CV
Education, experience, projects, publications, certifications, and technical skills.
Contact Information
| Name | Shubham Derhgawen |
| Professional Title | Robotics Graduate Student |
| sderh001@ucr.edu | |
| Phone | +1 (951)-465-9836 |
| Location | Riverside, California |
Professional Summary
Robotics graduate student at UC Riverside focused on embodied AI, machine learning, motion planning, and autonomous systems.
Experience
-
2025 - Riverside, California, US
Visiting Research Assistant
Motion Planning Lab, UC Riverside
Developing simulation and evaluation tooling for social robot navigation and embodied AI experiments.
- Developed a ROS 2 and Unity platform for crowd simulation and social robot navigation with support for 12 crowd policies.
- Built scenario generation, benchmarking, and evaluation tools for reproducible 75-trial and 75-episode experiments.
- Integrated crowd policies with motion matching and smoothing, reducing jerk by 9% and angular jerk by 21%.
-
2025 - 2025 Riverside, California, US
Grader/Reader
University of California, Riverside
Supported instruction for CS258 / EE227: Introduction to Reinforcement Learning.
- Graded assignments, projects, and exams for reinforcement learning coursework.
- Assessed student understanding of MDPs, dynamic programming, Monte Carlo methods, temporal-difference learning, and policy gradient methods.
-
2025 - 2025 Riverside, California, US
Visiting Research Student
Collaborative Intelligence Systems Lab, UC Riverside
Built infrastructure for human-in-the-loop autonomous driving experiments and multimodal data collection.
- Built a 3-vehicle CARLA platform across 3 machines with Logitech G923 controls for human-in-the-loop experiments.
- Developed a record-and-playback pipeline for real-time 720p simulation and high-resolution multimodal capture.
- Collected multimodal driving data in CARLA and supported real-world multi-agent driving data collection.
-
2022 - 2024 India
Software Developer
Vijeta Transport Private Limited
Built and maintained internal software systems for transport operations.
- Developed and maintained a customized transport management information system supporting business operations.
- Built real-time data handling and reporting components using Firestore and Power BI dashboards.
- Collaborated with stakeholders to translate operational requirements into deployable software features.
-
2020 - 2022 India
Systems Engineer
Tata Consultancy Services
Worked on enterprise ETL workflows and cloud migration efforts on Microsoft Azure.
- Supported migration and maintenance of ETL workflows from on-premises infrastructure to Microsoft Azure.
- Worked with C#, Azure Data Lake, Azure Data Factory, Azure Batch, and SSIS to build and maintain data pipelines.
- Monitored, debugged, and optimized ETL jobs to improve reliability and reduce downtime.
Education
-
2024 - 2025 Riverside, California, US
Master of Science
University of California, Riverside
Robotics
- Advanced Robotics
- Reinforcement Learning
- Foundations of Machine Learning
- Computational Methods for Robotics
- Artificial Intelligence
- Foundations of Robotics
- Information Theory
- Advanced Computer Vision
- Natural Language Processing
- Focus area: Embodied AI and Machine Learning.
-
2016 - 2020 Pune, India
Bachelor of Engineering
University of Pune
Information Technology
- Fundamentals of Data Structures and Algorithms
- Database Management Systems
- Operating Systems
- First Class with Distinction.
Publications
-
2026 CrowdROS: A Crowd Simulation Platform for Social Robot Navigation
IROS 2026
Submitted to IROS 2026 and currently under review. Authors: Shubham Derhgawen, Aadhar Chauhan, Andreas Panayiotou, Fabien Grzeskowiak, Julien Pettre, and Ioannis Karamouzas. * denotes co-first authorship.
Skills
Certificates
- Azure Data Scientist Associate - Microsoft
- Azure Fundamentals - Microsoft
- Accessibility in Action - Microsoft
- Problem Solving (Basic) - HackerRank
Projects
-
Autonomous Warehouse Pick-and-Deliver Robot
Developed an autonomous TurtleBot2-based robot with a manipulator for simulated warehouse pick-and-deliver tasks.
- Implemented a sampling-based planner to improve task-level planning for navigation and object delivery.
- Technologies used: Gazebo, ROS1, RViz, rqt, MoveIt.
-
Demonstration-Augmented Proximal Policy Gradient
Incorporated expert demonstrations into PPO to improve sample efficiency in LunarLander-v2.
- Modified the training objective to leverage expert data while maintaining task performance.
- Technologies used: Python, PyTorch, OpenAI Gym, Optuna, TensorBoard.