Name: Shivam Dhakad
Type: User
Bio: Meng. Robotics at University of Maryland, College Park
Robotics, Deep Learning, Computer Vision, Motion Planning and Navigation
Location: College Park, MD
Blog: https://tinyurl.com/MechanicalDesignPortfolio
Shivam Dhakad's Projects
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Repository for ARIAC (Agile Robotics for Industrial Automation Competition), consisting of kit building and assembly in a simulated warehouse
The project includes CAD designing and 3D printing the legged frame of the robot with Arduino control assembly, scripting the path planning and the computer-vision prepared assistive control to command the robot. Initially, the model is simulated in V-rep simulators and then applying the codes to the physical biped robot, which will mimic the action performed by the robot in the v-rep simulated environment with obstacles and paths.
Linear Inverted Pendulum Model based bipedal walking
A highly customizable and mobile first Hugo template for personal portfolio and blog.
Isaac Gym Reinforcement Learning Environments
A dataset of patient-derived anatomical environments with clinical tasks for medical robots.
An affordable Boston Dynamics-style robot dog for STEM education and AI-enhanced services.
Perception based autonmous navigation turtlebot
Reinforcement Learning on Bipedal-Walking-v3 by using modified version of SAC. We have achieved 300 score at episode 117, shows convergence in normal versionat the beginning of the 200 episodes. In hardcore we have achieved 300 rewards at episode 1296.
Designed a semi-automatic machine for small scale industry where the printing work is done manually using a screen-fabric frame. Machine prototype is designed on AutoCad software and mechanism operations were tested on MechDesigner software.
Assignments and notes for the Self Driving Cars course offered by University of Toronto on Coursera
portfolio webpage
Example repository for autonomous behaviors using TurtleBot3, as well as Docker workflows in ROS based projects.