OpenTechnical
This is a record of a document published elsewhere, first published by the European Patent Office, as EP-4706901-A1, on 11 March 2026. OpenTechnical did not first disclose it. The identifier, hashes and timestamps below record what this library served and when, not when the material became public. View the original.

OT-2026-000002028

Method of reinforcement learning of a soft actor-critic robot control model for non-prehensile manipulation of an object

Published
Permanent URL
Classification
Robotics & Automation › Robot Architectures
Inventors
GABRIEL MIROSLAV, LE BAO HUY, NGO ANH VIEN
Assignee
BOSCH GMBH ROBERT
Original source
EP-4706901-A1, the European Patent Office, 11 March 2026
Document SHA-256
bc3387af50b1c46ddddc8d86ebfd59467e6c2c9d3a11011cc98ab0a12cb458b1

Abstract

Various aspects relate to a method (200) of reinforcement learning a soft actor-critic robot control model (302) for manipulation of an object, wherein an actor (320) of the soft actor-critic robot control model (302) includes a motion parameter policy for determining, for each point of an object-representing point cloud (306), a motion parameter indicating how to move the object when being contacted at the point and includes a location policy for determining which point of the object-representing point cloud (306) is to be contacted, wherein the method includes a training of the soft actor-critic robot control model (302) using both, an entropy of the motion parameter policy and an entropy of the location policy at each point of the object-representing point cloud (306).

Publication information

Plain textMarkdownManifestIntegrity record

Citation

OpenTechnical Publication OT-2026-000002028, “Method of reinforcement learning of a soft actor-critic robot control model for non-prehensile manipulation of an object,” published September 15, 2026 at 19:10:18 UTC, https://opentechnical.org/p/OT-2026-000002028.

To cite specific content, add the paragraph or figure numbers.

Terms

This record reproduces a document published elsewhere and is provided for reference and study. Rights in the original remain with its owner. See the publication policy.