Anton Bernatskiy
University of Vermont
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Anton Bernatskiy.
genetic and evolutionary computation conference | 2015
Josh C. Bongard; Anton Bernatskiy; Kenneth R. Livingston; Nicholas Livingston; John H. Long; Marc L. Smith
Although recent work has demonstrated that modularity can increase evolvability in non-embodied systems, it remains to be seen how the morphologies of embodied agents influences the ability of an evolutionary algorithm to find useful and modular controllers for them. We hypothesize that a modular control system may enable different parts of a robots body to sense and react to stimuli independently, enabling it to correctly recognize a seemingly novel environment as, in fact, a composition of familiar percepts and thus respond appropriately without need of further evolution. Here we provide evidence that supports this hypothesis: We found that such robots can indeed be evolved if (1) the robots morphology is evolved along with its controller, (2) the fitness function selects for the desired behavior and (3) also selects for conservative and robust behavior. In addition, we show that if constraints (1) and (3) are relaxed, or structural modularity is selected for directly, the robots have too little or too much modularity and lower evolvability. Thus, we demonstrate a previously unknown relationship between modularity and embodied cognition: evolving morphology and control such that robots exhibit conservative behavior indirectly selects for appropriate modularity and, thus, increased evolvability.
Artificial Life | 2014
Anton Bernatskiy; Gregory S. Hornby; Josh C. Bongard
Recently it has been demonstrated that collaboration between automated algorithms and human users can be especially effective in robot behavior optimization tasks. In particular, we recently introduced a Fitness-based Search with Preferencebased Policy Learning (FS-PPL) approach, in which the algorithm models the user based on her preferences and then uses the model, along with the fitness function, to guide search. However, so far only interaction between a single human user and an evolutionary algorithm was considered. If multiple users contribute preferences, the algorithm must determine whether to model them separately or jointly. In this paper we describe an algorithm in which one evolutionary algorithm interacts with two users and determines the best way to model them automatically. We test the algorithm with automated substitutes for human users and show that it performs better for two users working together than for the same users working separately, thus demonstrating the potential for crowdsourcing robot behavior optimization.
Frontiers in Robotics and AI | 2016
Collin Cappelle; Anton Bernatskiy; Kenneth R. Livingston; Nicholas Livingston; Josh C. Bongard
In evolutionary robotics, populations of robots are typically trained in simulation before one or more of them are instantiated as physical robots. However, in order to evolve robust behavior, each robot must be evaluated in multiple environments. If an environment is characterized by
genetic and evolutionary computation conference | 2015
Anton Bernatskiy; Joshua Clifford Bongard
f
Frontiers in Robotics and AI | 2016
Nicholas Livingston; Anton Bernatskiy; Kenneth R. Livingston; Marc L. Smith; Jodi A. Schwarz; Joshua Clifford Bongard; David Wallach; John H. Long
free parameters, each of which can take one of
genetic and evolutionary computation conference | 2017
Sam Kriegman; Collin Cappelle; Francesco Corucci; Anton Bernatskiy; Nick Cheney; Josh C. Bongard
n_p
european conference on artificial life | 2017
Anton Bernatskiy; Josh C. Bongard
features, each robot must be evaluated in all
Adaptive Behavior | 2018
Anton Bernatskiy; Josh C. Bongard
n_p^f
genetic and evolutionary computation conference | 2017
Collin Cappelle; Anton Bernatskiy; Josh C. Bongard
environments to ensure robustness. Here we show that, if the robots are constrained to have modular morphologies and controllers, they only need to be evaluated in
conference on biomimetic and biohybrid systems | 2017
Collin Cappelle; Anton Bernatskiy; Josh C. Bongard
n_p