GT-RIPL/Awesome-LLM-Robotics

A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

What it solves

This repository addresses the challenge of keeping up with the rapidly evolving field of robotics research that utilizes Large Language Models (LLMs) and Multi-Modal Models. It acts as a centralized, curated index for researchers and developers to find relevant academic papers, tools, and frameworks in this intersection.

How it works

The project is a community-maintained, curated list of academic papers and resources. It organizes these entries into logical categories such as reasoning, planning, manipulation, and safety. Each entry typically includes a link to the paper, its associated code repository, and a project website, allowing users to quickly explore specific research areas.

Who it’s for

This list is designed for robotics researchers, AI engineers, and students who want to stay informed about the latest advancements in applying foundation models to robotic control, task planning, and embodied intelligence.

Highlights

  • Categorized collection of research papers covering reasoning, planning, and manipulation.
  • Includes dedicated sections for simulation frameworks and safety/red-teaming.
  • Features a list of surveys to help newcomers understand the landscape of robotic language grounding.
  • Open for community contributions via pull requests to ensure the list remains current.

Related

  • Project
    isaac-sim/IsaacSim

    Isaac Sim is NVIDIA’s GPU‑accelerated robotics simulator built on Omniverse, supporting realistic physics, RTX sensor rendering, ROS 2 integration, synthetic data generation, and a reinforcement‑learning framework (Isaac Lab). It runs on Windows or Ubuntu with an RTX GPU and can be built from source, packaged as a binary, Python wheel, or Docker image.

  • Project
    MichaelGrupp/evo

    evo is a Python package that offers command‑line tools and a small library for loading, comparing, visualising, and analysing trajectory data from odometry and SLAM systems. It supports common formats (TUM, KITTI, EuRoC, ROS/ROS2 bags), provides metrics like absolute and relative pose error, and produces publication‑ready plots and tables. Installable via pip (Python 3.11+), it works cross‑platform and integrates optional features such as Qt back‑ends, map tiles, and Rerun visualisation.

  • Project
    Seeed-Projects/reBot-DevArm

    An open-source robotic arm platform designed for learning and developing Embodied AI, featuring full hardware blueprints and deep integration with ROS2, Isaac Sim, and LeRobot.

  • Project
    dimensionalOS/dimos

    An agent-native operating system for robotics that allows developers to build and control hardware like quadrupeds and drones using Python and LLM-based commands.