Morphological change in machines accelerates the evolution of robust behavior

195 citations recorded by the source corpus.

How researchers see this paper

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

From evolutionary computation to the evolution of things (2015, background): “Artificial evolution implemented on real hardware, as in evolutionary robotics, offers a new research instrument to this end 42,92,93,94,95,96,97 .”
Reinforcement Learning for Improving Agent Design (2018, background): “Evolution plays a vital role in shaping an organism’s body to adapt to its environment; the brain and its ability to learn is only one of many body components that is co-evolved together [11, 47].”
A Neuroevolution Approach to General Atari Game Playing (2014, background): “Neuroevolution algorithms [13], [32] have been successful on a variety of tasks including quadruped locomotion [8], [50], evolution of morphology [6], design of robot morphology and control [29], Checkers [14], Unreal Tournament [38], and game playing [5], [47].”
Single-unit pattern generators for quadruped locomotion (2013, background): “evolving a special kind of neural network called a continuous time recurrent neural network (CTRNN) [3, 4, 35].”
The interaction of maturational constraints and intrinsic motivations in active motor development (2011, background): “…studies about maturational constraints only considers preprogrammed continuous clocks [17], or discrete release depending on notions of learning saturation [26] or estimation of success [27], no system allowing a continuous active control of these constraints has been proposed in the literature.”