The workshop brings together researchers from academia and industry working at the intersection of AI‑driven planning and control‑theoretic methods. Its goal is to foster a unified perspective on long‑horizon robot planning—one that combines the adaptability of learning with the predictability of control. By treating planning as a foundational, cross‑cutting capability, the workshop aims to advance resilient, reliable autonomy across domains such as mobile robotics, UAVs, manipulation, legged locomotion, and autonomous driving.
Topics of Interest (including but not limited to):
Learning‑based MPC, safe RL, hierarchical RL‑MPC, optimization‑based task and motion planning
Neural, diffusion, and hybrid planners with stability or safety filters
Safety shields, certified policy updates, robust MPC, adaptive controllers
Stability‑aware learning, adaptive control with learned dynamics
Formal verification, synthesis, and runtime assurance for learning-enabled systems
Shared abstractions for goals, constraints, and uncertainty (LTL/STL, Lyapunov functions, constraint graphs, value functions)
Hybrid symbolic–continuous planning and data‑driven components with guarantees
Evaluation of long‑horizon robustness, drift, degradation, and distribution shift
Applications in safety‑critical or long‑duration autonomy (aerial, ground, legged, field systems)
Important Dates:
Submission deadline: 17/07/2026 SUBMIT HERE!
Notification of acceptance: 20/08/2026
Camera‑ready deadline: TBA
Submission Format
We welcome original research papers, position papers, and work-in-progress contributions at the intersection of formal methods, artificial intelligence, robotics, planning, and control.
Authors may submit one of the following paper types:
Short papers (2–4 pages): describing preliminary results, emerging ideas, ongoing research, or concise summaries of recently published work.
Full papers (up to 8 pages): presenting original research contributions with sufficient technical detail and experimental or theoretical validation.
All submissions must follow the standard IROS format and will undergo peer review. Papers will be evaluated based on their relevance to the workshop theme, technical quality and originality, clarity of presentation, soundness of methodology, and the extent to which their claims are supported by theoretical analysis and/or experimental evidence.
The workshop is non-archival, allowing authors to submit work that is currently under review elsewhere or intended for future publication in conferences or journals. Accepted papers will be presented during the workshop as either spotlight talks or poster presentations.
Based on the number of submissions, the organizers will evaluate the possiblity 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".
Best Paper Awards
To recognize outstanding contributions, the workshop will present three Best Paper Awards. Award recipients will be selected based on the review process and presentation quality and will receive an official certificate at the end of the workshop.