This is the main repo for Air-Ground Collaboration for Language-Specified Missions in Unknown Environements. This repo contains the tools and software for this paper, including the aerial perception stack, aerial mission planning, ground autonomy stack, the ground LLM-planner and the distributed database for cross platform communication.
The repo is organized as follows:
- MOCHA: distributed database for cross-platform opportunistic communication.
- Air-Router: UAV planner that balances exploration and syncing data to the UGV.
- Symbiote: UAV Perception stack for state estimation and semantics graph building.
- SPINE: UGV LLM-enabled planner that ingests the semantic graph from the UAV.
- Jackal-Infrastructure: UGV autonomy and perception stack.
See the above repositories for details on how to run them.
Clone this repo with:
git clone --recursive https://github.com/KumarRobotics/lang-air-ground-teaming
This repo offers a visualizer for the semantic graph which can be viewed in real time or can after via a bag file. You need to add a map box key in map.js, once this is done you can run ros2 launch symbiote_ag viz.launch.py. If you want to view this in real time change the IP address from 127.0.0.1 to the IP of your robot and then you can connect to it via your browser on your basestation.
@ARTICLE{11053857,
author={Cladera, Fernando and Ravichandran, Zachary and Hughes, Jason and Murali, Varun and Nieto-Granda, Carlos and Ani Hsieh, M. and Pappas, George J. and Taylor, Camillo J. and Kumar, Vijay},
journal={IEEE Transactions on Field Robotics},
title={Air-Ground Collaboration for Language-Specified Missions in Unknown Environments},
year={2025},
volume={},
number={},
pages={1-1},
doi={10.1109/TFR.2025.3584019}}