Distributed System for Objects Localization in the Working Area of a Modular Reconfigurable Mobile Robot
Maria A. Volkova, Alexey M. Romanov, Mikhail P. Romanov
- Year
- 2021
- Citations
- 2
Abstract
The paper proposes a novel approach to the objects localization in the working area of a modular reconfigurable robot (MRR), w h ic h im plies the in stal la ti on of stat ionary mon itoring po int s (SMP), co n sisting of detachab le robot’s m o dule s and in- stalle d b y robot itself . Th is a ppro a c h is b a se d o n t h e a rc h itect u re of t h e MRR co n trol s y ste m pre v io u sl y propose d b y t h e au t h ors and a new method for comparing information about the speed and position obtained from various sensors. The key steps of the approach are following. Upon arriving in the target area, the MRR places SMPs, which consist of a power source, a computing de vice , a wireless transceiver and a sensor, detached from the robot. Then SMPs monitor the working area using different types of se n sors ( c am er a s , r an gefi nd ers , etc .), perfor m seg m e n t a tio n of t h e m e a s u re d da t a and tr an sfer t h is i n fo rma tio n to t h e robot . F u rther a sensor fusion is performed using a novel object tracking method, which makes it possible to localize target objects even in tho se ca ses whe n they are not vi sible b y so me of the SMP s . One of the key advanta ges of the ne w appro ach is a possibility of i m ple m e n t a tio n i n t h e d istrib u te d a rc h itect u re of a MRR. The simulation results show that proposed method has Multiple Object T r a c k i n g Acc u r a c y (MOT A ) m etric of 86 %, which is higher than the most of its analogues, while the estimated dynamic object lo ca li za tion error in a 8x7 m working area using 2 cameras and 1 rangefinder does not exceed 10 cm.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002