Graduate Research Assistant Pace University
• Developed object detection models for robots using the YOLO algorithm (CNN), increasing the capability of detecting 2D & 3D objects in static images and live feeds by 30%.
• Leveraged PyTorch and TensorFlow to develop autonomous decision-making for robots, achieving 95% accuracy.
• Created a simulation environment replicating real-world conditions using camera, LIDAR, and other sensors.
• Achieved 95% accuracy in environmental mapping and employed ISSAC Simulation and Unreal Engine for creating simulation.
• Integrated ROS, simulation tools, LLMs, and AI in robots to execute written commands (e.g., “detect the person”, “follow the person”), with an 80% success rate in command execution.
• Imported and utilized actual robot URDF and OBJ files within the simulation environment, reducing setup time by 30%.