Improved monocular depth estimation accuracy by learning an image-conditioned scaling factor to correct metric scale errors, enabling reliable 3D scene understanding without additional sensors.
Controlled a differential wheeled robot with a joystick by establishing bluetooth connections with the robot and joystick and mapping the joystick state to robot wheel speeds.
Created a program that converted input images (uploaded directly by users or captured with a robot’s fisheye camera) to trajectories that the robot would follow to perform its drawing task.
Trained and tested deep learning based object detection models, RetinaNet and YOLOv5, on an on-road vehicle dataset and their performance was investigated.
Designed an underwater localization system for UUVs utilizing inertial pose estimation and beacon triangulation based on acoustic communication understanding constraints of underwater communication and dead reckoning using IMU.
Created a map of school tunnel using various SLAM algorithms on sensor data collected by a LiDAR, Cameras, and IMU.
Employed Gmapping SLAM, Frontier-Based Exploration and tag detection on TurtleBot3 to achieve a reconnaissance mission autonomously in a closed and unkown environment.
Designed a wearable motion tracker and programmed its algorithm to track and evaluate user’s body postures while doing an exercise.
Designed a flower-care monitor system using various sensors such as moisture, light, and temperature sensors and stored the sensor data in a Google Cloud server through Wi-Fi to analyze futher.
Configured a robotic arm on a FPGA board and programmed the arm to follow motions of a Wii-mote controller.