Pourya Shahverdi

🧑‍💻️

Pourya Shahverdi

Robotics | AI/ML | Affective Computing | HRI/HCI

About Me

I am a fourth-year Ph.D. candidate in Electrical and Computer Engineering at Oakland University, expected to graduate in April 2025. I also lecture at the School of Engineering and Computer Science and serve as a graduate research assistant under Prof. Geoffrey Louie in the IRL² Intelligent Robotics Laboratory.

I am currently working on shaping the context-aware social robots behaviors leveraging generative AI and Large Language Models. My research focuses on robot learning, affective computing, behavior perception, conversational AI/ML, and human factor design for human-robot interaction (HRI/HCI/HMI). I have over 10 years of experience in robotics and accomplished projects in kinematics/dynamics modeling and control, humanoid imitation, manipulation and visual servoing, mobile robot navigation, and autonomous vehicles. I also served as a mentor for K12 students in RoboCup competitions, and achieved world-class honors.

Outside of work, I enjoy playing basketball, hiking, helping my wife with her bakery, and playing the Piano/Keyboard as well as Tar/Setar (traditional Persian instruments).

Download CV

Interests

Robot Learning
Behavior Perception
Affective Computing
Conversational AI/ML
Social Robotics
Human-Robot Interaction (HRI)
Kinematic & Dynamic Modeling
Controller Design

Education

Ph.D. Candidate in Electrical and Computer Engineering
Oakland University (MI-USA)
M.Sc. Mechatronics Engineering
Azad University of Qazvin (Iran)
B.Sc. Robotics Engineering
Hamedan University of Technology (Iran)

📚 My Mission

“Social Robots for Social Justice” is my slogan.

I strive to uncover the complexities of Social HRI to create reliable and transparent conversational AI models for robots and virtual agents. I believe that true human connection with artificial agents is only possible when they possess a degree of human-like emotional intelligence. My Ph.D. dissertation leverages foundational Large Language Models (LLMs) to develop context-aware affective conversational AIs. Through this work, I aim to enhance naturalness, trust, and empathy, fostering meaningful interactions between users and agents. Ultimately, I hope my efforts advance social justice by making high-quality social services, like healthcare and education, more accessible to underrepresented communities.

Please reach out to collaborate 😃

Featured Projects

Fall Prevention; Exercise; Robotics; Physical Therapy; Social Human-Robot Interaction

Effect of robotic delivery of physical activity and fall prevention exercise in older adults: a pilot cohort study

Abstract: Introduction The high prevalence of falls, lack of stability and balance, and general physical deconditioning are concerning issues for longevity and quality of life for adults aged 65 years and older. Although supervised delivery of the Otago Exercise Program (OEP) has demonstrated evidence of effectiveness in reducing fall risk of older adults, opportunities for ongoing unsupervised exercise performance are warranted. An option to facilitate exercise and performance of health behaviors may be via a social robot. The purpose of this study was to examine feasibility and initial outcomes of a robot-delivered fall prevention exercise program for community-dwelling older adults.

Jan 1, 2023

Social Robots; Affective Computing; Conversational AI; Backchanneling; Behavioral Sciences

Emotionally Specific Backchanneling in Social Human-Robot Interaction and Human-Human Interaction

Abstract: Backchanneling models, designed to enhance the interactive capabilities of robots, have primarily been trained on human-human interaction data. However, applying such data directly to social robots raises concerns due to dissimilarities in the way humans and robots exhibit verbal and nonverbal behaviors, particularly in the domain of emotional backchannels. This research aims to address this gap by conducting an exploratory study on the differences in human backchanneling behaviors during interactions with humans and social robots in various emotional contexts (e.g., happy and sad). Our findings reveal significant variations in emotionally specific backchannels between human-human and human-robot interactions under different emotional contexts. These results highlight the importance of designing backchanneling models that are tailored for human-robot interactions.

Jan 1, 2023

Autism; Social Robots; Behavioral Sciences; Group Instruction

Robot-mediated Group Instruction for Children with ASD: A Pilot Study

Abstract: Children diagnosed with autism spectrum disorder (ASD) typically work towards acquiring skills to participate in a regular classroom setting such as attending and appropriately responding to an instructor’s requests. Social robots have the potential to support children with ASD in learning group-interaction skills. However, the majority of studies that target children with ASD’s interactions with social robots have been limited to one-on-one interactions. Group interaction sessions present unique challenges such as the unpredictable behaviors of the other children participating in the group intervention session and shared attention from the instructor. We present the design of a robot-mediated group interaction intervention for children with ASD to enable them to practice the skills required to participate in a classroom. We also present a study investigating differences in children’s learning behaviors during robot-led and human-led group interventions over multiple intervention sessions. Results of this study suggests that children with ASD’s learning behaviors are similar during human and robot instruction. Furthermore, preliminary results of this study suggest that a novelty effect was not observed when children interacted with the robot over multiple sessions.

Jan 1, 2022

Humanoid Robots; Motion Imitation; Humanoid Dynamic; Balance Control

Balance Strategy for Human Imitation by a NAO Humanoid Robot

Abstract: This paper presents an ankle-based balance strategy for a NAO humanoid robot while imitating the human motions. In this approach, first, an inverted pendulum model based on the computed Center of Mass (CoM) is introduced and then, the support polygon is computed for each double support and single support phases. Center of the support polygon is assumed as the reference for balance controller and Ground projection of the Center of Mass (GCoM) is considered as the balance criteria. Using ankle joints correction, GCoM is restricted to the center of the support polygon. In order to control the balance criteria a Proportional-Integral-Derivative (PID) controller is used. The coefficients are first estimated using Ziegler-Nichols method; then, they were tuned by considering advantages of the imitation process. Implementation of the proposed approach leads to a better result in preserving the balance of the robot in soft realtime imitation of human whole-body and quasi-static motions. The proposed approach is validated by performing simulation and practical tests on a NAO H-25 version 4 robot.

Jan 1, 2017

Recent Publications

Iman Bakhoda, Pourya Shahverdi, Katelyn Rousso, Evan Dallas, Wing-Yue Geoffrey Louie (2025). Robot-mediated Read-aloud Context of Reading Comprehension and Vocabulary Development. Computers & Education-Under Review.

Cite

Pourya Shahverdi, Iman Bakhoda, Katelyn Rousso, Justin Klotz, Wing-Yue Geoffrey Louie (2025). The Dynamics of Story Internalization: A Pathway to Deeper Interaction with Social Robots. 2025 IEEE International Conference on Robotics and Automation (ICRA)-Under Review.

Cite

Wing-Yue Geoffrey Louie, Tanya Christ, Amanda Wowra, Danielle Alexander, Iman Bakhoda, Pourya Shahverdi (2024). “If a Robot was Teaching, Then Everybody Would Definitely Like School Better”: An Analysis of Grade 3-5 Children’s Perceptions of Learning STEM Vocabulary with an Educational Social Robot. 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN).

Cite DOI

Wing-Yue Geoffrey Louie, Tanya Christ, Pourya Shahverdi, Katelyn Rousso, Evan Dallas, Alexander Tyshka, Amanda Wowra, Kendra Barnett, Iman Bakhoda (2024). Exploring Task-Level Contingent Mediations for Vocabulary Instruction across Robot, Virtual, and Human Teachers. 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN).

Cite DOI

Pourya Shahverdi, Iman Bakhoda, Katelyn Rousso, Justin Klotz, Wing-Yue Geoffrey Louie (2024). Exploring the Impact of Narrator Type on Response Latency and Utterance Length During Interactive Storytelling. 2024 IEEE International Conference on Robotics and Automation (ICRA).

Cite DOI

See all publications