Showcase of Robotics & Perception
Bridging the gap between intelligent algorithms and physical execution through advanced computer vision and embedded systems.
Dronaid
AI Systems Engineer | Manipal, India
Jul 2022 - Sep 2023
Computer Vision on Edge
Integrated CV models across hardware, embedded & software layers. Improved YOLO realtime inference from 5 to 12 FPS by switching from Python to C++, tuning precision, and applying GPU optimizations (Triton, TensorRT, NSight, CUDA).
Embedded Systems
Worked with Jetson Nano and Raspberry Pi to build software & CV for drones. Integrated camera & LIDAR to CV models via ROS. Deep dived into Linux camera pipelines.
CV Perception Pipeline
YOLO for object detection -> Image segmentation for precise boundaries -> DEEPSORT for tracking -> Mapping coordinates with GPS & LIDAR.
Memory-Compute Profiling
System-level profiling to identify CPU, GPU, Memory, I/O bottlenecks. Troubleshooted end-to-end issues across all layers.
C++ Parallel Programming
Designed multi-threaded processing to separate capture, preprocessing, and inference for stable frame rates using OpenMP & MPI.
Exposure
Collaborated with 40+ members, gaining exposure to microcontrollers, networking, electronic subsystems, and manufacturing.
AI for Robotics & VLA Models
- Completed advanced robotics curriculum under Prof. Dieter Fox, implementing state estimation and planning algorithms including EKF-SLAM, RRT, particle filters & RL policies.
- Studied Vision-Language-Action (VLA) models for robotic control, mapping vision and language to dynamic action policies.
- Worked with LeRobot-So-100 arm to analyze generalization, task transfer, and VLA model training efficiency in simulated and physical environments.
Computer Vision Toolkit
Object Detection
Locating and classifying entities in dynamic environments.
Image Segmentation
Pixel-perfect boundaries for precise spatial awareness.
DEEPSORT Tracking
Persistent identity tracking across complex video frames.
