Hamidreza Kasaei

hamidreza.kasaei@rug.nl

I am an Assistant Professor in the Department of Artificial Intelligence at the University of Groningen, the Netherlands. I have extensive background in computer vision, machine learning and robotics. My main research interests lie in the area of 3D Object Perception and Object Manipulation. These days, I am particularly interested in enabling robots to incrementally learn from past experiences and intelligently and safely interact with non-expert human users using data-efficient open-ended machine-learning techniques. Therefore, my research group focuses on Lifelong Interactive Robot Learning (IRL-Lab), which we work at the cutting edge of robotics research.

/ IRL-Lab / Publications / Google Scholar / ResearchGate / LinkedIn / Github / YouTube /

Latest News

Jan. 2024: Four papers accepted at ICRA'24, one of the premier conferences in robotics. A big thank you to my students and collaborators!
1- Lifelong Robot Library Learning: Bootstrapping Composable and Generalizable Skills for Embodied Control with Language Models
2- Harnessing the Synergy between Pushing, Grasping, and Throwing to Enhance Object Manipulation in Cluttered Scenarios
3- Self-supervised Learning for Joint Pushing and Grasping Policies in Highly Cluttered Environments
4- TiV-ODE: A Neural ODE-based Approach for Controllable Video Generation From Text-Image Pairs Dec. 2023: Our paper titled Lifelong ensemble learning based on multiple representations for few-shot object recognition got accepted to Robotics and Autonomous Systems Journal! - [open-access]!
Set. 2023: Our paper titled Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter got accepted to 2023 Conference on Robot Learning (CORL)! [video]
June. 2023: Three papers accepted at IROS'23, one of the premier conferences in robotics. A big thank you to my students and collaborators!
1- Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition [video]
2- Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models [video]
3- L3MVN: Leveraging Large Language Models for Visual Target Navigation [video]
June. 2023: I received Google Research Scholar Award in the field of Machine Learning for my work on Continual Robot Learning in Human-centered Environments! Thank Google for their generous support!
June. 2023: I have been selected as an Outstanding Associate Editor for the IEEE Robotics and Automation Letters!
April. 2023: Our paper titled MORE: Simultaneous Multi-View 3D Object Recognition and Pose Estimation got accepted to Intelligent Service Robotics! - [open-access]!
March. 2023: We will organize a full-day workshop on the topic of "Interdisciplinary Exploration of Generalizable Manipulation Policy Learning: Paradigms and Debates" at RSS 2023.
Feb. 2023: Zhenxing Zhang successfully defended his Ph.D. thesis Generative Adversarial Networks for Diverse and Explainable Text-to-Image Generation. Congratulation Zhenxing!
Jan. 2023: Hamed Ayoobi successfully defended his Ph.D. thesis Explain What You See: Argumentation-Based Learning and Robotic Vision. Congratulation Hamed!
Jan. 2023: Hamidreza Kasaei is serving as associate editor for the IROS 2023!
Jan. 2023: Four of our papers have been accepted at ICRA'23, the premier conference in robotics. A big thank you to my students and collaborators!
1- Throwing Objects into A Moving Basket While Avoiding Obstacles. [video]
2- Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objects. [video]
3- Instance-wise Grasp Synthesis for Robotic Grasping. [video]
4- Frontier Semantic Exploration for Visual Target Navigation [video]
Nov. 2022: Hamidreza Kasaei gave an invited talk at the AI & Robotics in Healthcare | Data Science Center in Health (DASH) on Towards Lifelong Assistive Robotics: How to make life easier for people with disabilities? [video]
Nov. 2022: Hamidreza Kasaei gave an invited talk at the University of Aveiro, Portugal | Seminar in Robotics and Intelligent Systems on Robotics for Society: How robots can help us with a wide variety of tasks in different domains incrementally?
Oct. 2022: Our paper titled MVGrasp: Real-Time Multi-View 3D Object Grasping in Highly Cluttered Environments got accepted to Robotics and Autonomous Systems (RAS)! - [open-access]!
Sep. 2022: Hamidreza Kasaei is serving as associate editor for the IEEE Robotics and Automation Letters (RA-L)!
March. 2022: Our paper titled Sim-to-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution got accepted to Conference on Lifelong Learning Agents (CoLLAs 2022)! Congrats Georgios!
Sep. 2022: Hamidreza Kasaei is serving as associate editor for the IEEE ICRA 2023!
June 2022: We will organize a full-day workshop on 5th Robot Learning Workshop: Trustworthy Robotics at NeruIPS2022.
March. 2022: Our paper titled Lifelong 3D Object Recognition and Grasp Synthesis using Dual Memory Recurrent Self-Organization Networks got accepted to Neural Networks Journal! Congrats Krishna!
Jan. 2022: Hamidreza Kasaei is serving as associate editor for the IEEE/RSJ IROS 2022!

Research & Publication

My research interests focus on the intersection of robotics, machine learning and machine vision. I am interested in developing algorithms for intelligent robotic systems based on lifelong/continual learning and active exploration to enable robots to help humans in various daily tasks. I have been investigating on active perception and manipulation, where robots use their mobility and manipulation capabilities to model the world better. I have evaluated my works on different platforms including PR2, robotic arms, and humanoid robots. Please navigate the publications pages of my research group (IRL-Lab), if you are intersted to know more our research.

My research group (IRL-Lab), mainly focuses on interactive robot learning to make robots capable of learning in an open-ended fashion by interacting with non-expert human users. More specifically, we have been developing this goal over six particular research directions:

1 - Perception and Perceptual Learning

We are interested in attaining a 3D understanding of the world around us. In particular, the perception system provides important information that the robot has to use for interacting with users and environments.

2- Object Grasping and Object Manipulation

A service robot must be able to interact with the environment as well as human users. We are interested in fundamental research in object-agnostic grasping, affordance detection, task-informed grasping, and object manipulation.

3- Lifelong Interactive Robot Learning

A service robot must be able to interact with the environment as well as human users. We are interested in fundamental research in object-agnostic grasping, affordance detection, task-informed grasping, and object manipulation.

4- Dual-Arm Manipulation

A dual-arm robot has very good manipulability and maneuverability which is necessary to accomplish a set of everyday tasks (dishwashing, hammering). We are interested in efficient imitation learning, collabrative manipulation, and large object manipulation.

5- Dynamic Robot Motion Planning

We are interested in attaining fully reactive manipulation functionalities in a closed-loop manner. Reactive systems have to continuously check if they are at risk of colliding while planners should check every configuration that the robot may attempt to use.

6- Exploiting Multimodality

A service robot may sense the world through different modalities that may provide visual, haptic or auditory cues about the environment. In this vein, we are interested in exploiting multimodality for learning better representations to improve robot's performance.

Open Positions

We are actively looking for students to work on amazing robotic projects that involve:

Deep learning-based method for 3D object perception.
Visual representation learning for physical interaction (grasping and manipulation).
Deep reinforcement and imitation learning-based methods for planning & control.
Dual-arm object manipulation.
Lifelong Robot learning.
Efficient Supervision for Robot Learning.
Learning from Demonstration.
Multi-Task multimodal learning.
Simulation to real-world transfer learning (Sim2Real).

If you are interested in doing your PhD/Master/Bachelor thesis in one of the above areas, or working on a project with me, please send me an e-mail including:

  • Short CV
  • Short motivation letter

The motivation letter should state (½ - 1 page):

  • Topics that you are interested in
  • Type of project (theoretical/applied)
  • Intended starting date
  • Your relevant experiences


Seld-funded (externally funded) PhD, Master and Visiting Scholar

Good self-funded PhD, Master, and intern will be considered on a case by case basis. If you are interested in doing your PhD at Interactive Robot Learning Lab and you have funding from your Government (e.g., China Scholarship Council (CSC) scholarship), we can consider your application.

Contact



Dr. Hamidreza Kasaei
Artificial Intelligence Department,
University of Groningen,
Bernoulliborg building,
Nijenborgh 9 9747 AG Groningen,
The Netherlands.
Office: 340
Tel: +31-50-363-33926
Email: hamidreza.kasaei@rug.nl