About Me
Hello! I'm Nimish, a Robotics Engineer based in Enschede, the Netherlands.
I am a Robotics and Mechatronics Engineer with focus on Computer Vision. I completed my Masters from the University Twente. During my masters I worked on the thesis titled 3D Stereovision for Quantification of Skin Diseases under the supervision of dr.ir. Ferdi van der Heijden in the Robotics and Mechatronics research group.
I am passionate about Computers and interfacing them to simplify daily life by means of Electronics and Mechanics. My research interests include robotics, control theory, filtering techniques, visual odometry, simultaneous localization and mapping (SLAM), computer vision, 3D reconstruction, machine intelligence and machine learning. Currently, I am open to opportunities in the field of Robotics, Computer Vision, Deep Learning etc.
Where I’ve Studied
Master of Science - Electrical Engineering @ University of Twente
2018 - 2020 | Enschede, the Netherlands
- Specialization: Robotics and Mechatronics
-
Master Thesis:
Where I’ve Worked
Research Assistant @ Fraunhofer IPA
July - December 2019 | Stuttgart, Germany
- Developing Adaptive Offline Robot Programming Based on 3D Sensing
- Implementing deep learning algorithms to plan end to end optimal paths for mobile and articulated robots using Python and TensorFlow
- Setting up RESTful webservice for creating a library of CAD models for a labelled dataset generation
Skills I've
Programming
C, C++, Python, MATLAB, R, SQL, Java, Shell Scripting, Assembly, LATEX
Some Things I’ve Built
ES-EKF Visual SLAM
As a part of master thesis project, ES-EKF SLAM with quaternion kinematics was implemented to reconstruct the stereocamera trajectory and thereby reconstructing the object. Use of ES-EKF SLAM allows to have linear quaternion kinematics.
- MATLAB
3D surface reconstruction with sub-millimetre depth resolution
As a part of master thesis project, a stereocamera system was designed which is able to reconstuct objects with sub-millimetre depth resolution. Concept of positive and negative pattern projection by means of optical projector is evaluated provide robustness to specular reflection. As a consequence of wide baseline, DAISY desriptors is calculated.
- C++
- OpenCV
- MATLAB
- CloudCompare
- Android
Developing adptive offline robot programming based on 3D sensing
In this project, MPNet—a motion planning network, the technique employed by Qureshi et al. is used. This network receives environment information as point-clouds, as well as the robot’s initial and desired goal configurations and recursively calls itself to bidirectionally generate connectable paths. MPNet is implemented using Tensorflow, an end-to-end open-source machine learning platform with Python.
- Python
- TensorFlow
3D surface reconstruction
3D reconstruction of the face using measurements captured by 3DMD system. For this purpose, Computer Vision Toolbox is used. The image shows SURF keypoint correspondences.
- MATLAB
- 3DMD
3D surface reconstruction with sub-millimetre depth resolution
Concepts used while controlling the robot (e.g., twist, geometric jacobian etc.) have deep geometric meaning and are coordinate independent. This borrows concept of forward kinematics followed by differential kinematics, position control. Using these concepts position and velocity control laws are implemented.
- Arduino
- MATLAB
Other Noteworthy Projects
EKF-SLAM for Vehicle Localization
Vehicle trajectory estimation using static landmarks in an unexplored area. Three types of methadologies are investigated, viz.,
- Prediction Only
- Bearing and Distance Measurements
- Bearing Only
Virtual Camera Rotation for Photogrammetry
Estimation homography using set points and known object size
Robust Key Point Detection and Matching
- Comparision of Harris, Minimum Eigen, FAST, ORB, BRISK, SURF, KAZE, MSER features
- RANSAC for outlier detection and robust estimation
- Procrustes algorithm
Implementation of Kalman filter and Optimal Control Law for Human Movement Control
- Kalman filtering for state estimation during movement of human hand
- optimal feedback control strategy for muscle activation
What’s Next?
Get In Touch
Although I'm currently looking for new opportunities and my inbox is always open. Whether you have an opportunity, question or just want to say hi, and I'll get back to you!
Say Hello!