Autonomous robots operating in complex and dynamic environments must plan, adapt, and act coherently over extended time horizons. Today, however, planning remains split between AI‑driven approaches—offering flexibility and abstraction—and control‑driven approaches—offering structure, guarantees, and predictability. Neither alone fully enables autonomy that must remain resilient under disturbances and reliable across long deployments, distribution shifts, and evolving conditions.
This workshop brings together researchers from robotics, AI, and control theory to explore how learning‑based reasoning and control‑driven structure can be unified into robust long‑horizon planning architectures. The goal is to identify shared representations, hybrid algorithmic principles, and evaluation methodologies that support trustworthy, stable, and scalable autonomy.
We invite contributions presenting recent results, ongoing work, or position papers on topics including:
Long‑horizon planning under uncertainty
Hybrid RL–MPC architectures and learning‑augmented control
Temporal logic, symbolic reasoning, and structured representations for robotic planning
Safety‑critical planning, robust control, and certified policy updates
Detection and mitigation of behavioral drift in learning‑based planning systems
Evaluation of long‑term robustness, degradation, and distribution shift
Multi‑robot planning and persistent autonomy
Submissions are welcome from both academia and industry, and interdisciplinary contributions bridging AI and control are especially encouraged.
Papers must be prepared according to the IROS'26 format, and can have 4-8 pages. We also encourage submitting new ideas, even if not fully developed yet.
Papers will be evaluated for quality, relevance to the workshop theme, clarity, and whether claims are well-supported by theory or experiments.
All accepted contributions will be presented as posters during our poster session, with room for selected spotlight presentations. Accepted papers will be posted on the workshop website, and will not be part of the IROS conference proceedings.
Together with the authors of accepted contributions, we will consider the opportunity to propose a special issue in the newly established IEEE Transactions on Robot Learning dedicated to “Resilient and Reliable Robot Planning: Integrating AI and Control for Long-Horizon Autonomy”.