Learning directed locomotion in modular robots with evolvable morphologies

Lan，Gongjin1,2; De Carlo，Matteo2; van Diggelen，Fuda2; Tomczak，Jakub M.2; Roijers，Diederik M.2,3,4; Eiben，A. E.2

2021-11-01

10.1016/j.asoc.2021.107688

APPLIED SOFT COMPUTING   影响因子和分区

1568-4946

The vision behind this paper looks ahead to evolutionary robot systems where morphologies and controllers are evolved together and ‘newborn’ robots undergo a learning process to optimize their inherited brain for the inherited body. The specific problem we address is learning controllers for the task of directed locomotion in evolvable modular robots. To this end, we present a test suite of robots with different shapes and sizes and compare two learning algorithms, Bayesian optimization and HyperNEAT. The experiments in simulation show that both methods obtain good controllers, but Bayesian optimization is more effective and sample efficient. We validate the best learned controllers by constructing three robots from the test suite in the real world and observe their fitness and actual trajectories. The obtained results indicate a reality gap, but overall the trajectories are adequate and follow the target directions successfully.

Bayesian optimization Directed locomotion Evolutionary robotics Evolvable morphologies Modular robots

EI

英语

第一 ; 通讯

20213010681798

Controllers ; Learning systems ; Modular robots ; Statistical tests

Robotics:731.5 ; Control Equipment:732.1 ; Mathematical Statistics:922.2

COMPUTER SCIENCE

2-s2.0-85111048539

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China
2.Department of Computer Science,Vrije Universiteit Amsterdam,Netherlands
3.AI laboratory,Vrije Universiteit Brussel,Belgium
4.Institute of ICT,HU University of Applied Sciences Utrecht,Netherlands

Lan，Gongjin,De Carlo，Matteo,van Diggelen，Fuda,et al. Learning directed locomotion in modular robots with evolvable morphologies[J]. APPLIED SOFT COMPUTING,2021,111.

Lan，Gongjin,De Carlo，Matteo,van Diggelen，Fuda,Tomczak，Jakub M.,Roijers，Diederik M.,&Eiben，A. E..(2021).Learning directed locomotion in modular robots with evolvable morphologies.APPLIED SOFT COMPUTING,111.

Lan，Gongjin,et al."Learning directed locomotion in modular robots with evolvable morphologies".APPLIED SOFT COMPUTING 111(2021).