Webpage: kninad.github.io | GitHub: kninad | Email: ninadk.utd@gmail.com | LinkedIn: linkedin.com/in/kninad EDUCATION 2019 - Present: UNIVERSITY OF TEXAS AT DALLAS, _Ph.D. in Computer Science_ - Intelligent Robotics and Vision Lab 2017 - 2019: UNIVERSITY OF MASSACHUSETTS, AMHERST, _M.S in Computer Science_ 2013 - 2017: INDIAN INSTITUTE OF TECHNOLOGY (IIT) KANPUR, _B.S. in Mathematics and Scientific Computing_ WORK EXPERIENCE Machine Learning/AI Internship – _Covariant.ai_ Jan 2024 - May 2024 | Emeryville, CA - Worked as a researcher in problem domain of AI-based robotics for warehousing and logistics operations - Explored generative models like VAE and Latent Diffusion for robot grasp generation from real-world inputs - Building robot foundation models that can deal with multi-modal inputs like text and images Research and Development Internship – _Kitware Inc._ Jun 2022 - Aug 2022 | Remote - Researched machine learning algorithms for approximating medial skeleton of point clouds & voxels - Implemented UNet based segmentation models for skeletonizing 2D images and adapted them for 3D setting - Demonstrated improved results via point-cloud skeletonization on data from hippocampi and leaflet regions Graduate Research Assistant – _University of Texas at Dallas_ Aug 2019 - Present | Dallas, TX - Researcher in Intelligent Robotics & Vision Lab, working on robot grasping, 3D vision and learning from humans - Concurrent research on interactive perception for unseen object segmentation in cluttered environments - Prior work on submodular information measures for machine learning problems in data selection & active learning - Involved in mentoring students, working as a teaching assistant and taking guest lectures in selected courses Mitacs Globalink Research Internship – _University of Manitoba, Winnipeg_ May 2016 - Jul 2016 | Winnipeg, Canada - Studied the problem of graph sampling and extracting relevant statistics like clustering coefficient - Implemented scale-down sampling with like Metropolis-Hastings and Jump random walks in R - Statistical models like ERGM were used for producing model fits and simulating random networks - Worked on second project for simulating team performance and biases in a football tournament structure TECHNICAL SKILLS PROGRAMMING LANGUAGES: Python, C/C++, R FRAMEWORKS/LIBRARIES: PyTorch, ROS, CUDA, IsaacGym, Unity, OpenGL DEVELOPMENT TOOLS: Git/GitHub, Docker, VS Code, Vim, Tmux, LaTeX, Pandoc RESEARCH PROJECTS INTERACTIVE PERCEPTION | _Unseen Object Segmentation_ - Leveraging long term robot interaction with objects for real world unseen object segmentation - Proposed self-supervised data collection method to improved real world segmentation performance - Extended the method to utilize uncertainty in segmentation for minimizing number of interactions ROBOT MANIPULATION | _Robust Grasping & Skill Transfer_ - Learning a common representation across different robot gripper grasps for efficient skill transfer - Proposed object contact-based metric learning constraints for effective learning in common space - Demonstrated applications for human to robot grasp trasnfer via our encoding + retrieval pipeline REPLICABLE BENCHMARKING | _Perception, Grasping & Motion Planning_ - Developed an intuitive method for replicable, real-world scenes of objects for robot benchmarking - Implemented scene generation pipeline in simulation with focus on cluttered but graspable scenes - Extened 10 existing methods across pose estimation, segmentation and grasping for real world experiments SUBMODULAR INFORMATION MEASURES | _Machine Learning_ - Proposed novel information theoretic measures for submodular set functionsin context for robust machine learning - Theoretical properties backed up with applications on outlier aware subsets, summarization & clustering tasks - Follow up works demonstrated computer vision applications in active learning for object detection RELEVANT PUBLICATIONS 1. RobotFingerPrint: Unified Gripper Coordinate Space for Multi-Gripper Grasp Synthesis, _(Under Submission)_ 2. MultiGripperGrasp: A Dataset for Robotic Grasping from Parallel Jaw Grippers to Dexterous Hands, _In IEEE International Conference on Intelligent Robots and Systems (IROS) 2024_. 3. RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features, _In IEEE International Conference on Robotics and Automation (ICRA) 2024_. 4. SceneReplica: Benchmarking Real-World Robot Manipulation by Creating Replicable Scenes, _In IEEE International Conference on Robotics and Automation (ICRA) 2024_. 5. CIS2VR: CNN-based Indoor Scan to VR Environment Authoring Framework, _In IEEE International Conference on AI & extended and Virtual Reality (AIxVR) 2024_. 6. Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction. _In Robotics: Science and Systems (RSS), 2023_. 7. Skeletal Point Representations with Geometric Deep Learning. _In IEEE International Symposium on Biomedical Imaging (ISBI), 2023._ 8. NeuralGrasps: Learning Implicit Representations for Grasps of Multiple Robotic Hands. _In Conference on Robot Learning (CoRL), 2022._ 9. Virtepex: Virtual Remote Tele-Physical Examination System. _In ACM SIGCHI Conference on Designing Interactive Systems (DIS), 2022._ 10. Submodular combinatorial information measures with applications in machine learning. _In International Conference on Algorithmic Learning Theory (ALT), 2021._ OTHER EXPERIENCE PROFESSIONAL SERVICE: - Reviewer for CoRL, ICRA, IROS, IEEE VR, ACM MM, ICMR, ICHI - Organizing committee member: Workshop for Neural Representation Learning for Robot Manipulation at CoRL’23 TEACHING ASSISTANT: Machine Learning, Robotics, Computer Graphics, NLP, Statistics for Data Science MENTORSHIP: Peer mentor for new PhD students at UT-Dallas and member of Counselling Service at IIT Kanpur ACHIEVEMENTS & AWARDS - Awarded the competitive IEEE RAS Travel Grant for ICRA 2024 in Japan. - UT Dallas Graduate Student Assembly travel award for paper presentation. - Awarded the Mitacs Globalink scholarship for summer research internship in Canada. - Recipient of Inspire scholarship awarded by Govt. of India for academic performance at IIT Kanpur. - Secured a percentile score of 97.7 in JEE (Advanced)-2013 and 99.8 in JEE (Main)-2013 national engineering entrance examinations.