Dhruv Patel

Dhruv Patel

About me

I am an MS Robotics student at the School of Interactive Computing, Georgia Tech. I currently conduct research on Cross-Embodiment Learning for Robot Manipulation from Human-Play data at the Robot Learning and Reasoning (RL2) lab with Dr. Danfei Xu My interests broadly lie at the intersection of Robotics, Computer Vision and Deep Learning.

I spent summer 2024 interning at Honda Research Institute, USA, working on Scene Understanding for Autonomous Driving at Intersections. Before Georgia Tech, I explored open-source software development as a Google Summer of Code'23 contributor at Unify AI, with an aim to optimize SLAM for real-world deployment in Robotics applications. Prior to this, I was a Project Associate at the Robotics Research Centre (RRC), where I worked on Scene Understanding for Autonomous Driving in Adverse Weather Conditions (affiliated with Queensland University of Technology (QUT) and ZF Group, and spearheaded the IHub Project Mobility on UAV-based Visual Remote Sensing for Civil Infrastructure Safety Assessment.

I spent the summer of 2020 working on Simultaneous Localization and Mapping (SLAM) for Level-5 Autonomy at Swaayatt Robots. Post this, I transitioned to a Software Engineering role at Amdocs, and alongside, collaborated with the Norwegian Biometrics Laboratory (NTNU, Norway) to conduct research on Image Super-Resolution problem.

I always look forward to interesting collaborations or chats on AI. Feel free to ping me on LinkedIn or through email.

Interests

  • Robotics & Computer Vision
  • Deep Learning
  • AI & Neuroscience

Education

  • MS in Robotics, August 2023- May 2025

    Georgia Institute of Technology (Georgia Tech)

  • B.Tech in Electronics & Communication Engg, July 2016 - July 2020

    Sardar Vallabhbhai National Institute of Technology, Surat

Recent

Work Experience

 
 
 
 
 

Graduate Student Researcher

Robot Learning and Reasoning Lab (RL2), Georgia Tech

Jan 2024 - Present
Advisor: Dr. Danfei Xu
  • Cross-Embodiment Learning for Robot Manipulation from Human-Play Data [WebPage]
    • Keywords: Scene Understanding, ADAS, Robotics, Deep Learning,
     
     
     
     
     

    Research Associate Intern

    Honda Research Institute, USA

    May 2024 - August 2024

    • Developed perception algorithms for intersection detection and navigation for HRI’s Autonomous Vehicle (AV) platform.
    Keywords: Scene Understanding, ADAS, Robotics, Deep Learning,
     
     
     
     
     

    Open-Source Software Developer

    Google Summer of Code 2023

    June 2023 - August 2023

      Multi-backend framework support of GradSLAM in Ivy [WebSite]

      • Google Summer of Code'23 Contributor at Ivy - unify.ai
      • Developed a multi-backend framework support (PyTorch, JAX, NumPy, Tensorflow) for GradSLAM library in Ivy, with an aim to optimize deployment through highly efficient frameworks like JAX.
    Keywords: Robotics, Deep Learning, PyTorch, JAX, NumPy, Tensorflow
     
     
     
     
     

    Project Associate

    Robotics Research Centre(RRC), IIIT Hyderabad

    July 2021 – July 2023

      Scene Understanding for Autonomous Driving
      Advisors: Prof. Madhava Krishna and Dr. Sourav Garg

      • Collaborated with ZF Friedrichshafen group and Queensland University of Technology (QUT) Robotics on improving scene understanding and exploring object detection/tracking, segmentation for weather-agnostic setting.
      • Proposed GDIP: Gated Differentiable Image Processing (GDIP) for Object-Detection in Adverse Conditions, which establishes a new SOTA for foggy and low-lighting.
      • Researched downstream problems like video object detection/tracking in adverse weather setting exploring various spatio-temporal techniques. Also, explored Probabilistic Graphical Models (PGMs) for weather-agnostic feature refinement


      DodgeDrone: Vision-based Agile Drone Flight [WebPage]
      Advisors: Prof. Madhava Krishna

      • Devising a high-level control strategy for obstacle avoidance through Imitation Learning in conjunction with Reinforcement Learning.


      UAV-based Visual Remote Sensing for Automated Building Inspection (UVRSABI)
      Advisors: Prof. Madhava Krishna, Dr. Ravi Kiran and Dr. Harikumar Kandath

      • Automated assessment of civil structures with the help of visual remote sensing.
      • Utilized Structure-from-motion, state estimation, odometry etc. in conjunction with classical Computer Vision and Deep Learning-based visual inspection algorithms to robustly estimate critical structural parameters.
      • Developed and released an open-source library (UVRSABI) for the community. More details here.
    Keywords: Robotics, Computer Vision, Deep Learning, Reinforcement Learning, 3D Reconstruction, Autonomous Driving, ADAS, UAVs
     
     
     
     
     

    Software Engineer

    AMDOCS

    Aug 2020 – June 2021 Pune
    Scrum Master/Team Lead: Shreyas Kulkarni
  • Responsible for B2B production-level full-stack software development.
  • Developed cross-functional telecom software solutions for Comcast's Orion project (USA).
  • Collaborated with global product owners, ensuring end-to-end feature development, integration and validation with testing team.
  • Technical Stack: Java, ReactJS, SQL, Spring Boot, Maven, and Jenkins.
    • Keywords: Java, SQL, ReactJS, Object-oriented Programming, Microservices, Jenkins, Maven, Spring
     
     
     
     
     

    Research Intern

    Swaayatt Robots

    April 2020 – July 2020
    Advisor: Sanjeev Sharma (Founder & CEO - Swaayatt Robots)
  • Improved Visual Odometry and SLAM pipelines for Level-5 Autonomy.
  • Devised a semantic variant of the Iterative Closest Point (ICP) algorithm outperforming vanilla ICP in terms of matching loss and convergence time, respectively, on the Semantic KITTI dataset.
  • Developed a low-level C++ library.
    • REPORT PDF
    Keywords: Robotics, Mathematical Optimization, SLAM, ICP, LiDARs
     
     
     

    Deep Learning Research Intern

    Sardar Vallabhbhai National Institute Of Technology, Surat

    May 2019 - July 2019
    Advisor : Dr. Kishor Upla (Assistant Professor, ECED)
  • Implemented state-of-the-art FaceNet paper and validated it on a custom made dataset of 25 students.
    • Keywords: Face Recognition, Deep Learning

    Publications

    EgoMimic: Scaling Imitation Learning via Egocentric Videos
    Simar Kareer, Dhruv Patel*, Ryan Punamiya*, Pranay Mathur*, Shuo Cheng, Chen Wang, Judy Hoffman, Danfei Xu
    Conference on Robot Learning (CoRL) 2024
    PDF Code Website Video Hardware Datasets
    GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions
    Sanket Kalwar*, Dhruv Patel*, Aakash Aanegola, Krishna Reddy Konda, Sourav Garg, K. Madhava Krishna
    International Conference on Robotics and Automation (ICRA) 2023
    PDF Code Website
    UAV-based Visual Remote Sensing for Automated Building Inspection
    Kushagra Srivastava*, Dhruv Patel*, Aditya Kumar Jha, Mohhit Kumar Jha, Jaskirat Singh Ravi Kiran Sarvadevabhatla, Pradeep Kumar Ramancharla, Harikumar Kandath, K. Madhava Krishna
    Spotlight paper at European Conference on Computer Vision (ECCV) Workshop 2022
    PDF Code Website Documentation
    SRTGAN: Triplet Loss based Generative Adversarial Network for Real-World Super-Resolution
    Dhruv Patel*, Abhinav Jain*, Simran Bawkar, Manav Khorasiya, Kalpesh Prajapati, Kishor Upla, Kiran Raja, Raghavendra Ramachandra, Christoph Busch.
    7th International Conference on Computer Vision & Image Processing (CVIP) 2022.
    PDF Code Website

    Design of an Autonomous Agricultural Robot for Real-Time Weed Detection using CNN.
    Dhruv Patel*, Meet Gandhi*, Shankaranarayanan H.* and Anand Darji.
    AVES 2021 conference
    PDF Code Website

    Projects

    .js-id-Self
    All Deep Learning Computer Vision Robot Manipulation Autonomous Driving SLAM Other

    EgoMimic: Scaling Imitation Learning via Egocentric Video

    End-to-end robot learning for generalizable bimanual robot manipulation from embodied human data

    Asia-Pacific Robotics Contest 2018 & 2019

    Autonomous Navigation for OmniDrive and Quadruped robots

    Behavior Cloning and Dynamics Models for Robot Manipulation

    MLP, RNN, Diffusion policy variants and learning dynamics models in Robomimic

    Vision-Language Models for Dense Feedback Reward

    VLMs for Natural Language Human Feedback

    UAV-based Assessment of Civil Structures

    Automated building inspection using the aerial images captured using UAV.

    Obstacle Avoidance for UAV

    Predicting an obstacle-free patch for high level control commands

    Fytbuddy: A real-time gym fitness trainer

    A web app-based e-trainer using a flask web server and a Deep Learning-based model for posture correction

    Autonomous Agricultural Robot

    AGRIBOT to solve crop weed classification problem

    RFID System

    Identification system using RFID reader, LCD display and Atmel AVR microcontroller.

    Image Super-Resolution

    A triplet loss-based optimization framework for Image Super-Resolution

    Mapping for level-5 Autonomy

    Improved point cloud registration and mapping using semantic ICP

    Object Detection in Adverse weather setting

    Gated Differentiable Image Processing (GDIP), a domain-agnostic architecture for object detection in adverse conditions.

    Implementation of Path Searching/Tracking algorithms

    Implemented path search/track algorithms like Pure Pursuit, Djikstra, A-star etc.

    Teaching

    Graduate Teaching Assistant
  • Georgia Tech CS 6476: Computer Vision (grad-level) (Fall 2024)
  • Georgia Tech CS 6476: Computer Vision (undergrad-level), Georgia Tech (Spring 2024)
  • Georgia Tech CS 6476: Computer Vision (grad-level), Georgia Tech (Fall 2023)

    • Featured

    • UAV-based Visual Remote Sensing for Automated Building Inspection (UVRSABI)
      • Spotlight paper presentation at the CVCIE Workshop at ECCV 2022
      • Inaugurated by Central Road Research Institute to deploy in Telangana, India (Sept 2022)
    • AGRIBOT got funded under TEQIP-III program by Govt. of India, and we also presented at the open-source ROS Agriculture community meet. [YouTube]
    • Secured 12th and 13th rank in Asia-Pacific Robot Contest - RoboCon 2018 and 2019 respectively, among 100-plus universities. [RoboCon2019 YouTube] [RoboCon2018 YouTube]
    • Best Working Model - Stirling Engine at the National Science Day Celebrations, Physical Research Laboratory (PRL), India, during 12th grade.