https://unibwm-ifs-ailab.github.io/tag/ai/AIHugo Blox Builder (https://hugoblox.com)en-usThu, 04 Dec 2025 00:00:00 +0000https://unibwm-ifs-ailab.github.io/media/icon_hu4951135369306263711.pnghttps://unibwm-ifs-ailab.github.io/tag/ai/https://unibwm-ifs-ailab.github.io/post/2025-12-01-ajcai-australien/Thu, 04 Dec 2025 00:00:00 +0000https://unibwm-ifs-ailab.github.io/post/2025-12-01-ajcai-australien/<p>At the <strong>26th Australasian Joint Conference on Artificial Intelligence (AJCAI 2025)</strong>, held in Canberra, Australia, Björn Döschl presented the paper <em>&ldquo;Planner-Independent Extraction of Goals and Constraints from Natural Language for Open-World Mobile Robot Missions.&rdquo;</em> The work introduces a planner-independent pipeline for extracting goals and constraints from natural-language mission instructions and projecting them into planner-specific representations for open-world mobile robot missions.</p> <section> <h2>Conference Details</h2> <p><strong>Conference:</strong> <a href="https://ajcai2025.org/">AJCAI 2025</a></p> <p><strong>Full name:</strong> 26th Australasian Joint Conference on Artificial Intelligence</p> <p><strong>Date:</strong> 1–5 December 2025</p> <p><strong>Presentation date:</strong> 4 December 2025</p> <p><strong>Location:</strong> Lowitja O'Donoghue Cultural Centre, Australian National University, Canberra, Australia</p> <p><strong>Session:</strong> Short Oral Session 8: Robotic AI</p> <p><strong>Summary:</strong> Björn Döschl presented research on planner-independent goal and constraint extraction for open-world mobile robot missions.</p> </section> <section> <h2>Paper Details</h2> <p><strong>Title:</strong> Planner-Independent Extraction of Goals and Constraints from Natural Language for Open-World Mobile Robot Missions</p> <p><strong>Authors:</strong> Björn Döschl and Jane Jean Kiam</p> <p><strong>Proceedings:</strong> AI 2025: Advances in Artificial Intelligence, Lecture Notes in Computer Science, vol. 16371</p> <p><strong>Pages:</strong> 453–465</p> <p><strong>DOI:</strong> <a href="https://doi.org/10.1007/978-981-95-4972-6_35">10.1007/978-981-95-4972-6_35</a></p> <p><strong>Springer page:</strong> <a href="https://www.springerprofessional.de/en/planner-independent-extraction-of-goals-and-constraints-from-nat/51764620">Planner-Independent Extraction of Goals and Constraints from Natural Language for Open-World Mobile Robot Missions</a></p> </section> <section> <h2>Paper Summary</h2> <p> The paper addresses problem-instance acquisition for robot missions described in natural language. It combines an LLM-based goal and constraint extraction module with a planner-specific projection layer, allowing operator-defined mission instructions to be translated into structured representations for downstream planning systems. The approach is evaluated on mission instructions and demonstrated in AUSPEX for a Search and Rescue UAV scenario. </p> </section>