A reinforcement learning control approach for underwater manipulation under position and torque constraints

Carlucho, Ignacio; Paula, Mariano De; Barbalata, Corina; Acosta, Gerardo

doi:10.1109/ieeeconf38699.2020.9389378

Cited by 4 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RL has proven effective in terrestrial applications by transferring quadruped animal walking gaits onto robotic quadrupeds using RL [11] and teaching humanoid bipedal robots how to walk effectively [12]. Additionally, in an underwater context, RL has been successfully deployed to train a beaver like swimmer [13], underwater armed manipulators [14], and a simple two degree of freedom fin-based swimming systems [15]. High-fidelity models are essential for RL due to the substantial number of trials required for effective learning [16,17].…”

Section: Introductionmentioning

confidence: 99%

Using Reinforcement Learning to Develop a Novel Gait for a Bio-robotic California Sea Lion

Drago,

Kadapa,

Marcouiller

et al. 2024

Preprint

View full text Add to dashboard Cite

While researchers have made notable progress in bio-inspired swimming robot development, a persistent challenge lies in creating propulsive gaits tailored to these robotic systems. The California sea lion achieves its robust swimming abilities through a careful coordination of foreflippers and body segments. In this paper, reinforcement learning (RL) was used to develop a novel sea lion foreflipper gait for a bio-robotic swimmer using a numerically modelled computational representation of the robot. This model integration enabled reinforcement learning to develop desired swimming gaits in the challenging underwater domain. The novel RL gait outperformed the characteristic sea lion foreflipper gait in the simulated underwater domain. When applied to the real-world robot, the RL constructed novel gait performed as well or better than the characteristic sea lion gait in many factors. This work shows the potential for using complimentary bio-robotic and numerical models with reinforcement learning to enable the development of effective gaits and maneuvers for underwater swimming vehicles.

show abstract