In robotics, the ultimate goal of reinforcement learning is to endow robots with the ability to
learn, improve, adapt and reproduce tasks with dynamically changing constraints based on …

Evolutionary robotics using real hardware has been almost exclusively restricted to evolving
robot controllers, but the technology for evolvable morphologies is advancing quickly. We …

This work presents a platform for evolution of morphology in full cycle reconfigurable
hardware: The EMERGE (Easy Modular Embodied Robot Generator) modular robot …

Creating gaits for physical robots is a longstanding and open challenge. Recently, the
HyperNEAT generative encoding was shown to automatically discover a variety of gait …

Modern humanoid robots include not only active compliance but also passive compliance.
Apart from improved safety and dependability, availability of passive elements, such as …

The automation of manufacturing processes as a result of the Fourth Industrial Revolution,
rendered faster under the influence of the COVID-19 pandemic, leads to a question as to …

We consider a complex control problem: making a monopod accurately reach a target with a
single jump. The monopod can jump in any direction at different elevations of the terrain …

Learning to navigate unknown environments from scratch is a challenging problem. This
work presents a system that integrates world models with curiosity-driven exploration for …

This paper addresses a principal problem of in vivo evolution of modular multi-cellular
robots. To evolve robot morphologies and controllers in real-space and real-time we need a …

The main question this paper addresses is: What combination of a robot controller and a
learning method should be used, if the morphology of the learning robot is not known in …