Vaishanth Ramaraj

- Designed and implemented a low-latency, Rust-based pipeline for real-time streaming, synchronization, and recording of multi-camera and multi-sensor data, leveraging NVIDIA hardware-accelerated video encoding, achieving a low memory footprint and approx 5% CPU utilization on a Jetson Xavier. - Developed a data generation pipeline using SAM3 video tracking to expand labeled datasets by tracking objects across frames, enabling dataset scaling with less manual annotation, thereby accelerating model deployment in new environments. - Enhanced host-level monitoring system on Jetson Xavier that executes multi-layered action commands, resulting in a 60% reduction in CPU load. 7-Axis Manipulator - Implemented a time-parameterization algorithm for a 7-axis manipulator to enable smooth and reliable trajectory execution, computing parameterized trajectories in ≤10 ms under complex trajectory conditions and reducing overall trajectory execution time by 2–4 seconds. Object Detection Model - Integrated architectural enhancements into an existing multi-head object detection network by introducing an additional detection head, improving feature representation and enabling more consistent and accurate object localization and classification. Isaac Sim - Integrated a custom mobile manipulator with a 7-axis arm into Isaac Sim using OmniGraph nodes and ROS communication, and developed a greenhouse fruit farm simulation environment with deformable fruit models to realistically simulate gripper–fruit interactions during manipulation. - Developed OmniGraph nodes for procedurally generating partial simulation environments, ( e.g dynamic spawning of objects) and facilitating faster testing of robotic capabilities across diverse experimental setups. End to End Navigation Model - Developed an end-to-end vision-based navigation model using Transformers and diffusion policies, enabling mobile robot navigation from monocular camera input while supporting platform-agnostic deployment.

• Implemented a semantic segmentation network to detect leaf pruning points for automated plant maintenance, boosting accuracy by 30%. • Developed point cloud processing algorithms and machine learning models for point cloud registration, increasing the 3D reconstruction accuracy of small objects by 40% over conventional approaches.

• Implemented ROS2 micro-ros agent on Jetson devices remotely through SSH. Deployed the code using ARM based docker container and used X11-forwading to visualize GUI applications locally. • Integrated BlynkEdgent C++ package into ESP32 to scan and connect to multiple WiFi networks. Worked on integrating VPN services through docker to provide access to ROS2 systems on different networks. • Currently working on deploying Odometry Fusion packages on Jetson Nano.

• Managed a team to develop a modular autonomous navigation system for a powered wheelchair. • Designed and developed end-to-end pipelines for mapping and localization using ROS, PyTorch, RTabmap and OpenCV with real-time performance of 35 FPS. • Tested the software system in the Gazebo simulation with a dense environment to validate the system’s integrity. • Deployed the system using ARM-based docker container on Jetson Nano with Intel RealSense stereo camera, resulting in 52% cost savings and less than 10W power consumption. • Developed a real-time object detection system for smart wheelchair using YOLOv5 and Point Cloud algorithms for obstacle avoidance. • A lightweight KIVY framework GUI for touch navigation was implemented, for a user-friendly and intuitive control interface

• Developed a ROS-based automation system for a Water Aeration Device, reducing manual intervention. • Designed and deployed a Random Forest regression model on the cloud to analyze real-time sensor data with 160ms latency, ensuring 89% accuracy in aeration control predictions • Integrated an ESP32-based Wi-Fi controller with a mobile application using MQTT and RESTful APIs, enabling remote monitoring and real-time control, reducing on-site maintenance costs by 40%. • Optimized edge-to-cloud communication, reducing data transmission latency and ensuring 96% uptime for continuous aeration system monitoring.

Designed and fabricated a soft robotic gripper using flexible 3D-printed materials, enabling secure handling of fragile objects up to 500g. • Developed and simulated the complete mechanism in SolidWorks, optimizing structural integrity through stress analysis. • Developed mechanical linkages for underwater manipulation and integrated an ESP32-controlled stepper motor, ensuring precise actuation with a ±0.5mm tolerance. • Optimized the gripper’s design, reducing overall weight by 30% while maintaining high grip strength, enhancing efficiency for underwater applications.