This review provides a comprehensive survey of localization and mapping (L/M) techniques for self-driving vehicles. The authors analyze the current state of the art in feature extraction, mapping, and localization methods, as well as the challenges and future directions in this field. The paper discusses the importance of L/M in enabling autonomous driving, which aims to improve driving experiences, reduce accidents, and enhance safety and comfort for users. It also highlights the environmental impact of autonomous vehicles, including energy consumption, emissions, and integration into smart cities. The review categorizes feature extraction methods into semantic, non-semantic, and deep learning approaches. Semantic features involve extracting meaningful objects like roads, buildings, and poles, while non-semantic features provide abstract representations of the environment. Deep learning methods use neural networks to extract features from sensor data, such as LiDAR and camera inputs. The paper evaluates the effectiveness of these methods in terms of robustness, representativeness, and accessibility. The survey also examines methods for creating vehicle environment maps, considering both commercial and academic solutions. It distinguishes between known and unknown environments and proposes solutions for each. The paper explores different approaches to vehicle localization, classifying them based on mathematical characteristics and priorities. Each section concludes with related challenges and future directions. The review highlights security issues in self-driving vehicles, including potential vulnerabilities to attacks and the need for defense mechanisms. It also discusses the environmental impact of autonomous vehicles, including energy consumption, emissions, and integration into smart cities. The paper concludes with a discussion on the potential impacts of autonomous driving, emphasizing the need for further research and development in this area. The authors emphasize the importance of robust and accurate L/M techniques for the successful deployment of self-driving vehicles.This review provides a comprehensive survey of localization and mapping (L/M) techniques for self-driving vehicles. The authors analyze the current state of the art in feature extraction, mapping, and localization methods, as well as the challenges and future directions in this field. The paper discusses the importance of L/M in enabling autonomous driving, which aims to improve driving experiences, reduce accidents, and enhance safety and comfort for users. It also highlights the environmental impact of autonomous vehicles, including energy consumption, emissions, and integration into smart cities. The review categorizes feature extraction methods into semantic, non-semantic, and deep learning approaches. Semantic features involve extracting meaningful objects like roads, buildings, and poles, while non-semantic features provide abstract representations of the environment. Deep learning methods use neural networks to extract features from sensor data, such as LiDAR and camera inputs. The paper evaluates the effectiveness of these methods in terms of robustness, representativeness, and accessibility. The survey also examines methods for creating vehicle environment maps, considering both commercial and academic solutions. It distinguishes between known and unknown environments and proposes solutions for each. The paper explores different approaches to vehicle localization, classifying them based on mathematical characteristics and priorities. Each section concludes with related challenges and future directions. The review highlights security issues in self-driving vehicles, including potential vulnerabilities to attacks and the need for defense mechanisms. It also discusses the environmental impact of autonomous vehicles, including energy consumption, emissions, and integration into smart cities. The paper concludes with a discussion on the potential impacts of autonomous driving, emphasizing the need for further research and development in this area. The authors emphasize the importance of robust and accurate L/M techniques for the successful deployment of self-driving vehicles.