Virtual reality environment for trajectory generation and optimization. Application for trajectory tracking of Automated Guided Vehicles (AGV) evolving in uncertain environment
Supervisor Name : Mitrouchev Peter Doctoral School : I-MEP2 Start Date : 01.10.2015
Financing - Context - Partnerships :
Positioning and Challenges :
More of the existing platforms for path (trajectory) simulation, like RobotWorks, are generally designed for industrial robots working in fixed (stationer) position. Recently Automated Guided Vehicles AGV (systems) have been proven as good candidates to perform storages operations with a lighter, more economical, possibly safer performance and a much better payload-to-weight ratio. However, their orientation workspace is relatively limited which limits their applications for some special (particular) purposes in particular for industrial applications with predefined and imposed trajectory motion. Thus, it is necessary to propose a novel tracking kinematic system for AGV, in which a larger orientation workspace can be implemented thus allowing trajectory simulations and motion control for vehicle evolving in dynamic and uncertain environment. In the last decade, virtual reality (VR) technology, in interaction with the real world (Augmented reality), has evolved to a new level of sophistication. Now it combines several human–computer interfaces (HCI) to provide various sensations such as: visual, auditory, haptic, which enables users to become immersed in a computer generated platform. Visual data from Head Mounted Display (HMD) tracking system represents a useful tool to address human gestures recognition and particularly for characterizing the user view during motion simulation. Adding such a technique in HCI to improve platform of immersion in VR represents a scientific challenge for research today.
Description of the subject:
Today and in the near future (factory of the future) the use of Automated Guided Vehicles (AGV) raised natural problems for fast programming of their path (trajectory) and their optimization as well. In technological conditions, where learning would be desired, but technically difficult even impossible, there exists a need to use means of virtual reality environment. The programming of AGV path should be performed fast and safety, while industrial conditions require so. Thus, there is a challenge to start create such virtual vehicle programming and its associated simulation system. Existing software such as: RobCad, RobotMaster, RobotWorks,... bring quite little freedom for path generation, especially in velocity and acceleration of the AGV. Technological operations for delivery and handling, for instance, are famous for specific requirement to AGV mobility path and speed of movement. Thus, there are needs: to track the movement of AGV in order to achieve proper trajectory quality; to model its path and check collision detection while it is evolving in dynamical and uncertain environment.
In this context, the main objectives of the proposed PhD research subject are:
To find faster and optimal way for performing AGV motion trajectory simulation. For this purpose a methodology and test implementation of means of virtual reality will be proposed;
To create simulation procedure for AGV trajectory generation. For this purpose a virtual reality environment for learning with high accuracy of movement will be realized;
To find out possibility to implement such environment (software and hardware), and to know whether is feasible for industrial use and especially in the particular case of Small and Medium-Sized Enterprises (SMEs);
To build cheap and easy system, giving ability to medium skilled personnel from SMEs to learn AGV motion themselves and create its control;
To evaluate the possibility of implementing such a system in order to increase speed in path programming (by avoiding obstacles), and consequently improving the performances and the economic competitiveness of the enterprises.
Peter MITROUCHEV, Dr. MCF. HDR G-SCOP, Sciences for design, optimization and production, UMR 5272, CNRS, 46, av. Félix Viallet, 38031, GRENOBLE Cedex 1, FRANCE Office C-306, Gate C, 3-rd floor phone : + 33 (0)4 76 57 47 00 fax : + 33 (0)4 76 57 46 95 , E-mail : Peter.Mitrouchev@g-scop.inpg.fr www.g-scop.inpg.fr/~mitroucp/en/ URL: http://www.g-scop.inpg.fr/