RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Control

1 code implementation • 5 Dec 2020 • Siddhant Gangapurwala, Mathieu Geisert, Romeo Orsolino, Maurice Fallon, Ioannis Havoutis

We evaluate the robustness of our method over a wide variety of complex terrains.

reinforcement-learning Reinforcement Learning (RL)

An Efficient Paradigm for Feasibility Guarantees in Legged Locomotion

no code implementations • 16 Nov 2020 • Abdelrahman Abdalla1, Michele Focchi, Romeo Orsolino, Claudio Semini

We here develop a general formulation of the improved feasible region to guarantee dynamic balance alongside the satisfaction of both actuation and kinematic limits for arbitrary terrains in an efficient manner.