This paper provides a comprehensive survey of recent machine learning (ML) approaches applied to mobile robot control, categorized into supervised learning, unsupervised learning, and reinforcement learning. The authors discuss the strengths and weaknesses of these methods and highlight future research directions. The survey covers various tasks such as position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multi-robot coordination. Key challenges include complex algorithms, limited computational resources, real-time decision-making, adaptability to changing environments, data acquisition, and safety and reliability. The paper also reviews specific applications of ML in wheeled and walking robots, emphasizing the need for further research in nature-inspired walking robots.This paper provides a comprehensive survey of recent machine learning (ML) approaches applied to mobile robot control, categorized into supervised learning, unsupervised learning, and reinforcement learning. The authors discuss the strengths and weaknesses of these methods and highlight future research directions. The survey covers various tasks such as position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multi-robot coordination. Key challenges include complex algorithms, limited computational resources, real-time decision-making, adaptability to changing environments, data acquisition, and safety and reliability. The paper also reviews specific applications of ML in wheeled and walking robots, emphasizing the need for further research in nature-inspired walking robots.