Much of recent machine learning has focused on deep learning, in which neural network
weights are trained through variants of stochastic gradient descent. An alternative approach …

Simultaneous localization and map** responds to the problem of building a map of the
environment without any prior information and based on the data obtained from one or more …

This paper presents a machine learning approach to optimizing a quadrupedal trot gait for
forward speed. Given a parameterized walk designed for a specific robot, we propose using …

Legged locomotion holds the premise of universal mobility, a critical capability for many real-
world robotic applications. Both model-based and learning-based approaches have …

The reality gap, which often makes controllers evolved in simulation inefficient once
transferred onto the physical robot, remains a critical issue in evolutionary robotics (ER). We …

Gait optimization is a basic yet challenging problem for both quadrupedal and bipedal
robots. Although techniques for automating the process exist, most involve local function …

The contribution of the body to cognition and control in natural and artificial agents is
increasingly described as “offloading computation from the brain to the body,” where the …

The evolution of task-oriented control for robots with complex locomotor systems is currently
out of reach for traditional evolutionary computation techniques, as the coordination of a …

Over the last two decades the research and development of legged locomotion robots has
grown steadily. Legged systems present major advantages when compared with …

We present a general, two-stage reinforcement learning approach to create robust policies
that can be deployed on real robots without any additional training using a single …