國立虎尾科技大學 |

Contact-Based State Estimation and Policy Learning for Robotic Manipulation Tasks.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Contact-Based State Estimation and Policy Learning for Robotic Manipulation Tasks./
Author:	Li, Shuai.
Description:	1 online resource (181 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.
Contained By:	Dissertation Abstracts International79-02B(E).
Subject:	Robotics. -
Online resource:	click for full text (PQDT)
ISBN:	9780355453904

Contact-Based State Estimation and Policy Learning for Robotic Manipulation Tasks.
Li, Shuai.

Contact-Based State Estimation and Policy Learning for Robotic Manipulation Tasks. - 1 online resource (181 pages)

Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.

Thesis (Ph.D.)--Rensselaer Polytechnic Institute, 2017.

Includes bibliographical references

The robotic manipulation problem is very important in robotic research and appli- cations. In a typical robotic manipulation task, the robot needs to interact with certain objects to accomplish a goal, such as picking up a cup from a table. Without manipulation capabilities, robots will not be able to help humans with their daily tasks such as using tools to fix a broken car. Although the hardware of robots has been significantly improved, the ability to perceive the current state of a robotic manipulation task is still essential for a robot to fully utilize its hardware. However, less effort has been made to address the perception problem for robotic manipulation tasks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355453904Subjects--Topical Terms:

561941
Robotics.
Index Terms--Genre/Form:

554714
Electronic books.

Contact-Based State Estimation and Policy Learning for Robotic Manipulation Tasks.
LDR:03248ntm a2200361Ki 4500 001 916789
005 20180928111501.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355453904
035 $a (MiAaPQ)AAI10601777
035 $a (MiAaPQ)rpi:11106
035 $a AAI10601777
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Li, Shuai. $3 1190626
245 1 0 $a Contact-Based State Estimation and Policy Learning for Robotic Manipulation Tasks.
264 0 $c 2017
300 $a 1 online resource (181 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.
500 $a Adviser: Jeffery C. Trinkle.
502 $a Thesis (Ph.D.)--Rensselaer Polytechnic Institute, 2017.
504 $a Includes bibliographical references
520 $a The robotic manipulation problem is very important in robotic research and appli- cations. In a typical robotic manipulation task, the robot needs to interact with certain objects to accomplish a goal, such as picking up a cup from a table. Without manipulation capabilities, robots will not be able to help humans with their daily tasks such as using tools to fix a broken car. Although the hardware of robots has been significantly improved, the ability to perceive the current state of a robotic manipulation task is still essential for a robot to fully utilize its hardware. However, less effort has been made to address the perception problem for robotic manipulation tasks.
520 $a In this thesis, we focus on improving the perception capability for robots and addressing the problem of combining the perception capability with action planning and execution for robotic manipulation tasks. Our proposed approach combines Bayesian filtering methods with accurate models of multi-body dynamics for state estimation in the robotic manipulation tasks. In order to understand the design trade-offs of particle filter applications for the state estimation problems, we evalu- ate different particle filter modeling options in both simulation and physical exper- iments. We then propose a contact-based RBPF that samples the discrete contact states and updates the continuous state distribution through Kalman filters. Re- sults show that the contact-based RBPF is more effective and more efficient than the state of the art filters that sample the continuous state space. Finally, we apply reinforcement learning algorithms to learn policies for robotic manipulation tasks with a state space discretized using contact states. This discretized space learning is proven to be more effective than learning with continuous state space. We further propose to combine the learned policies with the contact-based RBPF for online action selection during robotic manipulation tasks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Robotics. $3 561941
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0771
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Rensselaer Polytechnic Institute. $b Computer Science. $3 1190468
773 0 $t Dissertation Abstracts International $g 79-02B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10601777 $z click for full text (PQDT)