Noushad Sojib

I am a Ph.D. candidate in Computer Science at the Cognitive Assistive Robotics Lab, University of New Hampshire, advised by Professor Momotaz Begum.

I completed my B.Sc. in Computer Science and Engineering from Shahjalal University of Science and Technology, where I was fortunate to work with my childhood idol, Professor M. Zafar Iqbal—a renowned scientist and science-fiction writer—and Dr. Ruhul Amin, whom I deeply admire.
I enjoy challenging myself—recently, I learned to juggle three balls, and my next goal is four.

Email  /  GitHub  /  Google Scholar  /  LinkedIn

Research

I am interested in making robot learn from lay users demonstrations. Since this data might be imperfect or contain errors, my focus is on developing methods for robots to learn safe and reliable behaviors from it.

Self Supervised Detection of Incorrect Human Demonstrations: A Path Toward Safe Imitation Learning by Robots in the Wild

We propose a Behavior Cloning for Error Detection (BED) framework that can detect incorrect human demonstrations in a self-supervised manner. With lay users demonstration we show that using our method robots can learn to avoid unsafe behaviors. We demonstrate the effectiveness of our method in RoboSuite simulation and with a Sawyer robot.

Self-Supervised Visual Motor Skills via Neural Radiance Fields

We propose a novel network architecture for visual imitation learning that exploits neural radiance fields (NeRFs) and key-point correspondence for self-supervised visual motor policy learning.

Robot From Scratch

I was inspired by the ASIMO robot, but there were no such robots in my country back then. Out of curiosity, I started learning how to build humanoid robots myself. During my undergraduate years, I founded RoboSUST, a robotics club where I worked with other passionate students to build several robots from scratch, including a biped walking humanoid.

Ribo Robot

Outcome: Ribo became one of the first humanoid robots publicly demonstrated in my country. It was showcased at multiple national events, drew strong interest from students and young people, and received wide coverage in newspapers and on television.

Lee: A biped walking robot

See the baby steps

Kiddo

Simulation and hardware.

Hardware Design

As I pursued my goal of building robots from scratch, I discovered a passion for designing smart devices—some of which are shown below.

3Wheel Mouse

Outcome: Islam, Md Touhidul, et al. “Wheeler: A three-wheeled input device for usable, efficient, and versatile non-visual interaction.” Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. 2024. Paper and Video:

Charging Dock

Outcome:

• Live demonstrated at IROS 2023..
• An extended version is being used with Hello-Stretch robot. See example

Lowcost Braille Display

Outcome: Sojib, Noushad, and M. Zafar Iqbal. “Single cell bangla braille book reader for visually impaired people.” 2018 International Conference on Bangla Speech and Language Processing (ICBSLP). IEEE, 2018. Paper

Design and source code from Jon Barron's website