# Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits

arXiv: https://arxiv.org/abs/2003.06495 · HTML: https://mlsanity.com/paper/2003.06495/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [Active Preference-Based Gaussian Process Regression for Reward Learning](https://mlsanity.com/paper/2005.02575/) (2020)
- [Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences](https://mlsanity.com/paper/2602.23116/) (2026)
- [Preferential Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2406.14699/) (2024)
- [Human-in-the-Loop Pareto Optimization: Trade-off Characterization for Assist-as-Needed Training and Performance Evaluation](https://mlsanity.com/paper/2603.23777/) (2026)
- [Local Preferential Bayesian Optimization](https://mlsanity.com/paper/2606.02351/) (2026)
- [Learning a Speed-adaptive Hip Exoskeleton Control Policy Via Sim-to-real Reinforcement Learning](https://mlsanity.com/paper/2609.28027/) (2026)
- [Context-Continuous Preference Learning for Exoskeleton Personalization](https://mlsanity.com/paper/2609.28427/) (2026)

## Abstract (arXiv)

Optimizing lower-body exoskeleton walking gaits for user comfort requires understanding users' preferences over a high-dimensional gait parameter space. However, existing preference-based learning methods have only explored low-dimensional domains due to computational limitations. To learn user preferences in high dimensions, this work presents LineCoSpar, a human-in-the-loop preference-based framework that enables optimization over many parameters by iteratively exploring one-dimensional subspaces. Additionally, this work identifies gait attributes that characterize broader preferences across users. In simulations and human trials, we empirically verify that LineCoSpar is a sample-efficient approach for high-dimensional preference optimization. Our analysis of the experimental data reveals a correspondence between human preferences and objective measures of dynamicity, while also highlighting differences in the utility functions underlying individual users' gait preferences. This result has implications for exoskeleton gait synthesis, an active field with applications to clinical use and patient rehabilitation.