AI-Enabled Adaptive Robots for Aerospace Industry 4.0

Period: Mar 2021 – Sep 2023
Role: Project Leader (Postdoctoral Researcher)
Principal Investigator: Prof. Homayoun Najjaran
Affiliation: University of British Columbia (UBC)
Funding: NSERC, CRIAQ, German Aeronautical Research Program (LuFo-8)
Consortium: UBC, UVic, Kinova, German Aerospace Center (DLR), Fraunhofer Society, ZAL, Brötje Automation
Website: https://www.criaq.aero/en/projects/

Overview

AIARA explores how artificial intelligence can enable highly adaptive robotic systems for advanced manufacturing and aerospace applications.

Traditional industrial robots rely on task-specific programming in highly structured environments, limiting their flexibility when tasks or environmental conditions change. AIARA investigates a new paradigm in which robots learn adaptive manipulation strategies and autonomously adjust their behavior in response to uncertainty and environmental variability.

The project aims to develop both algorithmic methods and experimental platforms for adaptive robotic manipulation in dynamic industrial settings.

Technical Focus

The project studies how modern AI techniques can enhance robotic adaptability, including:

• Learning-based robotic manipulation: Applying reinforcement learning and other machine learning techniques to robotic control.

• Adaptive models for variable environments: Enabling robots to generalize across changing tasks and environmental conditions.

• Transfer and meta-learning for robotics: Improving the ability of robots to reuse knowledge across different tasks.

• Integrated software and hardware testbeds: Developing experimental platforms to evaluate adaptive robotic systems.

My Contribution

As a project leader and postdoctoral researcher, I led the research activities on AI-driven adaptive robotic systems, focusing on learning-based approaches for robotic manipulation.

My contributions included:

• Leading the research direction on adaptive robotic learning methods

• Developing learning-based approaches for robotic manipulation under variable environments

• Designing experimental test platforms for evaluating adaptive robotic behaviors

• Coordinating research activities with academic and industrial partners across Canada and Germany

Applications and Impact

The project targets flexible automation in aerospace manufacturing, where robotic systems must operate in environments that are dynamic, partially structured, and frequently reconfigured for new production tasks.

By integrating machine learning with robotic experimentation platforms, AIARA explores how traditional industrial robots can evolve into learning-enabled adaptive systems capable of handling variability in tasks and environments.

The project contributes toward the development of next-generation intelligent automation systems for Industry 4.0, supporting more flexible and resilient manufacturing processes in aerospace and advanced industries.

Publications

• Z. Zhang, J. Hong, A. M. S. Enayati, H. Najjaran*, "Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning". (Submitted) [arXiv]

• A. M. S. Enayati, Z. Zhang, K. Gupta, and H. Najjaran*, "Exploiting Symmetry and Heuristic Demonstrations in Off-policy Reinforcement Learning for Robotic Manipulation". (Submitted) [arXiv]

• J. Hong, Z. Zhang, A. M. S. Enayati, and H. Najjaran*, "Human-Robot Skill Transfer with Enhanced Compliance via Dynamic Movement Primitives". (Submitted) [arXiv]

• R. Dershan, A. M. S. Enayati, Z. Zhang, D. Richert, and H. Najjaran*, "Facilitating Sim-to-real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulation", in IEEE Transactions on Artificial Intelligence, Early Access, doi: 10.1109/TAI.2023.3299252. [IEEEXplore][arXiv]

• A. M. Soufi Enayati, Z. Zhang, and H. Najjaran*,  "A methodical interpretation of adaptive robotics: Study and reformulation", in Neurocomputing, Vol. 512, no. 2022, pp. 381-397, 2022,  doi: 10.1016/j.neucom.2022.09.114. [ScienceDirect][ResearchGate]

• Z. Zhang, D. Wollherr, and H. Najjaran*,  "Disturbance estimation for robotic systems using continuous integral sliding mode observer", in International Journal of Robust and Nonlinear Control, Vol. 32, no. 14, pp. 7946-7966, Sept. 2022, doi: 10.1002/rnc.6252. [Wiley]

• Z. Zhang, R. Dershan, A. M. S. Enayati, M. Yaghoubi, D. Richert, and H. Najjaran*, "A High-Fidelity Simulation Platform For Industrial Manufacturing by Incorporating Robotic Dynamics Into an Industrial Simulation Tool", in IEEE Robotics and Automation Letters, Vol. 7, no. 4, pp. 9123-9128, 2022, doi: 10.1109/LRA.2022.3190096. [IEEEXplore]