Minahil Raza

I am a Doctoral Researcher in the Aalto Robot Learning Group at Aalto University, advised by Prof. Joni Pajarinen. My research focuses on enabling robots to operate robustly in partially observable, dynamic, and unstructured environments. I investigate methods that enable robots to adapt to uncertainty, reason about incomplete information, and interact effectively with complex real-world environments.

Previously, I completed an Erasmus Mundus Joint Master's in Engineering of Data-intensive Intelligent Software Systems (EDISS) at Åbo Akademi University and the University of the Balearic Islands, worked on autonomous load handling for heavy machines at Hiab, and was a research fellow at Nokia Bell Labs.

Email Google Scholar GitHub LinkedIn X
Minahil Raza

News

  • [Aug 2026] I participated in the Berkeley Method of Entrepreneurship (BMoE) bootcamp at UC Berkeley's Sutardja Center for Entrepreneurship and Technology: a week-long hands-on intensive workshop about startup fundamentals. I learnt so much from the fantastic team of mentors and collaborators.
  • [Jul 2026] Our paper "Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection" was accepted to IROS 2026. Preprint available on arXiv, project page here.
  • [May 2026] I attended the Unite! Research School 2026 in Oropa and Turin, Italy, on a Unite! grant, joining researchers and industry representatives across digital transition, energy, and enabling technologies.
  • [Jan 2026] I arranged and presented a "Spot the Robot Dog" demo at Shaking up Tech, Aalto's yearly event introducing women and gender minorities to university studies, letting visitors control our robot dog Spot via an Xbox controller or hand tracking.
  • [Sep 2025] I attended the PAISS summer school at Inria in Grenoble on a fully-funded scholarship, meeting leading researchers in AI and machine learning from Naver Labs and Meta.
  • [Aug 2025] I attended the IWIALS workshop at TU Darmstadt, spanning RL, VLAs, locomotion and manipulation.
  • [May 2025] I started my PhD at Aalto University in the Aalto Robot Learning Group, advised by Prof. Joni Pajarinen, focusing on robot manipulation and autonomous excavation.
  • [Jul 2024] I attended the Cornell, Maryland, Max Planck Pre-doctoral Research School (CMMRS 2024) at MPI-SWS on a fully-funded scholarship.
  • [Apr 2024] I was awarded the Extraordinary Master's Award for the best academic record in my degree at the University of the Balearic Islands.
  • [Oct 2023] I successfully defended my thesis, "Whole-body Manipulation using Reinforcement Learning," available here.
  • [Oct 2023] Our paper "Environmental stiffness restores mechanical homeostasis in vimentin-depleted cells" was published in Scientific Reports.
  • [Jan 2023] Our paper SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations was accepted to ICRA 2023.

Publications

Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection

Hadrien Crassous*, Mohamed Yassine Kabouri*, Minahil Raza*, Joni Pajarinen, Riad Akrour

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026

project page arxiv code

SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations

Khaled Nakhleh*, Minahil Raza*, Mack Tang*, Matthew Andrews, Rinu Boney, Ilija Hadžić, Jeongran Lee, Atefeh Mohajeri, Karina Palyutina

IEEE International Conference on Robotics and Automation (ICRA), 2023

paper

Environmental stiffness restores mechanical homeostasis in vimentin-depleted cells

Janine Grolleman, Nicole C.A. van Engeland, Minahil Raza, Sepinoud Azimi, Vito Conte, Cecilia M. Sahlgren, Carlijn V.C. Bouten

Scientific Reports, 2023

paper code

Towards Integrated Digital-twins: An Application Framework for Autonomous Maritime Surface Vessel Development

Minahil Raza*, Hanna Prokopova*, Samir Huseynzade, Sepinoud Azimi, Sebastien Lafond

MDPI Journal of Marine Science and Engineering, 2022

paper

SimuShips — A High Resolution Simulation Dataset for Ship Detection with Precise Annotations

Minahil Raza*, Hanna Prokopova*, Samir Huseynzade, Sepinoud Azimi, Sebastien Lafond

IEEE OCEANS 2022 Hampton Roads

dataset code

QuantYOLO: A High-Throughput and Power-Efficient Object Detection Network

Muhammad Gohar Javed*, Minahil Raza*, Muhammad Mohsin Ghaffar, Christ Weis, Norbert Wehn, Muhammad Shahzad, Faisal Shafait

Digital Image Computing: Techniques and Applications (DICTA), 2021

paper

Patents

Load Handling Controller, Method and Computer Program Product

Hiab AB — EP4596321A1, filed Dec 2024, published Aug 2025

patent

Load Handling System, Method and Computer Program Product

Hiab AB — EP4597249A1, filed Dec 2024, published Aug 2025

patent

Education

Experience

Awards

Talks & Presentations

Spot the robot dog demo at Shaking up Tech "Spot the Robot Dog" demo — Shaking up Tech, Aalto University (January 2026)