Prem Raj

Prem Raj

Ph.D. Scholar Email:praj@cse.iitk.ac.in

I am a Ph.D. scholar at IIT Kanpur's CSE department, working on Robust Grasp Strategies for Robotic Bin-picking. My research advisers are Laxmidhar Behera and Tushar Sandhan. I completed my BTech and MTeach at IIT Jodhpur and have previously worked as a software engineer at Samsung R&D.

My research interests and work focus on developing innovative and reliable robotic grasping stretegies for automated object picking for practical scenerios such as warehouse automation. My work aims to address the significant challenge of fully automated picking of novel objects in dense cluttered piles, enabling more efficient and reliable manipulation of objects by robots. For a quick view of the my current research work, please have a look at the experimental video of our recentaly published paper at IEEE-TASE.

Previously, my work Towards Object Agnostic and Robust 4-DoF Table-Top Grasping was selected as the finalist for best student paper award in IEEE International Confrence CASE 2022.

Publications

Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing

IEEE International Workshop on Intelligent Robots and Systems (IROS), 2020.

PDF Video Code Direct Download

Scalable and Time-Efficient Bin-Picking for Unknown Objects in Dense Clutter

IEEE Transactions on Automation Science and Engineering (T-ASE), 2023 .

Paper Video Direct Download

Towards Object Agnostic and Robust 4 -DoF Table-Top Grasping

IEEE 18th International Conference on Automation Science and Engineering (CASE), 2022 (Best Student Paper Award Finalist).

PDF Video Direct Download

Domain-Independent Disperse and Pick method for Robotic Grasping

International Joint Conference on Neural Networks (IJCNN), 2022.

PDF

Bin-picking novel objects through category-agnostic-segmentation: RGB matters.

IEEE International Conference on Robotic Computing (IRC), 2023 .

Paper Direct Download

Co-learning monocular depth-estimation and category-agnostic-segmentation for Bin-picking novel objects.

IEEE Robotics and Automation Letters (RA-L) (To be submitted).

News

Succesfully delivered the open-seminar! The first-step towards the completion of the PhD program.
Our paper on “Scalable and time-efficient bin-picking for unknown objects in dense clutter" has been accepted to IEEE Transaction on Automation Science & Engineering (TASE), 2023.
This work was jointly supervised by Dr. Tushar Sandhan and Prof. Laxmidhar Behera
Our paper Bin-picking of novel objects through category-agnostic-segmentation: RGB matters has been accepted to be published at IEEE Robotic Computing, 2023. The confrence is going to be held at Laguna Hills, CA on December 11-13, 2023.
From today the 4-month research visit under Mehta Rice Engineering Scholars Program is starting. I am thankful to Prof. Vaibhav Unhelkar for kindly agreeing to be my supervisor during this research study. I would be working upon implementing imitation-learning algorithm for real-world manipulation task with panda manipulator robot.
Selected for the Mehta Rice Engineering Scholars Program 2023.
Our paper “"Towards Object Agnostic and Robust 4-DoF Table-Top Grasping has been selected for best student paper award finalist for CASE, 2022 to be held in Mexico City at 10:10am to 12:00 pm on Monday, August 22, 2022.