Official code for IROS2023 paper "NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning".
For information, please refer to our website.
Correspondence to:
- Weizheng Wang (wang5716@purdue.edu)
Developing robotic technologies for use in human society requires ensuring the safety of robots' navigation behaviors while adhering to pedestrians' expectations and social norms. However, understanding complex human-robot interactions (HRI) to infer potential cooperation and response among robots and pedestrians for cooperative collision avoidance is challenging. To address these challenges, we propose a novel socially-aware navigation benchmark called NaviSTAR, which utilizes a hybrid Spatio-Temporal grAph tRansformer to understand interactions in human-rich environments fusing crowd multi-modal dynamic features. We leverage an off-policy reinforcement learning algorithm with preference learning to train a policy and a reward function network with supervisor guidance. Additionally, we design a social score function to evaluate the overall performance of social navigation. To compare, we train and test our algorithm with other state-of-the-art methods in both simulator and real-world scenarios independently. Our results show that NaviSTAR outperforms previous methods with outstanding performance.
[1]. (Under Review) Human-Robot Cooperative Distribution Coupling for Hamiltonian-Constrained Social Navigation
https://arxiv.org/pdf/2409.13573
[2]. (Under Review) Hyper-SAMARL: Hypergraph-based Coordinated Task Allocation and Socially-aware Navigation for Multi-Robot Systems
https://arxiv.org/pdf/2409.11561
[3]. (ICRA-2024) Multi-Robot Cooperative Socially-Aware Navigation Using Multi-Agent Reinforcement Learning
https://arxiv.org/pdf/2309.15234
[4]. (Under Review) SRLM: Human-in-Loop Interactive Social Robot Navigation with Large Language Model and Deep Reinforcement Learning
https://https//arxiv.org/pdf/2403.15648
[5]. (IROS-2022) FAPL: Feedback-efficient Active Preference Learning for Socially Aware Robot Navigation
https://ieeexplore.ieee.org/document/9981616
- OS: Ubuntu 20.04
- CPU: Intel i9-13900K
- GPU: Nvidia Geforce RTX 4090
- Python: 3.8
- Install Pytorch1.8.1
pip install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
- Install the dependencies from the
requirements.txt:
pip install -r requirements.txt
- Install Python-RVO2 library.
- To train a model with onpolicy algorithm PPO, Please run:
python train.py
- To train a model with offpolicy algorithm SAC, Please run:
python train_sac.py
Training model will be saved in data/navigation
Our pre-trained model (NaviSTAR) was saved in data/navigation/star_sac
To evaluate the model performance, please run:
python test.py
or
python test_sac.py
.giffiles were saved in gif
The visulaization cases of NaviSTAR were saved in gif/star_sac
If you find this repository useful, please cite our paper:
@inproceedings{wang2023navistar,
title={Navistar: Socially aware robot navigation with hybrid spatio-temporal graph transformer and preference learning},
author={Wang, Weizheng and Wang, Ruiqi and Mao, Le and Min, Byung-Cheol},
booktitle={2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
pages={11348--11355},
year={2023},
organization={IEEE}
}
This code partly bases on DSRNN, SAC. We thank the authors for releasing their code.
Le Mao, Weizheng Wang, and Byung-Cheol Min