The Utility of Evolving Simulated Robot Morphology Increases with Task Complexity for Object Manipulation

Abstract

Embodied artificial intelligence argues that the body and brain play equally important roles in the generation of adaptive behavior. An increasingly common approach therefore is to evolve an agentʼs morphology along with its control in the hope that evolution will find a good coupled system. In order for embodied artificial intelligence to gain credibility within the robotics and cognitive science communities, however, it is necessary to amass evidence not only for how to co-optimize morphology and control of adaptive machines, but why. This work provides two new lines of evidence for why this co-optimization is useful: Here we show that for an object manipulation task in which a simulated robot must accomplish one, two, or three objectives simultaneously, subjugating more aspects of the robotʼs morphology to selective pressure allows for the evolution of better robots as the number of objectives increases. In addition, for robots that successfully evolved to accomplish all of their objectives, those composed of evolved rather than fixed morphologies generalized better to previously unseen environmental conditions.

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

“…selection pressures have a critical importance in ER, as exemplified by the work on novelty search [106] and behavioral diversity [131], for instance; 5. changing morphological or environmental complexity helps [16,19,18,14].…”

Tendon-Driven Variable Impedance Control Using Reinforcement Learning

“…By interacting directly with the environment, the robotic system learned to perform dynamic behavior never encountered in the demonstration, exploiting subtle phenomena without system ID. The advantages of this kind of embodied learning have been explored in a variety of experiments, for example learning circuit configurations [26] or robot control and morphology [1]. Manipulators incorporating complex actuation and eventually sensory capabilities could benefit from learning from task-relevant experience as opposed to expert knowledge.…”

Lexicase selection outperforms previous strategies for incremental evolution of virtual creature controllers

“…It has demonstrated an ability to address challenging problems in many task domains including: gaits (Clune et al, 2009), object manipulation (Bongard, 2008), biological study (Crespi et al, 2013;Doorly et al, 2009), and the optimization of morphology (Auerbach and Bongard, 2010;Bongard, 2010;Cheney et al, 2013). Often, these tasks have a single performance objective, or weighted sum, to assess the fitness of each individual.…”