# Bayesian Optimization Using Domain Knowledge on the ATRIAS Biped

arXiv: https://arxiv.org/abs/1709.06047 · HTML: https://mlsanity.com/paper/1709.06047/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2017.

## Built on by (most cited first, 17 of 17)

- [Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces](https://mlsanity.com/paper/2304.11468/) (2023)
- [Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces](https://mlsanity.com/paper/2307.00618/) (2023)
- [Geometry-aware Bayesian Optimization in Robotics using Riemannian Mat'ern Kernels](https://mlsanity.com/paper/2111.01460/) (2021)
- [Rethinking Optimization with Differentiable Simulation from a Global Perspective](https://mlsanity.com/paper/2207.00167/) (2022)
- [Understanding High-Dimensional Bayesian Optimization](https://mlsanity.com/paper/2502.09198/) (2025)
- [Benchmarking Potential Based Rewards for Learning Humanoid Locomotion](https://mlsanity.com/paper/2307.10142/) (2023)
- [Safe Value Functions](https://mlsanity.com/paper/2105.12204/) (2021)
- [DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies](https://mlsanity.com/paper/2310.05714/) (2023)
- [Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks](https://mlsanity.com/paper/2207.03952/) (2022)
- [High-Dimensional Bayesian Optimization via Random Projection of Manifold Subspaces](https://mlsanity.com/paper/2412.16554/) (2024)
- [Experimenting, Fast and Slow: Bayesian Optimization of Long-term Outcomes with Online Experiments](https://mlsanity.com/paper/2506.18744/) (2025)
- [Deep Kernel and Image Quality Estimators for Optimizing Robotic Ultrasound Controller using Bayesian Optimization](https://mlsanity.com/paper/2310.07392/) (2023)
- [CobBO: Coordinate Backoff Bayesian Optimization with Two-Stage Kernels](https://mlsanity.com/paper/2101.05147/) (2021)
- [Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments](https://mlsanity.com/paper/2101.07599/) (2021)
- [Scaffolded Learning of In-place Trotting Gait for a Quadruped Robot with Bayesian Optimization](https://mlsanity.com/paper/2101.09961/) (2021)
- [Autotuning Bipedal Locomotion MPC with GRFM-Net for Efficient Sim-to-Real Transfer](https://mlsanity.com/paper/2409.15710/) (2024)
- [Offline Multi-Task Multi-Objective Data-Driven Evolutionary Algorithm with Language Surrogate Model and Implicit Q-Learning](https://mlsanity.com/paper/2512.15149/) (2025)

## Abstract (arXiv)

Controllers in robotics often consist of expert-designed heuristics, which can be hard to tune in higher dimensions. It is typical to use simulation to learn these parameters, but controllers learned in simulation often don't transfer to hardware. This necessitates optimization directly on hardware. However, collecting data on hardware can be expensive. This has led to a recent interest in adapting data-efficient learning techniques to robotics. One popular method is Bayesian Optimization (BO), a sample-efficient black-box optimization scheme, but its performance typically degrades in higher dimensions. We aim to overcome this problem by incorporating domain knowledge to reduce dimensionality in a meaningful way, with a focus on bipedal locomotion. In previous work, we proposed a transformation based on knowledge of human walking that projected a 16-dimensional controller to a 1-dimensional space. In simulation, this showed enhanced sample efficiency when optimizing human-inspired neuromuscular walking controllers on a humanoid model. In this paper, we present a generalized feature transform applicable to non-humanoid robot morphologies and evaluate it on the ATRIAS bipedal robot -- in simulation and on hardware. We present three different walking controllers; two are evaluated on the real robot. Our results show that this feature transform captures important aspects of walking and accelerates learning on hardware and simulation, as compared to traditional BO.