Learning a locomotion policy for quadruped robots has traditionally been constrained to a
specific robot morphology, mass, and size. The learning process must usually be repeated …

In this paper, we consider a general task of jumping varying distances and heights for a
quadrupedal robot in noisy environments, such as off of uneven terrain and with variable …

Quadruped animals are capable of seamless transitions between different gaits. While
energy efficiency appears to be one of the reasons for changing gaits, other determinant …

Legged robots are becoming increasingly agile in exhibiting dynamic behaviors such as
running and jumping. Usually, such behaviors are either optimized and engineered offline …

Deep Reinforcement Learning (RL) has demonstrated impressive results in solving complex
robotic tasks such as quadruped locomotion. Yet, current solvers fail to produce efficient …

Along with the advancement of robot skin technology, there has been notable progress in
the development of snake robots featuring body-surface tactile perception. In this study, we …

Typical legged locomotion controllers are designed or trained offline. This is in contrast to
many animals, which are able to locomote at birth, and rapidly improve their locomotion …

In reinforcement learning, the Markov Decision Process (MDP) framework typically operates
under a blocking paradigm, assuming a static environment during the agent's decision …

Classical snake robot control leverages mimicking snake-like gaits tuned for specific
environments. However, to operate adaptively in unstructured environments, gait generation …

Hexapod robots, with more legs and freedoms, excel in stability and terrain adaptability over
wheeled or quadruped robots. They are suited for tasks like geological exploration, outdoor …