Opt-mimic: Imitation of optimized trajectories for dynamic quadruped behaviors

Y Fuchioka, Z ** in Low-Gravity Environment
H Sang, S Wang - Journal of Aerospace Engineering, 2024 - ascelibrary.org
Legged robots offer advantages such as rapid mobility, adept obstacle-surmounting
capabilities, and long mission life in lunar exploration missions. The low-gravity environment …

[HTML][HTML] Efficient reinforcement learning for 3d jum** monopods

R Bussola, M Focchi, A Del Prete, D Fontanelli… - Sensors, 2024 - mdpi.com
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 …

A Hierarchical Scheme for Adapting Learned Quadruped Locomotion

M Aractingi, PA Léziart, T Flayols… - 2023 IEEE-RAS …, 2023 - ieeexplore.ieee.org
The quadruped locomotion task is generally conditioned on a velocity command that is user-
defined. However, certain features of the locomotion are not represented in this high-level …

Reinforcement Learning Derived High-Alpha Aerobatic Manoeuvres for Fixed Wing Operation in Confined Spaces

R Clarke, L Fletcher, S East, T Richardson - Algorithms, 2023 - mdpi.com
Reinforcement learning has been used on a variety of control tasks for drones, including, in
previous work at the University of Bristol, on perching manoeuvres with sweep-wing aircraft …

Robust visual sim-to-real transfer for robotic manipulation

R Garcia, R Strudel, S Chen, E Arlaud… - 2023 IEEE/RSJ …, 2023 - ieeexplore.ieee.org
Learning visuomotor policies in simulation is much safer and cheaper than in the real world.
However, due to discrepancies between the simulated and real data, simulator-trained …