Evolving coordinated quadruped gaits with the HyperNEAT generative encoding

  title={Evolving coordinated quadruped gaits with the HyperNEAT generative encoding},
  author={Jeff Clune and Benjamin E. Beckmann and Charles Ofria and Robert T. Pennock},
  journal={2009 IEEE Congress on Evolutionary Computation},
Legged robots show promise for complex mobility tasks, such as navigating rough terrain, but the design of their control software is both challenging and laborious. Traditional evolutionary algorithms can produce these controllers, but require manual decomposition or other problem simplification because conventionally-used direct encodings have trouble taking advantage of a problem's regularities and symmetries. Such active intervention is time consuming, limits the range of potential solutions… 

Figures from this paper

Evolving robot gaits in hardware: the HyperNEAT generative encoding vs. parameter optimization

This paper compares the performance of two classes of gait-learning algorithms: locally searching parameterized motion models and evolving artificial neural networks with the HyperNEAT generative encoding and a new method that builds a model of the fitness landscape with linear regression to guide further exploration.


Although the indirect encoding can evolve a stable bipedal gait, the overall neural architecture is brittle to small mutations, which suggests that some capabilities might be necessary to include beyond indirect encoding, such as lifetime adaptation.

Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding

The ability of generative soft-voxel systems to scale towards evolving a large diversity of complex, natural, multi-material creatures is suggested.

Combining MAP-Elites and Incremental Evolution to Generate Gaits for a Mammalian Quadruped Robot

This paper proposes a solution to overcome the problem of creating viable movement patterns for quadruped robots by implementing incremental evolution within the Quality Diversity framework, and shows that this approach is able to generate high fitness solutions early in the search process, keep these solutions and perform a more open-ended search towards the end of evolution.

Evolving Gaits for Physical Robots with the HyperNEAT Generative Encoding: The Benefits of Simulation

This paper tested the hypothesis that the beneficial properties of Hyper NEAT would outperform the simpler encoding if HyperNEAT gaits are first evolved in simulation before being transferred to reality, and it was confirmed, resulting in the fastest gaits yet observed for this robot.

Neuroevolutive Algorithms for Learning Gaits in Legged Robots

Gait generation for legged robots is a challenging task typically requiring either a hand-tuning design or a kinematic model of the robot morphology to compute the movements, generating a high

Generating gaits for physical quadruped robots: evolved neural networks vs. local parameterized search

This paper investigates various algorithms for automating the creation of quadruped gaits and compares the performance of two classes of learning gaits: locally searching parameterized motion models and evolving artificial neural networks with the HyperNEAT generative encoding.

Learning Fast Quadruped Robot Gaits with the RL PoWER Spline Parameterization

An algorithm called Policy learning by Weighting Exploration with the Returns, or RL PoWER is reported to have learned the fastest gait through only physical experiments yet reported in the literature, 16.3% faster than reported for HyperNEAT.

Rapid Evolution of Robot Gaits

This work investigates a simple and effective technique for rapidly evolving robot gaits in a manner of seconds or minutes rather than hours or days, and relies on two basic techniques to speed up evolution: Compositional Pattern Producing Network (CPPN) encodings and simple parameterized oscillator neurons.

Time delays in a HyperNEAT network to improve gait learning for legged robots

Gait generation for legged robots is an important task to allow an appropriate displacement in different scenarios. The classical manner to generate gaits involves handtuning design generating high



Modular neuroevolution for multilegged locomotion

The results suggest that the modular approach is effective for designing robust locomotion controllers for multilegged robots and scales well when the number of legs or their degrees of freedom are increased.

Generative representations for the automated design of modular physical robots

This work demonstrates an automatic design system that produces complex robots by exploiting the principles of regularity, modularity, hierarchy, and reuse, and demonstrates for the first time the evolution and construction of modular, three-dimensional, physically locomoting robots.

Gait Generation For Legged Robots

This paper surveys models of gait generation for legged robot generation, introduces the Ambler, a hexapod robot that can circulate its legs to produce unique gaits, and discusses the progress using a constraint-based method to generate theAmbler's gait.

Generative encoding for multiagent learning

The Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) generative approach to evolving neurocontrollers learns a set of coordinated policies encoded by a single genome representing a team of predator agents that work together to capture prey.

Autonomous evolution of dynamic gaits with two quadruped robots

This paper describes a system for autonomously evolving dynamic gaits on two of Sony's quadruped robots and shows the evolution of robust dynamic Gaits, one of which is used on the ERS-110, the first consumer version of AIBO.

Evolving the Walking Behaviour of a 12 DOF Quadruped Using a Distributed Neural Architecture

The main target of this paper is to show that the distributed architecture for the general control of robots can be applied to complex dynamic tasks like walking and show how a completely neural and distributed controller can be obtained for a robot ascomplex as Aibo on a task as complex as walking.

Evolving 3D Morphology and Behavior by Competition

This article describes a system for the evolution and coevolution of virtual creatures that compete in physically simulated three-dimensional worlds that can adapt to each other as they evolve simultaneously.

A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks

The main conclusion is that the ability to explore the space of regular connectivity patterns opens up a new class of complex high-dimensional tasks to neuroevolution.

A Hypercube-Based Indirect Encoding for Evolving Large-Scale Neural Networks

The main conclusion is that the ability to explore the space of regular connectivity patterns opens up a new class of complex high-dimensional tasks to neuroevolution.