Motion planning of a quadrotor robot game using a simulation-based projected policy iteration method

2019 ◽  
Vol 20 (4) ◽  
pp. 525-537
Author(s):  
Li-dong Zhang ◽  
Ban Wang ◽  
Zhi-xiang Liu ◽  
You-min Zhang ◽  
Jian-liang Ai
1992 ◽  
Vol 14 (9) ◽  
pp. 952-958 ◽  
Author(s):  
A.C.M. Dumay ◽  
M.N.A.J. Claessens ◽  
C. Roos ◽  
J.J. Gerbrands ◽  
J.H.C. Reiber

2015 ◽  
Vol 27 (3) ◽  
pp. 579-595 ◽  
Author(s):  
Antoine Sauré ◽  
Jonathan Patrick ◽  
Martin L. Puterman

2017 ◽  
Vol 107 (10) ◽  
pp. 767-772
Author(s):  
S. Fur ◽  
C. Scheifele ◽  
A. Pott ◽  
A. Prof. Verl

Beim „Griff in die Kiste“ kommen Robotersysteme mit intelligenten Algorithmen für die Objekterkennung, Bewegungsplanung und Bewegungssteuerung zum Einsatz. Auf dem Markt gibt es derzeit verschiedene Softwaretools, die sich mit der Steuerung solcher Systeme beschäftigen. Um die steigende Komplexität zu beherrschen und die Auslegung der Systeme zu optimieren, wird ein simulationsgestütztes Werkzeug zur simulationsbasierten Inbetriebnahme benötigt. Dieser Beitrag stellt ein Konzept für eine umfassende virtuelle Absicherung des industriellen „Griffs in die Kiste“ vor.   Robotic systems with intelligent algorithms for object detection, motion planning and motion control are used in bin picking. Various software tools which deal with the control of such systems, are available on the market. To manage the increasing complexity and to optimize the design of the systems, a simulation-based tool is required for simulation-based commissioning. This paper presents a concept for a comprehensive virtual security solution for industrial bin picking.


Author(s):  
Sergei Savin

In this chapter, the problem of motion planning for an in-pipe walking robot is studied. One of the key parts of motion planning for a walking robot is a step sequence generation. In the case of in-pipe walking robots it requires choosing a series of feasible contact locations for each of the robot's legs, avoiding regions on the inner surface of the pipe where the robot cannot step to, such as pipe branches. The chapter provides an approach to localization of pipe branches, based on deep convolutional neural networks. This allows including the information about the branches into the so-called height map of the pipeline and plan the step sequences accordingly. The chapter shows that it is possible to achieve prediction accuracy better than 0.5 mm for a network trained on a simulation-based dataset.


2015 ◽  
Vol 3 (1) ◽  
pp. 460-483 ◽  
Author(s):  
Denis Belomestny ◽  
Marcel Ladkau ◽  
John Schoenmakers

2019 ◽  
Vol 31 (1) ◽  
pp. 70-77
Author(s):  
Xiaowei Dong ◽  
Omar Mendoza-Trejo ◽  
Daniel Ortiz Morales ◽  
Ola Lindroos ◽  
Pedro La Hera

Sign in / Sign up

Export Citation Format

Share Document