0% Complete
صفحه اصلی
/
سی و یکمین کنفرانس بین المللی مهندسی برق
Semi-supervised Deep Reinforcement Learning in Decentralized Multi-Agent Collision Avoidance and Path Planning in a Complex Environment
نویسندگان :
Marzie Parooei
1
Mehdi Tale Masouleh
2
Ahmad Kalhor
3
1- دانشگاه تهران
2- دانشگاه تهران
3- دانشگاه تهران
کلمات کلیدی :
Decentralized،Multi Agent،Collision Avoidance،Deep Reinforcement Learning
چکیده :
The problem of path planning and collision avoidance in complex and natural environments is one of the basic requirements of the robotic world, enabling robots to enter social environments. This paper aims to provide a decentralized path planning and collision avoidance method in multi-agent environments. In this method, each agent is a decision-making unit that decides independently from other agents and based on what is in its field of view. In the present paper, classical methods have been used to generate data for training purposes. Models were trained offline by imitating classical methods then semi-supervised methods were used for feature extraction. The results obtained from this method were compared with the Optimal Reciprocal Collision Avoidance (ORCA) method in three environments with different densities and three different indices. The proposed method performed relatively optimally and successfully increased the interaction index while decreasing the computation time. On the other hand, due to the scalable potential of this method, the number of agents could be increased without affecting the computation time.
لیست مقالات
لیست مقالات بایگانی شده
اصلاح مسیرخروجی ID FANتا دودکش اشکودا و امکان سنجی بازیابی حرارتی دود
یاشار مغمومی - فرشته صادقی
Innovative Pathway Optimization for Autonomous Drones in Urban Landscapes Using Integrated Techniques
Seyed Ahmad Abtahi - M.A. Amiri Atashgah - Bahram Tarvirdizadeh - Mohammad Habashiniak
A New High Step-Up Quasi Z-Source DC-DC Converter Using Buffer and Switched Capacitor Techniques
Erfan Meshkizadeh - Ebrahim Afjei - Morteza Kheradmandi
Dynamic Gait Analysis Using Hybrid Neural Networks: Online classification and Prediction of Locomotion Modes
Samira Dehghanian - Hamed Jalaly Bidgoly
مبدل DC/DC افزاینده شبهرزونانسی مبتنی بر ضربکنندهی ولتاژ ترکیبی با کلیدزنی نرم و بهرهی ولتاژ بالا
کوشا چوبداری عمران - رضا بیرانوند
Design and Modeling of Graphene Based Electro-absorption Modulator Integrated with Hybrid Plasmonic Waveguides
Hadi Soofi - Shima Karkon Bagheri - Hamid Vahed
Location of Distributed Generation in the Distribution Network concerning of Capacity Credit with the TLBO Optimization Algorithm
Mohammadali Arash - Mohammad Khakroei
Novel continuous phase DDS model for linear Chirp Signal Simulation in Pulse Compression Radar
Shahin Khakisedigh - Artin Khosravian - Mobin Jamali
Power Transformer Vibration Study and its Application in Winding Deformation Detection
Amir Esmaeili Nezhad - Mohammad Hamed Samimi
Optimal Placement of Of Maintenance Teams in Distribution Networks to Minimize Energy Not Supplied
Qasem Asadi - Ali Ashoornezhad - Hamid Falaghi - Maryam Ramezani
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2