# Exosense: A Vision-Based Scene Understanding System For Exoskeletons

**Source**: https://dynamic.robots.ox.ac.uk/projects/exosense/
**Parent**: https://dynamic.robots.ox.ac.uk/projects/

Jianeng Wang1, [Matias Mattamala](https://mmattamala.github.io/)1, [Christina Kassab](https://ckassab.github.io/)1, Guillaume Burger2, Fabio Elnecave2, [Lintong Zhang](https://ori.ox.ac.uk/people/lintong-zhang/)1, Marine Petriaux2, [Maurice Fallon](https://ori.ox.ac.uk/people/maurice-fallon/)1

1 [Dynamic Robot Systems Group](https://dynamic.robots.ox.ac.uk/), Oxford Robotics Institute, University of Oxford
\
2 [Wandercraft SAS](https://en.wandercraft.eu/)

Accepted to IEEE Robotics and Automation Letters (RA-L) 2025

IEEE

Arxiv

YouTube

\

\

**Abstract:**
Self-balancing exoskeletons are a key enabling technology for individuals with mobility impairments. While the current challenges focus on human-compliant hardware and control, unlocking their use for daily activities requires a scene perception system. In this work, we present *Exosense*, a vision-centric scene understanding system for self-balancing exoskeletons. We introduce a multi-sensor visual-inertial mapping device as well as a navigation stack for state estimation, terrain mapping and long-term operation. We tested Exosense attached to both a human leg and Wandercraft’s *Personal Exoskeleton* in real-world indoor scenarios. This enabled us to test the system during typical periodic walking gaits, as well as future uses in multi-story environments. We demonstrate that Exosense can achieve an odometry drift of about 4 cm per meter traveled, and construct terrain maps under 1 cm average reconstruction error. It can also work in a visual localization mode in a previously mapped environment, providing a step towards long-term operation of exoskeletons.

**Citation**

```
@ARTICLE{Wang2025,
  author={Wang, Jianeng and Mattamala, Matias and Kassab, Christina and Burger, Guillaume and Elnecave, Fabio and Zhang, Lintong and Petriaux, Marine and Fallon, Maurice},
  journal={IEEE Robotics and Automation Letters}, 
  title={Exosense: A Vision-Based Scene Understanding System for Exoskeletons}, 
  year={2025},
  volume={10},
  number={4},
  pages={3510-3517},
  doi={10.1109/LRA.2025.3543971}
}
```

**Acknowledgement:**
This work is supported by a Royal Society University Research Fellowship (Fallon, Kassab), Horizon Europe project DigiForest 101070405 (Wang), and EPSRC C2C Grant EP/Z531212/1 (Mattamala). We thank Wayne Tubby and Matthew Graham for hardware design support.