Transactions on Robot Learning (T-RL) publishes fundamental advances in development and use of Artificial Intelligence (AI) methods that address challenges specific to robotic and automation systems, incorporating the constraints and opportunities present in physical systems, and tackling key barriers to the full deployment of AI in a robot from perception to control.

Examples of topics within the scope of T-RL include, but are not limited to, transfer learning for efficient knowledge transfer across robotic platforms, tasks, and environments; methods tailored to key robotic challenges such as limited pre-existing data, poor generalizability, slow learning timescales and low robustness in physical deployment; algorithmic advances in AI-based control of robots and automation systems that offer safety and reliability guarantees. Topics may include robot learning algorithms for human-robot collaboration, such as methods for prediction of human behavior; explainable and transparent AI-driven control of robots and automation systems; building trust; and attributing responsibility.

T-RL publishes work with both theoretical and practical significance. This includes foundational mathematical and algorithmic advances and application papers, including benchmarks describing robotics and automation use cases that enable reproducibility and comparisons between approaches. Applications in real hardware in addition or to complement evaluation in simulation are expected. Tutorial and review papers provide an overview of developments and/or use of statistical learning algorithms and approaches that advance new capabilities in robotics and automation.