · DOI · Paper page
  19. 10.1109/ROBOT.1995.525695 · DOI
  20. 10.1023/A:1008824626321 · doi:10.1023/a:1008824626321
  21. 10.1109/TRO.2016.2624754 · DOI · Paper page
  22. 10.1007/s11263-015-0816-y · DOI · Paper page

Cited by

See all 107

Metadata

Authors
Devo, A., Mezzetti, G., Costante, G., Fravolini, M. L., & Valigi, P.
Venue
IEEE Transactions on Robotics
Published
2020-10
Volume
36
Issue
5
Pages
1546-1561
ISSN
  • 1552-3098 (ISSN-L)
  • 1941-0468
OpenAlex
W3029795912
Cited by
107
References
24
FWCI
5.11
Type
journal article
Language
en
Open access
green
Funders
Università degli Studi di Perugia (RICBA17MRF, RICBA18MF)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.