Scalable robot task planning improves with ontology grounded framework
OntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task Planning
Robotics
Summary
Robots that follow instructions often struggle when tasks are long or locations large because they have trouble understanding where things are and what can be done next. The authors created OntoPlan, which uses a shared symbolic language to let robots better understand their surroundings and the task rules. This helps robots make better plans more efficiently, even in bigger spaces, and asks questions if instructions are unclear. OntoPlan was tested on many tasks and outperformed other methods in success and speed.
What this means in practice
- •For robotics engineers: Build robots that plan tasks efficiently in large indoor spaces using a symbolic approach for better spatial and action understanding.
- •For home automation developers: Create home robots that can handle complex cleaning or organization tasks with improved understanding of their environment and instructions.
Authors
Hyeongwoo Nam, Woongje Cho, Juwon Kim, Jongeun Choi
Abstract
Large language model (LLM)-based robot task planning is promising for open-ended instruction following, but degrades on long-horizon tasks in large environments. When spatial information is conveyed to the LLM through text, the model can fail to capture spatial context, and token cost grows with environment size. Generating action sequences directly with an LLM also makes it difficult to satisfy the current world state and action preconditions. We address this with an ontology-grounded scene representation that aligns objects, spaces, relations, and states in a shared symbolic vocabulary for spatial reasoning and task planning, and with OntoPlan, an agentic framework that interprets instructions, selectively retrieves task-relevant information, formalizes goals and constraints, and produces executable plans. Across 150 general tasks spanning five indoor environments and three scene scales, OntoPlan achieves 0.89 average task success, compared with 0.27 for the strongest baseline, while using 18.1k total tokens per task on average, about 5.6$\times$ fewer than the most efficient baseline. These advantages persist as scene scale increases, whereas prior methods degrade more sharply in success and remain far more costly in tokens. OntoPlan also responds appropriately to ambiguous or infeasible instructions by asking follow-up questions or reporting insufficient information rather than committing to invalid plans. Code available at https://github.com/namhyeongwoo/OntoPlan.