This paper reviews the application of foundation models in real-world robotics, focusing on their use in replacing specific components within existing robot systems. Foundation models, such as Large Language Models (LLMs) and Vision-Language Models (VLMs), are trained on large datasets and can be applied to a wide range of tasks through in-context learning, fine-tuning, or zero-shot methods. They are particularly useful in robotics for perception, motion planning, and control. The paper discusses how foundation models can be used for low-level perception, high-level perception, high-level planning, low-level planning, and data augmentation. It also covers the development of robotic foundation models, which are designed for robotics-specific tasks, including pre-trained visual representations, vision language models, and end-to-end control policies. The paper highlights various applications of foundation models in robotics, such as object recognition, navigation, manipulation, and communication. It concludes with a discussion of future challenges and implications for practical robot applications.This paper reviews the application of foundation models in real-world robotics, focusing on their use in replacing specific components within existing robot systems. Foundation models, such as Large Language Models (LLMs) and Vision-Language Models (VLMs), are trained on large datasets and can be applied to a wide range of tasks through in-context learning, fine-tuning, or zero-shot methods. They are particularly useful in robotics for perception, motion planning, and control. The paper discusses how foundation models can be used for low-level perception, high-level perception, high-level planning, low-level planning, and data augmentation. It also covers the development of robotic foundation models, which are designed for robotics-specific tasks, including pre-trained visual representations, vision language models, and end-to-end control policies. The paper highlights various applications of foundation models in robotics, such as object recognition, navigation, manipulation, and communication. It concludes with a discussion of future challenges and implications for practical robot applications.