articleNature Machine IntelligenceMar 18, 2025HYBRID OA

Embodied large language models enable robots to complete complex tasks in unpredictable environments

RMRuaridh Mon-WilliamsGLGen LiRLRan LongWDWenqian DuCGChristopher G. Lucas

Princeton University · Massachusetts Institute of Technology · +2 more institutions

PubMed
Indexed incrossrefpubmed

Abstract

Completing complex tasks in unpredictable settings challenges robotic systems, requiring a step change in machine intelligence. Sensorimotor abilities are considered integral to human intelligence. Thus, biologically inspired machine intelligence might usefully combine artificial intelligence with robotic sensorimotor capabilities. Here we report an embodied large-language-model-enabled robot (ELLMER) framework, utilizing GPT-4 and a retrieval-augmented generation infrastructure, to enable robots to complete long-horizon tasks in unpredictable settings. The method extracts contextually relevant examples from a knowledge base, producing action plans that incorporate force and visual feedback and enabling…

Citation impact

63
total citations
FWCI
61.18
Percentile
100%
References
58
Citations per year

Authors

5

Topics & keywords

Topics
Keywords
  • Embodied cognition
  • Robot
  • Computer science
  • Human–computer interaction
  • Artificial intelligence
No related works found for this paper.

Funding