Explainable, Interpretable, and Human-Aligned AI and Robotics

As artificial intelligence and robotic systems become increasingly autonomous and complex, their deployment in real-world, human-centered environments raises critical challenges related to interpretability, transparency, trust, and safety. While modern learning-based approaches, particularly foundation models and reinforcement learning, have achieved remarkable performance, they often operate as opaque “black boxes,” limiting human understanding and oversight. This lack of explainability hampers user trust, accountability, and effective human–AI collaboration, especially in safety-critical robotic applications. Addressing these challenges requires interdisciplinary approaches that integrate cognitive modeling, causal reasoning, multimodal grounding, and human-aware system design. By advancing explainable, interpretable, and human-aligned AI and robotics, the research community can enable systems that not only perform effectively but also communicate their reasoning, adapt to human context, and operate in a trustworthy and ethically responsible manner.

The goal of this Research Topic is to advance the development of socially intelligent robotic systems that can interact with humans in transparent, trustworthy, and context-aware ways. Social robots operate in dynamic, open-ended environments where human intentions, norms, and expectations play a central role, making explainability and human alignment critical challenges. This topic aims to foster innovations that enable robots to reason about human behavior, communicate their decisions and intentions, and adapt their actions based on social and contextual cues. By addressing challenges in interpretability, multimodal grounding, causal reasoning, and failure awareness, we seek to promote robust and ethically responsible human-robot interaction. Contributions are encouraged that bridge technical advances with human-centered design, supporting the deployment of social robots that can be understood, trusted, and effectively integrated into everyday human environments.

Authors are encouraged to address (but are not limited to) the following themes:
- Cognitive Modeling for Interpretable and Human-Aligned AI
- Foundation models for Interpretability and Transparency
- Interpretable and Transparent Robot Behavior
- Knowledge-Based Robotic Design
- Multimodal and Grounded Explanations
- LLM-based and Neural-Symbolic Approaches for Explanation Generation
- Evaluation for Explanations, Interpretability, Trust and Faithfulness
- Explainable Reinforcement Learning
- Failure Recognition, Assessment, and Recovery in Robotic Scenarios
- Human and Context Awareness in Robotics
- Causal and Counterfactual Reasoning in AI

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Policy and Practice Reviews
• Review
• Systematic Review
• Technology and Code

Keywords: Explainability, Interpretability, Transparency, Robot, AI

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.