计算技术与自动化2026，Vol.45Issue(1)：1-8,8.DOI:10.16339/j.cnki.jsjsyzdh.202601001
融合Transformer与SAC算法的无人车视觉导航模型
Visual Navigation Model for Unmanned Ground Vehicles Integrating Transformer and SAC
摘要
Abstract
To address the high perception and safety requirements of autonomous navigation tasks in real-world environ-ments,this paper proposes an unmanned ground vehicle(UGV)visual navigation model that integrates Transformer and SAC(Soft Actor-Critic)algorithms.This model utilizes a Vision Transformer(ViT)network to extract image features,which serve as state inputs for the reinforcement learning algorithm,thereby enhancing the UGV's perception capabilities.To mitigate safety issues arising from visual sensor failures,a pre-trained radar policy is employed as a low computational cost emergency fallback during the decision-making process.Simulation experiments conducted in Gazebo demonstrate that the visual navigation policy trained with Vision Transformer not only converges faster and achieves higher success rates but also ensures navigation stability through effective coordination of multi-modal strategies during sensor failures.Further-more,the trained model exhibits excellent adaptability and robustness across different environments.关键词
深度强化学习/Vision Transformer/自主导航/Gazebo仿真Key words
deep reinforcement learning/Vision Transformer/autonomous navigation/Gazebo simulation分类
信息技术与安全科学引用本文复制引用
张益敏,刘磊..融合Transformer与SAC算法的无人车视觉导航模型[J].计算技术与自动化,2026,45(1):1-8,8.基金项目
航空科学基金资助项目(2024Z071108001) （2024Z071108001）
中央高校业务费资助项目(B240203012) （B240203012）
