Open Access

ARTICLE

Multi-View Latent Imitation Learning with Mamba-Based Action Encoding for Unmanned Surface Vehicle Navigation

Manh-Tuan Ha¹, Nhu-Nghia Bui², Dinh-Quy Vu^1,*, Thai-Viet Dang^2,*

1 Department of Vehicle and Energy Conversion Engineering, School of Mechanical Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam
2 Department of Mechatronics, School of Mechanical Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam

* Corresponding Authors: Dinh-Quy Vu. Email: ; Thai-Viet Dang. Email:

(This article belongs to the Special Issue: Intelligent Perception, Decision-making and Security Control for Unmanned Systems in Complex Environments)

Computers, Materials & Continua 2026, 88(1), 47 https://doi.org/10.32604/cmc.2026.078280

Received 28 December 2025; Accepted 15 April 2026; Issue published 08 May 2026

Abstract

The development of Unmanned Surface Vehicles (USVs) has become a key focus in marine robotics, fueling the need for navigation systems capable of performing complex and delicate tasks with speed and precision. However, the end-to-end path tracking process often encounters challenges in learning efficiency, and generalization, and varying environmental conditions. To achieve sample-efficient and robust USV navigation in dynamic maritime environments, the paper proposes a novel hierarchical multi-view latent imitation learning (IL) architecture. By formulating a latent IL objective, the framework disentangles diverse navigation modalities through continuous variables, preventing mode collapse and enhancing behavioral adaptability to non-stationary conditions. High-dimensional multi-view observations are transformed via a ViT-based backbone into compressed latent features to minimize redundant environmental information. These representations are processed by a Mamba-based action encoder, which leverages selective state-space modeling to capture long-term temporal dependencies with high computational efficiency. A UNet-based decoder subsequently forecasts optimal action sequences by synthesizing spatial maps to infer critical environment-agent relationships. This preliminary multi-view latent IL-based trajectory ensures precise tracking and dynamic stability while adhering to physical vehicle constraints. Experimental results validate that this end-to-end approach achieves robust path planning effectiveness, obstacle avoidance capability, and model training efficiency in complex, multi-modal maritime scenarios.

---

Keywords

---