EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ROIV-SLAM: Rotation-Optimized Inertial–Visual SLAM for a Non-Coaxial Two-Wheeled Robot Under Roll Disturbances

Chong Feng, Cheng Ren, Wenbo Gao, Zhan Shi, Chunjuan Bo, Chang Kou, Zhun Feng

Sensors · 25.06.2026 · 26 (13) · 4053

DOI: 10.3390/s26134053 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.06.2026. Verfasst von Chong Feng und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Information and Communication, Dalian Minzu University, Dalian 116600, China. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the problem of high-frequency roll disturbances generated during dynamic balancing in non-coaxial two-wheeled robots, this paper proposes a Rotation-Optimized Inertial–Visual SLAM system (ROIV-SLAM) for robust state estimation. The proposed approach adopts a decoupled architecture for translation and rotation estimation. In the front-end, an Extended Kalman Filter (EKF) is employed to fuse LiDAR, an inertial measurement unit (IMU), and wheel odometry to obtain an initial translation estimate. Meanwhile, a physical manifold constraint is constructed using the gravity vector and surface normals extracted from RGB-D point clouds, supporting stable rotation estimation under high-frequency disturbances through Lie-group-based optimization. In the back-end, a factor graph is established, and loop closure robustness is enhanced through vision–LiDAR scan matching. Experimental results indicate that ROIV-SLAM achieves improved trajectory consistency with respect to the optimized reference trajectory and more robust mapping performance compared with the evaluated baseline approaches in the tested scenarios. The results further suggest that introducing task-specific physical dynamic constraints and a decoupled estimation mechanism helps suppress high-frequency motion noise inherent to balancing robots, thereby improving the robustness of state estimation in complex environments.

Schlagwörter

Stichwörter der Autor:innen

SLAMmotion disturbancesnon-coaxial two-wheeled robotrotation optimizationvisual–inertial fusion

Autor:innen und Institutionen

  • College of Information and Communication, Dalian Minzu University, Dalian 116600, China.
  • Dalian Everyday Good Electronic Co., Ltd., Tieshan Dongsan Road, Dalian 116630, China.
  • Industry-Education Integration Center, Liaoning Railway Vocational and Technical College, Jinzhou 121000, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Feng, C., Ren, C., Gao, W., Shi, Z., Bo, C., Kou, C., & Feng, Z. (2026). ROIV-SLAM: Rotation-Optimized Inertial–Visual SLAM for a Non-Coaxial Two-Wheeled Robot Under Roll Disturbances. Sensors, 26(13), 4053. https://doi.org/10.3390/s26134053

Vancouver

Feng C, Ren C, Gao W, Shi Z, Bo C, Kou C, et al. ROIV-SLAM: Rotation-Optimized Inertial–Visual SLAM for a Non-Coaxial Two-Wheeled Robot Under Roll Disturbances. Sensors. 2026;26(13):4053. doi:10.3390/s26134053

BibTeX
@article{Feng2026,
  author = {Feng, Chong and Ren, Cheng and Gao, Wenbo and Shi, Zhan and Bo, Chunjuan and Kou, Chang and Feng, Zhun},
  title = {ROIV-SLAM: Rotation-Optimized Inertial–Visual SLAM for a Non-Coaxial Two-Wheeled Robot Under Roll Disturbances},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4053},
  doi = {10.3390/s26134053}
}
Kostenlos starten →