Piyush Khandelwal
Senior Staff Research Scientist at SonyAI
Austin, Texas, United States
Summary
👤
Senior🎓
Top SchoolPiyush Khandelwal is a Senior Staff Research Scientist with 14 years of experience specializing in autonomous mobile robots, probabilistic planning, and continual learning systems. Based in Austin, he has progressed through research roles at Cogitai and SonyAI, building end-to-end robot prototypes and production-ready algorithms that let agents learn continuously from their environment. His work spans simulation and hardware—contributing to Gazebo ROS packages to improve namespace and plugin integration—demonstrating deep practical knowledge of robot simulation stacks. Piyush combines rigorous academic training (PhD/MS from UT Austin, BTech from IIT Roorkee) with applied industry impact, including a deployed HVAC control algorithm at Nest. He excels at bridging simulation, embedded platforms, and cloud experimentation to move learning algorithms from lab demos to real systems. Colleagues turn to him for designing scalable infrastructures that let intelligent robots improve performance over time.
14 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (PhD) Computer Science, Doctor of Philosophy (PhD) Computer Science at The University of Texas at AustinIndian Institute of Technology Roorkee
English, Hindi
Github Skills (10)
simulations10
robotics-simulation10
c-language10
gazebosim10
cprogramming-language10
robot-simulator10
ros10
gazebo-simulator10
urdf8
sdf8
Programming languages (9)
Github contributions (5)
ros-simulation/gazebo_ros_pkgs
Jun 2013 - Aug 2013
Wrappers, tools and additional API's for using ROS with Gazebo
Role in this project:
Back-end Developer
Back-end DeveloperContributions:18 commits, 1 comment, 1 issue in 1 month
Contributions summary:Piyush focused on enhancing the Gazebo ROS packages by implementing functionalities related to robot namespaces within SDF and URDF models, enabling better plugin integration. Their work included modifying the `gazebo_ros_api_plugin.cpp` file to add robot namespace support and incorporating a differential drive plugin, which demonstrates an understanding of robotics simulation. The contributions involve working with Gazebo plugins and ROS, which are core technologies for robot simulation.
gazeboapiroboticsignitionrobotics-simulation
utexas-bwi/eband_local_planner
Dec 2012 - Sep 2017
ROS Local planner based on the eband approach. Based on the original implementation by Christian Connette and Bhaskara Marathi. This local planner has been adapted primarily for differential drive robots, but still supports the original holonomic drive controls.
Contributions:73 commits, 3 PRs, 8 pushes in 4 years 10 months
roboticsmarathiadaptedapproachdifferential-drive
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.