SMART is an efficient soft-tool that bridge the gap between Multi-Agent Path Finding (MAPF) and real-world application. More details can be found in our paper: Advancing MAPF towards the Real World: A Scalable Multi-Agent Realistic Testbed (SMART) [1].
This repo requires RPC for communication between server and clients.
Install Argos 3, please refer to this Link for instruction.
- To build the project, first navigate to the home folder Then:
git submodule init git submodule update mkdir build cd build cmake .. make -j If a linking error occurs, please remove the conda from your path (e.g. in your ~/.bashrc).
To produce fast but not debuggable code, type:
cmake -DCMAKE_BUILD_TYPE=Release .. make cd .. python run_sim.py --map_name=random-32-32-20.map --scen_name=random-32-32-20-random-1.scen --num_agents=50 --path_filename=example_paths_xy.txt --flip_coord=0 python run_sim.py --map_name=random-32-32-20.map --scen_name=random-32-32-20-random-1.scen --num_agents=50 --path_filename=example_paths_yx.txt --flip_coord=1 python run_sim.py --map_name=random-32-32-20.map --scen_name=random-32-32-20-random-1.scen --num_agents=50 --path_filename=example_paths_xy.txt --flip_coord=0 --headless=True python run_sim.py --map_name=random-32-32-20.map --scen_name=random-32-32-20-random-1.scen --num_agents=50 --path_filename=example_paths_yx.txt --flip_coord=1 --headless=True [1] Yan, Jingtian, Zhifei Li, William Kang, Kevin Zheng, Yulun Zhang, Zhe Chen, Yue Zhang, Daniel Harabor, Stephen Smith, and Jiaoyang Li. "Advancing MAPF towards the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)." arXiv preprint arXiv:2503.04798 (2025).