Prabin Kumar Rath

I am pursuing my Masters in Robotics and AI at Arizona State University. My research interest lies in 3D Computer Vision, Motion Planning, and Reinforcement Learning for Robotics applications.

Currently I am working with Dr. Hongbin Yu at ASU-EVSTS Lab to develop robust and efficient detection and tracking algorithms with 128 channel LiDARs. My research focus is to improve pedestrian safety at traffic intersections using infrastructure sensor setups.

For my masters thesis I have joined the Logos Lab to work on on Neural Motion Planning for robotic manipulators with Dr. Nakul Gopalan

Earlier I was a software developer and data analyst at Wells Fargo - EGS, where I worked on document layout analysis for numerical data extraction from handwritten forms.

I received my B.Tech degree in Computer Science and Engineering from the National Institute of Technology, Rourkela. During my junior year summer internship, I worked with Dr. Alex Ramirez-Serrano at the UVS Robotarium Lab - University of Calgary and developed efficient perception algorithms for humanoid robots. Before that, I collaborated with Dr. Dilip Kumar Pratihar at the Soft Computing Lab - Indian Institute of Technology, Kharagpur, and developed control algorithms for rehabilitation robots.

Email  /  CV  /  Github  /  Google Scholar  /  Linkedin  /  ResearchGate

Real-time VRU safety metrics evaluation strategies for urban traffic intersections.

Leader-follower pair identification and metrics evaluation from aerial drone videos.

Complex-YOLO 3D detection and EKF tracking pipeline for measuring intersection safety metrics with CAROM dataset as pseudo ground truth.

Health Kit project for hospitals to assist doctors in simplifying diagnosis.

Detection and Tracking of Moving Objects (DATMO) algorithm for robot navigation in dynamic environments.

paper / code

Room Automation Module for switching electrical appliances remotely through Web, Bluetooth, and IR.

A robot for playing the game of chess physically with an user. Powered with strong chess engines and interactive UI it provides all virtual game features and ensures the authenticity of the original board game.

Multi-robot swarm pattern formation using the Signed Distance Field (SDF) of hand drawn images.

Implementation of T-REX and D-REX Inverse Reinforcement Learning (IRL) algorithm for learning form suboptimal demonstrations.

Deep Reinforcement Learning with PyTorch and OpenAI-Gym. Implementation of Deep-Q-Learning and Dueling Double Deep-Q-Learning Algorithms.

An AI agent that utilizes Monte Carlo Tree Search (MCTS) for exploration and exploitation but switches to customized reflex actions at critical zones.

Implementation of ST-ResNet model for predicting traffic flow on BikeNYC and TaxiBJ datasets.

A tutorial for integrating ROS navigation and mapping stack with your custom differential drive robot.

Trajectory optimization for the cart pole swing-up problem and balancing inverted pendulum on a cart pole system using LQR control.

Simple LSTM model for classifying colloquial english sentences onto motion commands. Curated text to command dataset.

Mathematical modelling of end effector pitch. Closed-loop PID control for canceling the base motion effects on the end effector.

Customized replica of Turtlebot arm for pick and place tasks. ROS Control and MoveIt stack. Gym compatible environment for training RL agent in Gazebo.

6DOF holonomic robot with integrated vision sensors for carrying out planned missions autonomously in underwater environments.

A 2D Dot matrix printer is a DIY project made from old CD drives.

A Bluetooth controlled robot with on board FSR (Force Sensitive Resistor) for weight detection. It has indication LEDs to prompt the user about the detected weights.

A 8*8*8 LED cube made using 9 shift registers 74HC595 and Arduino Nano.