Amin Arami

The development of humanoid robots, particularly in enhancing human-robot interaction, is a rapidly advancing field. This paper explores the simulation of the Thormang humanoid robot and the development of advanced grasping models using machine learning techniques. Our research delves into the intricacies of kinematics, dynamics, and computer vision, paving the way for more intuitive and effective humanrobot interactions. Using and comparing different 6D pose models such as CASAPose, we continue to perform the provided tasks in object manipulation.

Armin Baratian Sarabi, Amin Arami, Amirmohammad Zarif Shahsavan Nejad, Amirmahdi Zarif, Soroush Sadeghnejad Verified by AVIS CertificateFIRA World Summit 2026Submitted 17 Sept 2026

This study delivers a comprehensive and specialized evaluation of the Proportional-Integral-Derivative (PID), Pure Pursuit, and Stanley controllers for path-tracking in autonomous vehicles, conducted within the AVIS (Autonomous Vehicle Intelligent Software) Engine. Utilizing an advanced analytical geometric vision algorithm enhanced with sliding window techniques, the analysis rigorously assesses controller performance across varied driving scenarios. Key metrics, including Mean Squared Error (MSE), Cross-Track Error (CTE), Steering Over Time, Normalized Lateral Deviation, and Angular Error Over Time, are derived from 1000 simulation runs at 100 Hz. The study provides an in-depth exploration of each controller’s operational principles, parameter optimization, and dynamic response, incorporating insights from the AVIS Engine’s physics layer and vehicle dynamics model. These findings offer critical guidance for designing robust autonomous navigation systems tailored to diverse operational contexts.

Armin Baratian Sarabi, Amin Arami, Amirmohammad Zarif Shahsavan Nejad, Amirmahdi Zarif Shahsavan Nejad, Soroush Sadeghnejad Verified by AVIS CertificateFIRA World Summit 2025Submitted 23 Jul 2025

The development of humanoid robots, particularly in enhancing human-robot interaction, is a rapidly advancing field. This paper explores the simulation of the Thormang humanoid robot and the development of advanced grasping models using machine learning techniques. Our research delves into the intricacies of kinematics, dynamics, and computer vision, paving the way for more intuitive and effective human-robot interactions. Using and comparing different 6D pose models such as CASAPose, we continue to perform the provided tasks in object manipulation.

Armin Baratian Sarabi, Amin Arami, Amirmohammad Zarif Shahsavan Nejad, Amirmahdi Zarif Shahsavan Nejad, Soroush Sadeghnejad Verified by AVIS CertificateFIRA World Summit 2024Submitted 16 Jun 2024