SurGE: Surrogate Gradient-guided Evolution for Co-design of Legged Robots with Parallel Elasticity

2026-06-20 · Yulun Zhuang, Yue Qin, Justin Lu, Zelin Shen, Yichen Wang, Sicheng He, Yanran Ding arxiv

Co-design of legged robots with elastic elements is challenging due to the non-differentiability of contact dynamics and mechanism engagement. This paper presents SurGE, a framework that computes surrogate gradients of the design objective through a differentiable pipeline consisting of a kinodynamic single-rigid-body (Kino-SRB) model and a design-aware control policy, and injects them into CMA-ES via mean shift with cosine-annealed step decay. On a 4-DOF design space of a hopping robot with unidirectional parallel spring, SurGE achieves 6 times lower cross-seed standard deviation and 18% tighter population concentration compared to vanilla CMA-ES, while matching or improving the best objective. Hardware experiments on a 2D design subspace show that, starting from a hand-tuned initial design, SurGE reduces the design objective by 37.65% on hardware, with the improvement trend identified in simulation transferring consistently to the physical system. SurGE provides the potential to accelerate non-differentiable co-design problems in legged robots via surrogate model gradients.

📄 PDF Abstract BibTeX arXiv:2606.21866

Code (0)

등록된 구현이 없습니다.

Guided evolutionary strategies: Augmenting random search with surrogate gradients

2018-06-26 · ICLR 2019 5 · Niru Maheswaranathan, Luke Metz, George Tucker, Dami Choi 외

Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the …

Meta-Learning Reinforcement Learning

Guided Evolutionary Strategies: Escaping the curse of dimensionality in random search

2019-05-01 · ICLR 2019 5 · Niru Maheswaranathan, Luke Metz, George Tucker, Dami Choi 외

Meta-Learning Reinforcement Learning

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

2026-05-09 · Haoyu Huang, Boyu Liu, Linlin Yang, Yanjing Li 외 arxiv

The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Thro…

Image Classification Object Detection

NEUZZ: Efficient Fuzzing with Neural Program Smoothing

2018-07-15 · Dongdong She, Kexin Pei, Dave Epstein, Junfeng Yang 외

Fuzzing has become the de facto standard technique for finding software vulnerabilities. However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger software bugs. Most popular fuzzers use ev…

Evolutionary Algorithms

Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions

2019-10-11 · Florian Meier, Asier Mujika, Marcelo Matheus Gauy, Angelika Steger

Evolutionary Strategies (ES) are known to be an effective black-box optimization technique for deep neural networks when the true gradients cannot be computed, such as in Reinforcement Learning. We continue a recent line…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)