Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture

Jie Fan; Xudong Zhang; Yijie Chen; Jiangbo Geng; Yutong Jiang; Xuan Liu

doi:10.1007/978-981-95-4875-0_1

Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture

Jie Fan
, Xudong Zhang^*
, Yijie Chen
, Jiangbo Geng
, Yutong Jiang
, Xuan Liu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper introduces a novel terrain recognition method designed for unstructured environments, combining BiLSTM and Transformer encoder networks. The BiLSTM effectively captures temporal dependencies in the data, while the Transformer’s attention mechanism models the correlations between control commands and trajectory information. The proposed method demonstrates an impressive accuracy of 0.9696 on the test set. Furthermore, a deployment strategy is outlined for integrating the method within the modern multi-domain electronic and electrical (E/E) architecture of unmanned ground vehicles, providing valuable insights for real-world applications.

Original language	English
Title of host publication	Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers
Editors	Huiyun Li, Zhongli Wang, Shuai Zhao, Peng Sun, Michael Herrmann, Xi Zheng, Yuling Liu
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	1-12
Number of pages	12
ISBN (Print)	9789819548743
DOIs	https://doi.org/10.1007/978-981-95-4875-0_1
Publication status	Published - 2026
Externally published	Yes
Event	3rd CCF Intelligent Vehicles Symposium, CIVS 2025 - Hangzhou, China Duration: 16 Aug 2025 → 18 Aug 2025

Publication series

Name	Communications in Computer and Information Science
Volume	2631 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	3rd CCF Intelligent Vehicles Symposium, CIVS 2025
Country/Territory	China
City	Hangzhou
Period	16/08/25 → 18/08/25

Keywords

Deep learning
E/E architecture
Terrain recognition
Unmanned ground vehicle

Access to Document

10.1007/978-981-95-4875-0_1

Cite this

Fan, J., Zhang, X., Chen, Y., Geng, J., Jiang, Y., & Liu, X. (2026). Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture. In H. Li, Z. Wang, S. Zhao, P. Sun, M. Herrmann, X. Zheng, & Y. Liu (Eds.), Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers (pp. 1-12). (Communications in Computer and Information Science; Vol. 2631 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-4875-0_1

Fan, Jie ; Zhang, Xudong ; Chen, Yijie et al. / Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture. Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers. editor / Huiyun Li ; Zhongli Wang ; Shuai Zhao ; Peng Sun ; Michael Herrmann ; Xi Zheng ; Yuling Liu. Springer Science and Business Media Deutschland GmbH, 2026. pp. 1-12 (Communications in Computer and Information Science).

@inproceedings{39e213a4d5fe4f55ad3b1667f8aacf2e,

title = "Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture",

abstract = "This paper introduces a novel terrain recognition method designed for unstructured environments, combining BiLSTM and Transformer encoder networks. The BiLSTM effectively captures temporal dependencies in the data, while the Transformer{\textquoteright}s attention mechanism models the correlations between control commands and trajectory information. The proposed method demonstrates an impressive accuracy of 0.9696 on the test set. Furthermore, a deployment strategy is outlined for integrating the method within the modern multi-domain electronic and electrical (E/E) architecture of unmanned ground vehicles, providing valuable insights for real-world applications.",

keywords = "Deep learning, E/E architecture, Terrain recognition, Unmanned ground vehicle",

author = "Jie Fan and Xudong Zhang and Yijie Chen and Jiangbo Geng and Yutong Jiang and Xuan Liu",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 3rd CCF Intelligent Vehicles Symposium, CIVS 2025 ; Conference date: 16-08-2025 Through 18-08-2025",

year = "2026",

doi = "10.1007/978-981-95-4875-0\_1",

language = "English",

isbn = "9789819548743",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "1--12",

editor = "Huiyun Li and Zhongli Wang and Shuai Zhao and Peng Sun and Michael Herrmann and Xi Zheng and Yuling Liu",

booktitle = "Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers",

address = "Germany",

}

Fan, J, Zhang, X, Chen, Y, Geng, J, Jiang, Y & Liu, X 2026, Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture. in H Li, Z Wang, S Zhao, P Sun, M Herrmann, X Zheng & Y Liu (eds), Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers. Communications in Computer and Information Science, vol. 2631 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 1-12, 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Hangzhou, China, 16/08/25. https://doi.org/10.1007/978-981-95-4875-0_1

Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture. / Fan, Jie; Zhang, Xudong; Chen, Yijie et al.
Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers. ed. / Huiyun Li; Zhongli Wang; Shuai Zhao; Peng Sun; Michael Herrmann; Xi Zheng; Yuling Liu. Springer Science and Business Media Deutschland GmbH, 2026. p. 1-12 (Communications in Computer and Information Science; Vol. 2631 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture

AU - Fan, Jie

AU - Zhang, Xudong

AU - Chen, Yijie

AU - Geng, Jiangbo

AU - Jiang, Yutong

AU - Liu, Xuan

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - This paper introduces a novel terrain recognition method designed for unstructured environments, combining BiLSTM and Transformer encoder networks. The BiLSTM effectively captures temporal dependencies in the data, while the Transformer’s attention mechanism models the correlations between control commands and trajectory information. The proposed method demonstrates an impressive accuracy of 0.9696 on the test set. Furthermore, a deployment strategy is outlined for integrating the method within the modern multi-domain electronic and electrical (E/E) architecture of unmanned ground vehicles, providing valuable insights for real-world applications.

AB - This paper introduces a novel terrain recognition method designed for unstructured environments, combining BiLSTM and Transformer encoder networks. The BiLSTM effectively captures temporal dependencies in the data, while the Transformer’s attention mechanism models the correlations between control commands and trajectory information. The proposed method demonstrates an impressive accuracy of 0.9696 on the test set. Furthermore, a deployment strategy is outlined for integrating the method within the modern multi-domain electronic and electrical (E/E) architecture of unmanned ground vehicles, providing valuable insights for real-world applications.

KW - Deep learning

KW - E/E architecture

KW - Terrain recognition

KW - Unmanned ground vehicle

UR - https://www.scopus.com/pages/publications/105028089025

U2 - 10.1007/978-981-95-4875-0_1

DO - 10.1007/978-981-95-4875-0_1

M3 - Conference contribution

AN - SCOPUS:105028089025

SN - 9789819548743

T3 - Communications in Computer and Information Science

SP - 1

EP - 12

BT - Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers

A2 - Li, Huiyun

A2 - Wang, Zhongli

A2 - Zhao, Shuai

A2 - Sun, Peng

A2 - Herrmann, Michael

A2 - Zheng, Xi

A2 - Liu, Yuling

PB - Springer Science and Business Media Deutschland GmbH

T2 - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025

Y2 - 16 August 2025 through 18 August 2025

ER -

Fan J, Zhang X, Chen Y, Geng J, Jiang Y, Liu X. Terrain Recognition for Unstructured Environments Using BiLSTM-Transformer Networks Under Multi-domain E/E Architecture. In Li H, Wang Z, Zhao S, Sun P, Herrmann M, Zheng X, Liu Y, editors, Intelligent Vehicles - 3rd CCF Intelligent Vehicles Symposium, CIVS 2025, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2026. p. 1-12. (Communications in Computer and Information Science). doi: 10.1007/978-981-95-4875-0_1