# Powered Prosthesis Locomotion on Varying Terrains: Model-Dependent Control with Real-Time Force Sensing

arXiv: https://arxiv.org/abs/2105.11561 · HTML: https://mlsanity.com/paper/2105.11561/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2021.

## Built on by (most cited first, 2 of 2)

- [Ground Reaction Force Estimation via Time-aware Knowledge Distillation](https://mlsanity.com/paper/2506.10265/) (2025)
- [Selective Correlation Based Knowledge Distillation for Ground Reaction Force Estimation](https://mlsanity.com/paper/2605.00888/) (2026)

## Abstract (arXiv)

Lower-limb prosthesis wearers are more prone to falling than non-amputees. Powered prostheses can reduce this instability of passive prostheses. While shown to be more stable in practice, powered prostheses generally use model-independent control methods that lack formal guarantees of stability and rely on heuristic tuning. Recent work overcame one of the limitations of model-based prosthesis control by developing a class of provably stable prosthesis controllers that only require the human interaction forces with the prosthesis, yet these controllers have not been realized with sensing of these forces in the control loop. Our work realizes the first model-dependent prosthesis knee controller that uses in-the-loop on-board real-time force sensing at the interface between the human and prosthesis and at the ground. The result is an optimization-based control methodology that formally guarantees stability while enabling human-prosthesis walking on a variety of terrain types. Experimental results demonstrate this force-based controller outperforms similar controllers not using force sensors, improving tracking across 4 terrain types.