Beep Beep!
This kid loves building ROBOTS!
Follow @VihaanAkshaaySanta Barbara, California
vihaanakshaay@gmail.com
Skills
Python, C++, Ruby, HTML, MATLAB, Mathematica, TensorFlow, Keras, PyTorch, ROS (Robot Operating System), PCL(Point Cloud Library), Gazebo, RViz, Blender, Fusion360, Jupyter, Git, Linux
Probabilistic Robotic Algorithms (Localization, Mapping, SLAM, Path planning and Navigation), Applied Deep Reinforcement Learning, Innovative Robotic Solution Modelling, Fusion360
Coding Activity
About
Life is a continuous learning journey! I am an enthusiastic and dedicated graduate student, currently pursuing a Master of Science in Computer Science. My background includes a B.Tech in Mechanical Engineering and an M.Tech in Robotics from IIT Madras. I am versatile, quick to grasp new concepts, and enjoy collaboration. My current focus is on Deep Reinforcement Learning and Robotics. My ambition is to develop embodied AI systems that continuously learn from human interaction, envisioning a future where robots become integral, ever-learning assistants in our daily lives.
Education
Master of Science
University of California, Santa Barbara
Master of Science in Computer Science (Machine Learning Specialization)
Dual Degree (B.Tech in Mechanical Engineering + M.Tech in Robotics)
Indian Institute of Technology, Madras
Bachelor of Technology in Mechanical Engineering & Inter Disciplinary Master of Technology in Robotics
Robotics Software Engineer Nanodegree
Udacity
Programmed various robots in simulation and worked with Jetson TX2 hardware implementing various robotic algorithms(Localization, Mapping, SLAM, Path Planning and Navigation, 3D perception, Deep Learning, Manipulator Kinematics) and tools(ROS using python & C++, RViz, Gazebo and more).
https://www.udacity.com/course/robotics-software-engineer--nd209
Projects
Bi-Directional Goal-Conditioning for State Space Search Problems
Developed the ‘SRE-DQN’ (Scrambler-Resolver-Explorer) framework, leveraging bi-directional task generation through ‘Foresight Relabelling’ and goal-conditioned DQN.
Cascaded Deep Monocular 3D Pose Estimation with Evolutionary Synthetic Training Data
With the first step of identifying key points from ample raw video data for unsupervised behavior recognition using option discovery, this project proposes using open-source three-dimensional synthetic animated mouse models to improve existing pose and estimation models.
AI for Earth - Landslide Detection
Developing a deep learning model for landslide prediction using Multi-band Satellite Imagery, benchmarking against Mask RCNN and YOLO models for effective instance segmentation across diverse regions.
Interactive Traffic Classification using Semi-Supervised Graphical Approaches
By leveraging graphical machine learning models (such as GCN and DGCNN), using psuedo-labeling and exploiting the dependencies between bursts, we achieved near State-of-the-Art performance in interactive network traffic classification with smaller models (0.2% the size of a BERT-based model).
https://vihaanakshaay.github.io/assets/reports/Graph_ML_Report.pdf
ARTEMIS - Railroad Crack Detection Robot
ARTEMIS is an autonomous robot that traverses inbetween the railway tracks, detects faults and sends the coordinates for further action to be taken.
https://www.jamesdysonaward.org/2017/project/railroad-crack-detection-bot/
Robotic Arm - Pick and Place
The goal of the project is to solve is to simulate a robotic arm and perform a pick-and-place exercise very similar to Amazon Robotics Challenge.
https://github.com/VihaanAkshaay/Project_Robo-ND_Robotic-Arm_Pick-And-Place
3D Perception Project
The goal of this project is to program a PR2 to identify and acquire target objects from a cluttered space and place them in a bin. The project is based on the 'Stow Task' portion of Amazon's Robotics Challenge.
https://github.com/VihaanAkshaay/Project_Robo-ND_3D-Perception-Project
Robotic Arm - Pick and Place
In a simulated environment, given camera input from a drone, the goal is to train a fully convoluted neural network to identify the location of a moving target and to control the drone to follow the same.
Work Experience
Graduate Student Researcher
Jackson Laboratory
Developed unsupervised techniques to discover stereotyped behaviours exhibited by mice moving in a fixed arena. Computer Vision models were used for pose estimation from video data recorded by Jackson Labs are improved. By modeling behaviours as hierarchies, new option discovery algorithms were implemented to identify repeated behaviours. Dr. Ravindran B, Indian Institute of Technology Madras & Dr. Vivek Kumar, Jackson Labs, Bar Harbor, Maine.
iBot(Robotics) Club Head
iBot Club, Centre for Innovation
Managed and mentored various projects as well as conducted robotics oriented session with the aim of improving the tech culture in the institute.
Robotics Intern
Ramakrishna Math, Chennai
Worked on 'Biley Bot', a lifelike, interactive humanoid robot of young Swami Vivekananda, soon to be displayed in Vivekanandar House Museum, Chennai.
Summer Engineering Intern
Toyota Kirloskar Motor Pvt Ltd
Industrial internship with on-field experience from a reputed manufacturing factory. Experience on workshop floor included a project study on Backdoor Cushion Rubber Miss Elimination.