Scholarlink

This paper reviews deep learning applications in autonomous vehicle navigation, emphasizing the role of Convolutional Neural Networks (CNNs) in key visual tasks like lane detection, obstacle avoidance, and traffic sign recognition. CNNs enable vehicles to process large image datasets for real-time decision-making. The study also covers simulators like CARLA and AirSim, essential for model training and testing in controlled environments. It highlights the importance of model accuracy, speed, and robustness to ensure safe navigation. Performance evaluation metrics and challenges in real-time decision-making are discussed, making this review a comprehensive guide for advancing self-driving, technologies.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning-Based Self-driving Car Simulator: Development and Evaluation

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • K. Nirosha,
  • S. Sowmya,
  • Omkar Ingle,
  • Nihal Sawrey,
  • Ch. Dinesh,
  • G. Suhas

摘要

This paper reviews deep learning applications in autonomous vehicle navigation, emphasizing the role of Convolutional Neural Networks (CNNs) in key visual tasks like lane detection, obstacle avoidance, and traffic sign recognition. CNNs enable vehicles to process large image datasets for real-time decision-making. The study also covers simulators like CARLA and AirSim, essential for model training and testing in controlled environments. It highlights the importance of model accuracy, speed, and robustness to ensure safe navigation. Performance evaluation metrics and challenges in real-time decision-making are discussed, making this review a comprehensive guide for advancing self-driving, technologies.