CoChat

Target-Driven Visual Navigation by Using Causal Intervention

Zhao, Xinzhou, Wang, Tian, Li, Yanjing, Zhang, Baochang, Liu, Kexin, Liu, Deyuan, Wang, Chuanyun, Snoussi, Hichem · 2024 · IEEE Transactions on Intelligent Vehicles

The DOI matches its Crossref record; 41 of the 50 references it cites were found in a registry or an index.

Abstract

Target-driven visual navigation presents great potentials in scientific and industrial fields. It takes the target and environment observations as input. However, during training, we found that the agent sometimes got stuck in specific locations. Based on the analysis on visual information from a novel causal perspective, one of the most critical hurdles is the neglect of confounders in environments, which often leads to spurious correlations. Mitigating the confounding effect helps to discover the real causality and therefore are taken into consideration in other fields such as object detection. In this article, we propose Causal Intervention Visual Navigation (CIVN), based on deep reinforcement learning (DRL) and causal intervention. We realize causal intervention using front-door adjustment as most confounders are hard to model explicitly. Specifically, CIVN is implemented by Causal Attention, which is a reasonable approximation of causal intervention for visual navigation. Causal attention provides high-quality representation, which is leveraged by DRL and reduces the number of “stuck”. It is worth mentioned that causal intervention is for the first time applied by us in solving the confounding effect in target-driven visual navigation. Extensive experiments on AI2-THOR demonstrate that CIVN achieves better performance than prior arts. Specifically, the generalization for unknown targets and scenes is improved by a large margin, which is a basic research topic in visual navigation. Moreover, to obtain better generalization, we propose a novel experiment utilizing pre-trained models firstly.

Overview

Integrity signals

Registry

Crossref · 10.1109/tiv.2023.3288810

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 41 references

Research works printed but not linked: 1

  1. 10.5555/3045118.3045336 · doi:10.5555/3045118.3045336

Cited by

See all 86

Metadata

Authors
Zhao, X., Wang, T., Li, Y., Zhang, B., Liu, K., Liu, D., Wang, C., & Snoussi, H.
Affiliations
  • Beihang University (CN)
  • State Key Laboratory of Software Development Environment (CN)
  • Shenyang Aerospace University (CN)
  • Université de Technologie de Troyes (FR)
Venue
IEEE Transactions on Intelligent Vehicles
Published
2024-01
Volume
9
Issue
1
Pages
1294-1304
ISSN
  • 2379-8858 (ISSN-L)
  • 2379-8904
OpenAlex
W4381886279
Cited by
86
References
50
Citations by year
2026: 43 · 2025: 40 · 2024: 3
FWCI
8.11
Type
journal article
Language
en
Open access
closed
Locations
  • IEEE Transactions on Intelligent Vehicles (publishedVersion)
  • HAL (submittedVersion)
Funders
  • National Natural Science Foundation of China (62141604, 61972016, 62032016, 92067204, 61703287)
  • Beijing Nova (2022122)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
  • Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
Keywords
causal intervention, confounding, spurious correlations, front-door adjustment, causal attention, deep reinforcement learning, pre-trained models, AI2-THOR

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Target-Driven Visual Navigation by Using Causal Intervention. https://app.cochat.ai/papers/10.1109/tiv.2023.3288810
The paper
Zhao, X., Wang, T., Li, Y., Zhang, B., Liu, K., Liu, D., Wang, C., & Snoussi, H. (2024). Target-Driven Visual Navigation by Using Causal Intervention. IEEE Transactions on Intelligent Vehicles. https://doi.org/10.1109/tiv.2023.3288810

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.