Innovations in Science and Technologies Volume 2 Issue 8 (2025) · pp. 95-107

KO‘P-TUZILMALI MUHITDA TOZALOVCHI ROBOT UCHUN DISTRIBUTIONAL REINFORCEMENT LEARNING ASOSIDAGI MARSHRUT REJALASHTIRISH STRATEGIYASI

Maxsudxonov, Amixon

Read at source PDF

Abstract

Ushbu maqola nomaʼlum muhitlarda harakatlanuvchi tozalovchi robot uchun yangi marshrut rejalashtirish strategiyasini taklif etadi. Taklif qilingan yondashuv Lightweight Learned Image Denoising with Instance Adaptation (LIDIA) va Deep Q-Network (DQN) texnologiyalarini yagona ramkaga (framework) integratsiyalash orqali amalga oshiriladi. Ushbu kombinatsiya robotlarga ko‘p obʼyektli hududlarda to‘qnashuvsiz harakatlanish imkonini beradi. Birinchi bosqichda, muhitning chuqurlik tasvirlari robotning o‘rnatilgan kamerasidan olinadi. Bu xom tasvirlar odatda shovqinli bo‘lgani sababli, LIDIA texnologiyasi qo‘llanilib, maʼlumotlar kalibrlanadi va tasvir sifati yaxshilanadi.

Muhitda tozalovchi robotPath – planningDistributional reinforcement learningDQN NetworkSub – reward mechanism

Metadata source: the journal's OAI-PMH archive · Sindex does not store the full text; it links to the source.

Cite

APA 7 
Maxsudxonov, Amixon (2025). KO‘P-TUZILMALI MUHITDA TOZALOVCHI ROBOT UCHUN DISTRIBUTIONAL REINFORCEMENT LEARNING ASOSIDAGI MARSHRUT REJALASHTIRISH STRATEGIYASI. Innovations in Science and Technologies, 2(8), 95-107.
GOST R 7.0.5 
Maxsudxonov, Amixon KO‘P-TUZILMALI MUHITDA TOZALOVCHI ROBOT UCHUN DISTRIBUTIONAL REINFORCEMENT LEARNING ASOSIDAGI MARSHRUT REJALASHTIRISH STRATEGIYASI // Innovations in Science and Technologies. 2025. Т. 2. № 8. С. 95-107.
BibTeX 
@article{amixon2025,
  author  = {Maxsudxonov, Amixon},
  title   = {KO‘P-TUZILMALI MUHITDA TOZALOVCHI ROBOT UCHUN DISTRIBUTIONAL REINFORCEMENT LEARNING ASOSIDAGI MARSHRUT REJALASHTIRISH STRATEGIYASI},
  journal = {Innovations in Science and Technologies},
  year    = {2025},
  volume  = {2},
  number  = {8},
  pages   = {95-107}
}
RIS 
TY  - JOUR
AU  - Maxsudxonov, Amixon
TI  - KO‘P-TUZILMALI MUHITDA TOZALOVCHI ROBOT UCHUN DISTRIBUTIONAL REINFORCEMENT LEARNING ASOSIDAGI MARSHRUT REJALASHTIRISH STRATEGIYASI
JO  - Innovations in Science and Technologies
PY  - 2025
VL  - 2
IS  - 8
SP  - 95
EP  - 107
ER  -