About Me


Aswath's Photo
 Hello! I am Aswath Muthuselvam, welcome to my personal website. In this space, I will share my projects and professional updates. Currently, I am a software engineer at Magic Leap, working on Ground Truth data using advanced Camera Systems, Motion capture systems for applications like Hand Tracking, Localization, and Mapping. Previously, I graduated from the University of Maryland, College Park, with Master of Engineering degree in Robotics. I also worked with Dinesh Manocha at the GAMMA lab.  I graduated with a Bachelors degree in Electronics and Communications Engineering from Vellore Institute of Technology. During the final semester, I have interned at Ericsson India Global Services, where I worked on “Deeplearning based disease detection in Horticultural crops.”
LinkedIn / CV / GitHub

Check out my projects and publications below.

Projects and Publications


CrossLoc3D
CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition - ICCV 23
Github / Arxiv / Poster

Tianrui Guan, Aswath Muthuselvam, Montana Hoover, Xijun Wang, Jing Liang, Adarsh Jagan Sathyamoorthy, Damon Conover, Dinesh Manocha

First, we present a cross-source point cloud dataset, which consists of Ground Truth global point cloud in UTM coordinates generated from aerial map and Query point clouds captured from Spot and Husky robots. Secondly, we show a novel architecture to localize the Query point cloud in the Ground Truth point cloud. 

Self Driving Car Trajectory prediction
Github / Report
Predict the trajectory of a Self-Driving vehicle, given a Birds eye view of the traffic scene. Used Lyft’s perdiction dataset and L5Kit’s Jupyter notebooks template. Leveraging Attention mechanism of Vision Transformer and an Fully connected layer to predict the trajectory of a Self Driving Vehicle.

RRT CUDA
Github
Parallize obstacle collision check with cuda kernels.

Human Pose Estimation and Forecasting
Report
1. Improved accuracy from SOTA Poseformer architecture by using various loss functions for Human Pose estimation. 
2. DA-STS-GCN(Domain Adaptive Space Time Separable Graph Convolutional Network) for Human Pose forecasting. 
3. Trained the networks on Human 3.6M dataset.

AR Cube Projection
Github 
Projecting a 3D unit cube in a monocular video using an Aruco Marker as feature location.

Lane detection
Github / Report
1. Find the lanes on the road.
2. Identify and mark the left and right lane with different colors. 

Dijsktra Path Planning
Github
Path planning from start to goal location while avoiding obstacles.

A* Path Planning
Github
Path planning from start to goal location while avoiding obstacles.

Panda Robot ARM Trajectory Planner
Github
Implement a robot arm planner using ROS and Moveit

Curve Fitting through data points
Github
Fit a second order polynomial for a list of 2D data points as a ball follows a projectile motion. 

Depth from 2 images
Github 
1. Undistort 2 images with given camera extrinsics.
2. Do image path matching by keeping one image as reference. 
3. Create disparity map using sliding window method
4. Compute depth with disparity map.

KNN Image Segmentation
Github /
An Android mobile phone’s accelerometer and Gyroscope data is used to detect potholes in realtime.

Omnidirectional robot with UR5 arm
Github /

A 6DOF arm can manipulate objects in SE3(translation + rotation) space, however, one constraint remains, the arm’s reachability. OmniDirectional wheeled mobile robots are free to move in the XY plane in any direction, allowing more freedom of movement than Non-Holonomic Car like robots. Combine these two ideas, we get a high DOF arm + infinite reachability in XY plane. To name a couple of examples, these robots can be used in warehouse operations and perform agricultural tasks.
Technical approach:
- Arm: Calculation of inverse kinematic for the arm using Pseudo-Inverse Jacobian.
- Robot base: Calculation of angular velocity of motors by inverting Forward Transformation from base frame to wheel frame. Then using PID for feedback control using errors in position.

Inverse Kinematics of UR5 arm
Github /
Inverse kinematics for a 6-DOF Robotic arm is calcuated by taking Jacobian Pseudo-Inverse of the Forward Transformation of each arm joints. Implemented with Coppelia-Sim simulation software.

Swarm Robots
Github /
Multiple agents push a large object. Each agent plans a path to the destination using RRT* algorithm.

Ground Plane Free Space Segmentation for Autonomous robots
Github /
 

Realtime   Detection
Github / Slides
An Android mobile phone’s accelerometer and Gyroscope data is used to detect potholes in realtime.

C++ Shooter Game
Github 
Simple shooting game coded for 11th grade school project.