Amir Mehdi Soufi Enayati

Amir Mehdi Soufi Enayati

Auto-generated profile, based on publicly available information

Amir Mehdi Soufi Enayati

Faculty of Engineering and Computer Science, University of Victoria, Victoria, BC, Canada

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 July 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ZZZengjie Zhang
Zengjie Zhang
RDRam Dershan
Ram Dershan
AEAmir M. Soufi Enayati
Amir M. Soufi Enayati
MYMarjan Yaghoubi
Marjan Yaghoubi
DRDean Richert
Dean Richert
Homayoun NajjaranHomayoun Najjaran
Homayoun Najjaran
Simulation provides an efficient and safe evaluation solution for industrial automation to pretest software before deploying it in real systems. However, only high-fidelity simulation environments that precisely reconstruct the behavioral patterns of real systems can guarantee a successful transfer from simulation to reality (sim-to-real). Many existing industrial simulation tools provide libraries for various industrial devices, which simplify the development efforts significantly, but they generally lack the ability to model the system dynamics and often fail to generate a realistic representation when the system performance is sensitive to the modeling deviation. For example, robots equipped with intelligent algorithms potentially lead to task failure if the software is sensitive to the variation of the system dynamics. In this paper, we design a novel simulation platform for industrial manufacturing use cases consisting of a cooperative robot and a modular manufacturing device. With the dynamic model of the robot integrated into a manufacturing digital-twining software, the platform achieves high simulation fidelity by incorporating the effect of the robot dynamics to the control logic of the industrial tasks. Also, the simulation can exchange data with the real robot via an open protocol, which enables the simultaneous test of the real and simulated systems. Two experiments are conducted on the simulation platform to validate its fidelity in terms of the consistent control logic with the real system. Also, a workpiece distribution use case is studied to show how the simulation platform is used to develop a task-planning algorithm for a manufacturing application.

26 September 2024 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
ZZZengjie Zhang
Zengjie Zhang
JHJayden Hong
Jayden Hong
AEAmir M. Soufi Enayati
Amir M. Soufi Enayati
Homayoun NajjaranHomayoun Najjaran
Homayoun Najjaran
Reinforcement learning (RL) for motion planning of multi-degree-of-freedom robots still suffers from low efficiency in terms of slow training speed and poor generalizability. In this paper, we propose a novel RL-based robot motion planning framework that uses implicit behavior cloning (IBC) and dynamic movement primitive (DMP) to improve the training speed and generalizability of an off-policy RL agent. IBC utilizes human demonstration data to leverage the training speed of RL, and DMP serves as a heuristic model that transfers motion planning into a simpler planning space. To support this, we also create a human demonstration dataset using a pick-and-place experiment that can be used for similar studies. Comparison studies reveal the advantage of the proposed method over the conventional RL agents with faster training speed and higher scores. A real-robot experiment indicates the applicability of the proposed method to a simple assembly task. Our work provides a novel perspective on using motion primitives and human demonstration to leverage the performance of RL for robot applications.

27 July 2023 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
AEAmir M. Soufi Enayati
Amir M. Soufi Enayati
RDRam Dershan
Ram Dershan
ZZZengjie Zhang
Zengjie Zhang
DRDean Richert
Dean Richert
Homayoun NajjaranHomayoun Najjaran
Homayoun Najjaran
Simulation is essential to reinforcement learning (RL) before implementation in the real world, especially for safety-critical applications like robot manipulation. Conventionally, RL agents are sensitive to the discrepancies between the simulation and the real world, known as the sim-to-real gap. The application of domain randomization, a technique used to fill this gap, is limited to the imposition of heuristic-randomized models. We investigate the properties of intrinsic stochasticity of real-time simulation (RT-IS) of off-the-shelf simulation software and its potential to improve RL performance. This improvement includes a higher tolerance to noise and model imprecision and superiority to conventional domain randomization in terms of ease of use and automation. Firstly, we conduct analytical studies to measure the correlation of RT-IS with the utilization of computer hardware and validate its comparability with the natural stochasticity of a physical robot. Then, we exploit the RT-IS feature in the training of an RL agent. The simulation and physical experiment results verify the feasibility and applicability of RT-IS to robust agent training for robot manipulation tasks. The RT-IS-powered RL agent outperforms conventional agents on robots with modeling uncertainties. RT-IS requires less heuristic randomization, is not task-dependent, and achieves better generalizability than the conventional domain-randomization-powered agents. Our findings provide a new perspective on the sim-to-real problem in practical applications like robot manipulation tasks.

15 May 2026 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Open access
IJIman Jalilvand
Iman Jalilvand
AEAmir Mehdi Soufi Enayati
Amir Mehdi Soufi Enayati
HHHadi Hosseinionari
Hadi Hosseinionari
RSRudolf Seethaler
Rudolf Seethaler
ANApurva Narayan
Apurva Narayan
Abbas Sadeghzadeh MilaniAbbas Sadeghzadeh Milani
Abbas Sadeghzadeh Milani