Evolving Quadrupedal Robot Gaits
Evolving Robot Gaits in Simulation
Creating gaits for physical robots is a longstanding and open challenge. Recently, the HyperNEAT generative encoding was shown to automatically discover a variety of gait regularities, producing fast, coordinated gaits, but only for simulated robots. A follow-up study found that HyperNEAT did not produce impressive gaits when they were evolved directly on a physical robot. A simpler encoding hand-tuned to produce regular gaits was tried on the same robot, and outperformed HyperNEAT, but these gaits were first evolved in simulation before being transferred to the robot. In this paper, we tested the hypothesis that the beneficial properties of HyperNEAT would outperform the simpler encoding if HyperNEAT gaits are first evolved in simulation before being transferred to reality. That hypothesis was confirmed, resulting in the fastest gaits yet observed for this robot, including those produced by nine different algorithms from three previous papers describing techniques for generating gaits for this robot. This result is important because it confirms that the early promise shown by generative encodings, specifically HyperNEAT, were not limited to evolving gaits in simulation, but indeed work on real robots.
Lee S., Yosinski J., Glette K., Lipson H., Clune J. (2013) "Evolving gaits for physical robots with the HyperNEAT generative encoding: the benefits of simulation". In preparation.
Evolving Robot Gaits in Hardware
Creating gaits for legged robots is an important task to enable robots to access rugged terrain, yet designing such gaits by hand is a challenging and time-consuming process. In this paper we investigate various algorithms for automating the creation of quadruped gaits. Because many robots do not have accurate simulators, we test gait-learning algorithms entirely on a physical robot. We compare the performance of two classes of gait-learning algorithms: locally searching parameterized motion models and evolving artificial neural networks with the HyperNEAT generative encoding. Specifically, we test six different parameterized learning strategies: uniform and Gaussian random hill climbing, policy gradient reinforcement learning, Nelder-Mead simplex, a random baseline, and a new method that builds a model of the fitness landscape with linear regression to guide further exploration. While all parameter search methods outperform a manually-designed gait, only the linear regression and Nelder-Mead simplex strategies outperform a random base- line strategy. Gaits evolved with HyperNEAT perform considerably better than all parameterized local search methods and produce gaits nearly 9 times faster than a hand-designed gait. The best HyperNEAT gaits exhibit complex motion patterns that contain multiple frequencies, yet are regular in that the leg movements are coordinated.
Yosinski J., Clune J., Hidalgo D., Nguyen S., Zagal J., Lipson H. (2011) "Evolving Robot Gaits in Hardware: the HyperNEAT Generative Encoding Vs. Parameter Optimization," In Proceedings of the European Conference on Artificial Life (ECAL). 890-897.