Photo of Dmytro Humeniuk

Dmytro Humeniuk

PhD student

Contact Me

About Me

PhD candidate in Computer Engineering, specializing in the development of AI-driven robotic systems, with graduation expected in winter 2025-2026. Strong background in programming, numerical methods, and machine learning, including deep learning and reinforcement learning. Expertise in advanced simulation-based testing and validation of robotic systems. Experienced in developing autonomous robotic systems using NVIDIA Isaac Sim and ROS 2, including robotic manipulators with vision-based perception. PhD student at Polytechenique Montreal . I obtained a master's degree from Polytechnique Montreal and a bachelor degree from Kyiv Igor Sikorsky Polytechnic University, Ukraine

Selected Projects

AmbieGen

AmbieGen is a flexible and modular framework for automated scenario-based testing of autonomous robotic systems. It leverages evolutionary search algorithms and machine learning to generate and evolve test scenarios that expose weaknesses and critical failures in the system under test. It is designed to be easily extensible, allowing researchers and practitioners to incorporate their own testing strategies and domain knowledge. It can be easily installed with: pip install ambiegen.

Documentation   Code

Image Description

QA-enhanced development of intelligent robotic manipulators in Isaac Sim

In collaboration with Sycodal, in this project we develop reliable and robust robotic manipulators containing ML components. We propose MARTENS approach (Manipulator Robot Testing and Enhancement in Simulation) implemented in the NVIDIA Isaac Sim simulation environment. The approach was published and presented at ASE 2024 conference.

Paper  

Image Description
Image Description

Representation Improvement in Latent Space for Search-Based Testing of Autonomous Robotic Systems

We propose RILaST (Representation Improvement in Latent Space for Search-Based Testing) approach, which enhances test representation by mapping it to the latent space of a variational autoencoder. We evaluate RILaST on two use cases, including autonomous drone and autonomous lane-keeping assist system. Images below illustrate how the test represented in a latent space changes by changing one of the latent variables.

Paper   Code

Image Description
Image 1 Image 2

Reinforcement Learning Informed Evolutionary Search for Autonomous Systems Testing

Co-authors: Prof. Khomh, Prof. Antoniol

In this project we use Reinforcement learning to initialize some part of a genetic algorithm to improve the initial population and increase the efficiency of the search for useful test scenes. We condunct experiments on the RL-controlled robotic ant as well as on an autonomous vehicle lane-keeping assist system.

Paper   Code

Image Description
Image Description   Image Description  

A framework for generating test scenes for autonomous cyber-physical systems with evolutionary search algorithms

Co-authors: Prof. Khomh, Prof. Antoniol

I this project we develop a tool for generating test-scenes for autonomous cyber-physical systems using evolutionary algorithms. Our tool starts with a population of randomly generated test scenes and evolves them, promoting the test scenes that reveal failures of the system under test. Refer to the approach paper for a more detailed description of the algorithm and to the tool paper for the description of the tool software.

  Approach Paper     Tool Paper   Code

Image Description  

Participation in the SBST Cyber-Physical Systems Testing Tool Competition

Co-authors: Prof. Khomh, Prof. Antoniol

This is a tool competition, where competitors should propose a test generator that produces virtual roads to test a vehicle lane keeping assist system. The aim of the generation is to produce diverse failure-inducing tests, i.e., roads that make the lane keeping assist system drive out of the lane. The ranking of the tools is based on coverage which measures the number of failed tests and their diversity. In 2022, our tool AmbieGen has won the competion.

Our submissions: 2021 ( ),  2022 (1st place ),  2023 (2nd place ) 2024 (2nd place ) 2024 (UAV testing )

Image Description   Image Description  

Selected publications

Representation Improvement in Latent Space for Search-Based Testing of Autonomous Robotic Systems

Humeniuk, Dmytro, Foutse Khomh. "Representation Improvement in Latent Space for Search-Based Testing of Autonomous Robotic Systems." Submitted to ACM Trans. Softw. Eng. Methodol.

In-Simulation Testing of Deep Learning Vision Models in Autonomous Robotic Manipulators

Dmytro Humeniuk, Houssem Ben Braiek, Thomas Reid, and Foutse Khomh. 2024. In-Simulation Testing of Deep Learning Vision Models in Autonomous Robotic Manipulators. In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE '24). Association for Computing Machinery, New York, NY, USA, 2187–2198. https://doi.org/10.1145/3691620.3695281.

Reinforcement Learning Informed Evolutionary Search for Autonomous Systems Testing

Humeniuk, Dmytro, Foutse Khomh, and Giuliano Antoniol. "Reinforcement learning informed evolutionary search for autonomous systems testing." ACM Trans. Softw. Eng. Methodol. 33, 8, Article 216 (November 2024), 45 pages. https://doi.org/10.1145/3680468.

AmbieGen: A search-based framework for autonomous systems testing

Dmytro Humeniuk, Foutse Khomh, Giuliano Antoniol, AmbieGen: A search-based framework for autonomous systems testing, Science of Computer Programming, Volume 230, 2023, 102990, ISSN 0167-6423, https://doi.org/10.1016/j.scico.2023.102990.

A search-based framework for automatic generation of testing environments for cyber-physical systems

Humeniuk, Dmytro, Foutse Khomh, and Giuliano Antoniol. "A search-based framework for automatic generation of testing environments for cyber–physical systems." Information and Software Technology 149 (2022): 106936.