English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Task planning for robotic cooking involves generating a sequence of actionsfor a robot to prepare a meal successfully. This paper introduces a novel tasktree generation pipeline producing correct planning and efficient execution forcooking tasks. Our method first uses a large language model (LLM) to retrieverecipe instructions and then utilizes a fine-tuned GPT-3 to convert them into atask tree, capturing sequential and parallel dependencies among subtasks. Thepipeline then mitigates the uncertainty and unreliable features of LLM outputsusing task tree retrieval. We combine multiple LLM task tree outputs into agraph and perform a task tree retrieval to avoid questionable nodes andhigh-cost nodes to improve planning correctness and improve executionefficiency. Our evaluation results show its superior performance compared toprevious works in task planning accuracy and efficiency.

From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network