Aditya M. Deshpande

I recieved my PhD in Mechanical Engineering from the University of Cincinnati working with Profs. Manish Kumar and Ali A. Minai. My PhD research was focused on embodied intelligence in robots.

Curriculum Vitae: PDF

Email: deshpaad [at] mail [dot] uc [dot] edu

Research Interests

Embodied Intelligence, Evolutionary Approaches in robotics, Developmental Robotics, Deep reinforcement learning, Swarm and Multi-robot systems, Flying Robots, IoT

Research

  • DeepCPG Policies for Robot Locomotion.
    [arxiv][paper][Media]
  • Robust deep reinforcement learning for quadcopter control.
    [arxiv][paper][code]
  • Developmental reinforcement learning of control policy of a quadcopter UAV with thrust vectoring rotors.
    [arxiv][paper][code]
  • Computer Vision Toolkit for Non-invasive Monitoring of Factory Floor Artifacts.
    [paper]
  • One-Shot Recognition of Manufacturing Defects in Steel Surfaces.
    [website][code][arxiv][paper]
  • Self-Organized Circle Formation around an Unknown Target by a Multi-Robot Swarm using a Local Communication Strategy.
    [paper]
  • Robot swarm for efficient area coverage inspired by ant foraging: The case of adaptive switching between brownian motion and lévy flight.
    [paper]
  • Constraint handling in firefly algorithm.
    [paper]

Teaching

Projects

  • pyneat - NeuroEvolution of Augmenting Topologies (NEAT) [GitHub]
  • torch_shnet - Stacked HourGlass Networks for Human Pose Estimation [GitHub]
  • indoor_bot - Simple autonomous indoor robot [webpage]
  • Multi-object trackers in Python [webpage]
  • Autonomous Flying Robot [webpage]