Using response surfaces and expected improvement to optimize snake robot gait parameters

By Matthew Tesch, Jeff Schneider, Howie Choset. 2011

103 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computational Theory and Mathematics

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, methodology): “Some recent work including (Tesch et al., 2011; Stulp and Sigaud, 2012) suggest that much of the benefit of policy search is achieved by black-box methods.”
Deep Kernels for Optimizing Locomotion Controllers (2017, methodology): “For example, [5] use snake robots, [3] use a hexapod, which are statically stable robots.”
An Experimental Evaluation of Bayesian Optimization on Bipedal Locomotion (2014, methodology): “Both Probability of improvement [9] and Expected Improvement [14] have been previously employed in gait optimization.”
Bayesian optimization for learning gaits under uncertainty (2015, methodology): “Probability of improvement [9], expected improvement [10] and upper conﬁdence bound [13] have all been previously employed in gait optimization.”
Safe controller optimization for quadrotors with Gaussian processes (2015, background): “Examples include gait optimization of legged robots [10], [11] and controller optimization for a snake-like robot [12].”
Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective (2019, methodology): “This matches the intuition and results presented in recent works like (Bagnell and Schneider, 2001; Szita and Lörincz, 2006; Tesch et al., 2011; Salimans et al., 2017; Mania et al., 2018) that show parameter space black-box policy search methods outperforming state-of-the-art action space methods fo”
Residual Policy Learning (2018, background): “Focusing on control speciﬁcally, Bayesian optimization approaches are popular for learning controllers based on Gaussian process models of objective functions to be optimized [18, 19, 20, 21, 22].”
Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics (2016, unknown): “2007) and the optimization of the controller parameters of a snake-like robot (Tesch et al. 2011).”
Variational Bayesian Optimization for Runtime Risk-Sensitive Control (2012, background): “Recently there has been increased interest in applying Bayesian optimization (BO) algorithms to solve model-free policy search problems [17, 19, 20, 33, 28, 13].”