In the past decade, theory and applications of autonomous systems have been widely studied from multidisciplinary perspectives including robotics, artificial intelligence, and control theory. To realize adaptive optimization abilities of autonomous systems, various machine learning methods have been studied to discover knowledge from observed data. Due to the requirements of unknown and complex environments, it is necessary for autonomous systems to have improved learning ability such as online learning and learning from imbalanced data, for sensing, planning, and motion control. Efforts to address these difficulties include incremental learning from stream data, online reinforcement learning (RL), approximate dynamic programming (ADP), online learning with partial feedback, and explore/exploit tradeoffs. However, there are still many challenges in developing efficient machine learning algorithms with good generalization ability for autonomous systems in uncertain, dynamic environments.

To solve the above difficult problems related to machine learning in autonomous systems, it will be beneficial to bring together the researchers from machine learning, pattern recognition, robotics, and control theory. This special issue will provide a forum for different research efforts towards new machine learning theory and algorithms with applications to autonomous systems.

Potential topics include, but are not limited to:

• Online reinforcement learning for adaptive optimal control
• Approximate dynamic programming and adaptive critic designs
• Incremental learning theory and algorithms
• Online statistical learning and optimization
• Learning from stream data for object detection and classification
• Other machine learning approaches with applications in autonomous systems