MeWBots: Mecanum-Wheeled Robots for Collaborative Manipulation in an Obstacle-Clustered Environment Without Communication

2021 ◽  
Vol 102 (1) ◽  
Author(s):  
Aditya Rauniyar ◽  
Hem Chandra Upreti ◽  
Aman Mishra ◽  
Prabhu Sethuramalingam
Keyword(s):  
2021 ◽  
Vol 11 (1) ◽  
pp. 11
Author(s):  
Sokratis Tselegkaridis ◽  
Theodosios Sapounidis

Educational robotics (ER) seems to have a positive effect on students and, in many cases, might help them to successfully assimilate knowledge and skills. Thus, this paper focuses on ER and carries out a literature review on educational robotics simulators with Graphical User Interfaces (GUIs). The review searches for relevant papers which were published in the period 2013–2020 and extracted the characteristics of the simulators used. The simulators that we describe in this article cover various robotic technologies, offering students an easy way to engage with virtual robots and robotics mechanisms, such as wheeled robots or drones. Using these simulators, students might cover their educational needs or prepare themselves for educational robotic competitions by working in as realistic as possible conditions without hardware restrictions. In many cases, simulators might reduce the required cost to obtain a robotic system and increase availability. Focusing on educational robotics simulators, this paper presents seventeen simulators emphasizing key features such as: user’s age, robot’s type and programming language, development platform, capabilities, and scope of the simulator.


1997 ◽  
Vol 30 (20) ◽  
pp. 17-24 ◽  
Author(s):  
T. Hamel ◽  
P. Souères ◽  
D. Meizel

Author(s):  
Qingyuan Zheng ◽  
Duo Wang ◽  
Zhang Chen ◽  
Yiyong Sun ◽  
Bin Liang

Single-track two-wheeled robots have become an important research topic in recent years, owing to their simple structure, energy savings and ability to run on narrow roads. However, the ramp jump remains a challenging task. In this study, we propose to realize a single-track two-wheeled robot ramp jump. We present a control method that employs continuous action reinforcement learning techniques for single-track two-wheeled robot control. We design a novel reward function for reinforcement learning, optimize the dimensions of the action space, and enable training under the deep deterministic policy gradient algorithm. Finally, we validate the control method through simulation experiments and successfully realize the single-track two-wheeled robot ramp jump task. Simulation results validate that the control method is effective and has several advantages over high-dimension action space control, reinforcement learning control of sparse reward function and discrete action reinforcement learning control.


2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Jun Dai ◽  
Naohiko Hanajima ◽  
Toshiharu Kazama ◽  
Akihiko Takashima

The improved path-generating regulator (PGR) is proposed to path track the circle/arc passage for two-wheeled robots. The PGR, which is a control method for robots so as to orient its heading toward the tangential direction of one of the curves belonging to the family of path functions, is applied to navigation problem originally. Driving environments for robots are usually roads, streets, paths, passages, and ridges. These tracks can be seen as they consist of straight lines and arcs. In the case of small interval, arc can be regarded as straight line approximately; therefore we extended the PGR to drive the robot move along circle/arc passage based on the theory that PGR to track the straight passage. In addition, the adjustable look-ahead method is proposed to improve the robot trajectory convergence property to the target circle/arc. The effectiveness is proved through MATLAB simulations on both the comparisons with the PGR and the improved PGR with adjustable look-ahead method. The results of numerical simulations show that the adjustable look-ahead method has better convergence property and stronger capacity of resisting disturbance.


Author(s):  
Alexey S. Matveev ◽  
Andrey V. Savkin ◽  
Michael Hoy ◽  
Chao Wang

2017 ◽  
Vol 3 (4) ◽  
pp. 227 ◽  
Author(s):  
Yekkehfallah Majid ◽  
Yuanli Cai ◽  
Guao Yang ◽  
Naebi Ahmad ◽  
Zolghadr Javad

Sign in / Sign up

Export Citation Format

Share Document