Jinsheng Chen
Jinsheng Chen has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Youchun Xu
Institute of Military Transportation, Army Military Transportation University, Tianjin 300161, China
3 shared publications Feng Lu
1 shared publication- Feng Lu
Army Military Transportation University, Tianjin, China
1 shared publication - Feng Lu
Institute of Military Transportation, PLA Joint Logistics Support Force University of Engineering, Tianjin 300161, China
1 shared publication - Jianshi Li
Institute of Military Transportation, PLA Joint Logistics Support Force University of Engineering, Tianjin 300161, China
1 shared publication - Le Wang
PLA Joint Logistics Support Force University of Engineering, Tianjin 300161, China
1 shared publication
Latest Publications
- Open Access
- 1 December 2026
- Published by KEAI Publishing in Biomimetic Intelligence and Robotics
- Vol. 6 (4)
Anti-disturbance control for longitudinal motion of distributed electric drive unmanned ground vehicle
- 1 December 2026
- Published by KEAI Publishing in Biomimetic Intelligence and Robotics
- Vol. 6 (4)
Open AccessAnti-disturbance control for longitudinal motion of distributed electric drive unmanned ground vehicle
- Open Access
- 17 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (12) , 6155
Rotation-Equivariant Feature Learning on Polar BEV for Robust LiDAR Place Recognition
LiDAR-based place recognition is critical for long-term autonomous navigation in Global Navigation Satellite System (GNSS)-denied environments, yet existing methods struggle to balance accuracy and efficiency under substantial yaw rotations. This paper proposes a robust framework based on a multi-channel polar bird’s-eye-view (BEV) representation. Under yaw-dominated revisits, the polar BEV image transforms yaw rotation into cyclic column shifts, providing a useful structural prior for rotation-equivariant feature extraction. Raw point clouds are projected onto polar BEV grids encoding density, height, and intensity. A rotation-equivariant feature extractor comprising a Radial Compression Module and a rotation-equivariant Transformer module captures long-range azimuthal dependencies via Conditional Positional Encoding and Circular Relative-Position Bias. The equivariant features are aggregated by NetVLAD into a compact global descriptor, trained end-to-end with a hard-example mining triplet loss. Extensive experiments on the public KITTI and NCLT datasets, as well as our self-constructed LiDAR Place Recognition Revisit (LPRR) dataset, demonstrate competitive performance on KITTI and superior performance on NCLT and LPRR among the compared methods. The proposed framework achieves a favorable trade-off between performance and computational cost, and shows promising cross-dataset generalization on the evaluated NCLT and LPRR datasets without fine-tuning.
- 17 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (12) , 6155
Open AccessRotation-Equivariant Feature Learning on Polar BEV for Robust LiDAR Place Recognition
LiDAR-based place recognition is critical for long-term autonomous navigation in Global Navigation Satellite System (GNSS)-denied environments, yet existing methods struggle to balance accuracy and efficiency under substantial yaw rotations. This paper proposes a robust framework based on a multi-channel polar bird’s-eye-view (BEV) representation. Under yaw-dominated revisits, the polar BEV image transforms yaw rotation into cyclic column shifts, providing a useful structural prior for rotation-equivariant feature extraction. Raw point clouds are projected onto polar BEV grids encoding density, height, and intensity. A rotation-equivariant feature extractor comprising a Radial Compression Module and a rotation-equivariant Transformer module captures long-range azimuthal dependencies via Conditional Positional Encoding and Circular Relative-Position Bias. The equivariant features are aggregated by NetVLAD into a compact global descriptor, trained end-to-end with a hard-example mining triplet loss. Extensive experiments on the public KITTI and NCLT datasets, as well as our self-constructed LiDAR Place Recognition Revisit (LPRR) dataset, demonstrate competitive performance on KITTI and superior performance on NCLT and LPRR among the compared methods. The proposed framework achieves a favorable trade-off between performance and computational cost, and shows promising cross-dataset generalization on the evaluated NCLT and LPRR datasets without fine-tuning.
- Open Access
- 30 October 2025
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 111 (4) , 1-20
Autonomous Plug-in Charging for Wheeled Mobile Manipulator in Unstructured Environments
- 30 October 2025
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 111 (4) , 1-20
Open AccessAutonomous Plug-in Charging for Wheeled Mobile Manipulator in Unstructured Environments