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

Ignacio Carlucho, Mariano De Paula, Corina Barbalata, Gerardo G. Acosta

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In marine operations underwater manipulators play a primordial role. However, due to uncertainties in the dynamic model and disturbances caused by the environment, low-level control methods require great capabilities to adapt to change. Furthermore, under position and torque constraints the requirements for the control system are greatly increased. Reinforcement learning is a data driven control technique that can learn complex control policies without the need of a model. The learning capabilities of these type of agents allow for great adaptability to changes in the operative conditions. In this article we present a novel reinforcement learning low-level controller for the position control of an underwater manipulator under torque and position constraints. The reinforcement learning agent is based on an actor-critic architecture using sensor readings as state information. Simulation results using the Reach Alpha 5 underwater manipulator show the advantages of the proposed control strategy.

Original languageEnglish
Title of host publication2020 Global Oceans
Subtitle of host publicationSingapore - U.S. Gulf Coast
ISBN (Electronic)9781728154466
Publication statusPublished - 9 Apr 2021
Event2020 Global Oceans: Singapore - U.S. Gulf Coast - Biloxi, United States
Duration: 5 Oct 202030 Oct 2020


Conference2020 Global Oceans
Abbreviated titleOCEANS 2020
Country/TerritoryUnited States


  • Deep Deterministic Policy Gradient
  • Intelligent control
  • Neural networks
  • Reinforcement learning
  • Underwater manipulation

ASJC Scopus subject areas

  • Oceanography
  • Automotive Engineering
  • Instrumentation
  • Signal Processing


Dive into the research topics of 'A reinforcement learning control approach for underwater manipulation under position and torque constraints'. Together they form a unique fingerprint.

Cite this