Long-horizon Locomotion and Manipulation on a Quadrupedal Robot with Large Language Models

Authors:
  • YOYutao Ouyang
    Yutao Ouyang
  • JLJinhan Li
    Jinhan Li
  • YLYunfei Li
    Yunfei Li
  • ZLZhongyu Li
    Zhongyu Li
  • CYChao Yu
    Chao Yu
  • KSKoushil Sreenath
    Koushil Sreenath
  • YWYi Wu
    Yi Wu

Abstract
We present a large language model (LLM) based system to empower quadrupedal robots with problem-solving abilities for long-horizon tasks beyond short-term motions. Long-horizon tasks for quadrupeds are challenging since they require both a high-level understanding of the semantics of the problem for task planning and a broad range of locomotion and manipulation skills to interact with the environment. Our system builds a high-level reasoning layer with large language models, which generates hybrid discrete-continuous plans as robot code from task descriptions. It comprises multiple LLM agents: a semantic planner for sketching a plan, a parameter calculator for predicting arguments in the plan, and a code generator to convert the plan into executable robot code. At the low level, we adopt reinforcement learning to train a set of motion planning and control skills to unleash the flexibility of quadrupeds for rich environment interactions. Our system is tested on long-horizon tasks that are infeasible to complete with one single skill. Simulation and real-world experiments show that it successfully figures out multi-step strategies and demonstrates non-trivial behaviors, including building tools or notifying a human for help.

This publication has 10 references indexed in Scilit: