Cristian Beltran

Cristian Beltran
Osaka University | Handai · School of Engineering Science

Master of Engineering
Intern at Omron Sinic X since April 2021 until September 2022

About

19
Publications
3,120
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
147
Citations
Citations since 2016
18 Research Items
146 Citations
20162017201820192020202120220204060
20162017201820192020202120220204060
20162017201820192020202120220204060
20162017201820192020202120220204060
Additional affiliations
October 2019 - present
Osaka University
Position
  • PhD Student
Education
April 2017 - October 2019
Osaka University
Field of study
  • Robotics and AI
January 2009 - August 2013
Universidad de La Sabana
Field of study
  • Information Engineering

Publications

Publications (19)
Conference Paper
Full-text available
In this paper, we seek to improve the robotic grasping using reinforcement learning towards the automation of assembly tasks. We employed a reinforcement learning method based on the policy search algorithm, call Guided Policy Search, to learn policies for the grasping problem. The goal was to evaluate if policies trained solely using sets of primi...
Article
Full-text available
Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges, especially when using rigid position-controlled manipulators. These challenges include the need for a robust con...
Article
Full-text available
Industrial robot manipulators are playing a significant role in modern manufacturing industries. Though peg-in-hole assembly is a common industrial task that has been extensively researched, safely solving complex, high-precision assembly in an unstructured environment remains an open problem. Reinforcement-learning (RL) methods have proven to be s...
Patent
【課題】手先の位置に関する制御と力に関する制御とを両立させることを可能とするロボットアームの制御装置、制御方法、及びプログラムを提供する。【解決手段】ロボットの関節を駆動するための関節指令値を一定のサイクルごとに与えてロボットを作動させるプロセッサを有するロボットの制御装置である。プロセッサは、関節の位置、関節の速度、及びロボットの手先にかかる力を含むセンシング情報と、手先の位置及び力との関係を学習した学習済みモデルに基づいて、サイクルごとに手先の位置目標値及び力目標値を生成し、位置目標値とセンシング情報に基づく手先の位置との偏差を表す位置偏差値と、力目標値とセンシング情報に基づく手先にかかる力との偏差を表す力偏差値とのそれぞれに補償変換を施した値の線形和を算出し、かつ線形和を制御偏差値とし...
Preprint
Full-text available
The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount of robot interaction with its environment. Curriculum Learning (CL) has been proposed to expedite learning. However, most research...
Article
High-mix, low-volume assembly has been a long-standing challenge for robot systems. We present a complete 2-armed robot system with general-purpose grippers and hand-held tools, which can perform assembly for a wide variety of objects with tight tolerances. The complete source code and 3D-printed-part designs are available for download and can be e...
Article
Full-text available
Factory automation robot systems often depend on specially-made jigs that precisely position each part, which increases the system's cost and limits flexibility. We propose a method to determine the 3D pose of an object with high precision and confidence, using only parallel robotic grippers and no parts-specific jigs. Our method automatically gene...
Article
Full-text available
Complex contact-rich insertion is a ubiquitous robotic manipulation skill and usually involves nonlinear and low-clearance insertion trajectories as well as varying force requirements. A hybrid trajectory and force learning framework can be utilized to generate high-quality trajectories by imitation learning and find suitable force control policies...
Article
Full-text available
Complex assembly tasks involve nonlinear and low-clearance insertion trajectories with varying contact forces at different stages. For a robot to solve these tasks, it requires a precise and adaptive controller which conventional force control methods can not provide. Imitation learning is a promising method for learning controllers that can solve...
Preprint
Full-text available
Robotic assembly tasks involve complex and low-clearance insertion trajectories with varying contact forces at different stages. While the nominal motion trajectory can be easily obtained from human demonstrations through kinesthetic teaching, teleoperation, simulation, among other methods, the force profile is harder to obtain especially when a re...
Preprint
Full-text available
Featured Application: Assembly tasks with industrial robot manipulators. Abstract: Industrial robot manipulators are playing a more significant role in modern manufacturing industries. Though peg-in-hole assembly is a common industrial task which has been extensively researched, safely solving complex high precision assembly in an unstructured envi...
Preprint
Full-text available
Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges, especially when using rigid position-controlled manipulators. These challenges include the need for a robust con...
Conference Paper
Full-text available
Towards industrial automation with general-purpose robotic systems, it is indispensable to enable robot manipulators the ability to adapt by itself to its surroundings and to learn to handle new manipulation tasks. To this end, in this paper, we propose a robotic assembly framework for learning a Reinforcement Learning (RL) policy to solve manipula...
Chapter
Full-text available
This work deals with a novel intelligent visual assisted picking task approach, for industrial manipulator robot. Intelligent searching object algorithm, around the working area, by RANSAC approach is proposed. After that, the image analysis uses the Sobel operator, to detect the objects configurations; and finally, the motion planning approach by...
Article
Full-text available
This work deals with a novel intelligent visual assisted picking task approach, for industrial manipulator robot. Intelligent searching object algorithm, around the working area, by RANSAC approach is proposed. After that, the image analysis uses the Sobel operator, to detect the objects configurations; and finally, the motion planning approach by...

Network

Cited By

Projects

Projects (2)
Archived project
Diseñar, implementar y probar un sistema de control automático On-line, para la producción lípidos con potencial para Biodiesel a partir de microalgas