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

For effective human-robot interaction, robots need to understand, plan, andexecute complex, long-horizon tasks described by natural language. Recentadvances in large language models (LLMs) have shown promise for translatingnatural language into robot action sequences for complex tasks. However,existing approaches either translate the natural language directly into robottrajectories or factor the inference process by decomposing language into tasksub-goals and relying on a motion planner to execute each sub-goal. Whencomplex environmental and temporal constraints are involved, inference overplanning tasks must be performed jointly with motion plans using traditionaltask-and-motion planning (TAMP) algorithms, making factorization into subgoalsuntenable. Rather than using LLMs to directly plan task sub-goals, we insteadperform few-shot translation from natural language task descriptions to anintermediate task representation that can then be consumed by a TAMP algorithmto jointly solve the task and motion plan. To improve translation, weautomatically detect and correct both syntactic and semantic errors viaautoregressive re-prompting, resulting in significant improvements in taskcompletion. We show that our approach outperforms several methods using LLMs asplanners in complex task domains. See our project websitehttps://yongchao98.github.io/MIT-REALM-AutoTAMP/ for prompts, videos, and code.

AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers