Spot - Spatial AI & Robotics Lab

Spot is a quadruped robot provided by DARPA, serving as a core experimental platform for SAIR Lab’s research on real-world Spatial AI under mission-driven constraints. Rather than a lab-only system, Spot anchors our work in challenge-scale environments where robustness, repeatability, and recovery matter.

It is the platform where our methods are evaluated end-to-end: from perception and memory to planning and execution, across repeated deployments in the same evolving spaces.

Publications

Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints.
Qiwei Du, Zitong Zhan, Shaoshu Su, Bowen Li, Yi Du, Zhipeng Zhao, Taimeng Fu, Sebastian Scherer, Jiaoyang Li, Chen Wang.
arXiv preprint arXiv:2606.06877, 2026.

Reducing failures by 80% and eliminating exposure bias of neuro-symbolic task planning
```
@article{du2026iflax,
  title = {Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints},
  author = {Du, Qiwei and Zhan, Zitong and Su, Shaoshu and Li, Bowen and Du, Yi and Zhao, Zhipeng and Fu, Taimeng and Scherer, Sebastian and Li, Jiaoyang and Wang, Chen},
  journal = {arXiv preprint arXiv:2606.06877},
  year = {2026},
  url = {https://arxiv.org/abs/2606.06877},
  website = {https://sairlab.org/iflax/},
  video = {https://youtu.be/aRkq4TXYEhM},
  cover = {/img/posts/2026-06-08-iflax/iflax_cover_video.mp4},
  addendum = {Reducing failures by 80\% and eliminating exposure bias of neuro-symbolic task planning}
}
```
```
Du, Qiwei and Zhan, Zitong and Su, Shaoshu and Li, Bowen and Du, Yi and Zhao, Zhipeng and Fu, Taimeng and Scherer, Sebastian and Li, Jiaoyang and Wang, Chen, "Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints," arXiv preprint arXiv:2606.06877, 2026.
```