boot sequence
[OK] Loading kernel modules...
bash — sanket@portfolio:~

01. About Me

Building the future, one system at a time

Hello! I'm Sanket, an engineer interested in the intersection of technology, mathematics and physics. What began as curiosity about how things work has grown into a drive to build systems that can move and think in the real world, blending control theory, physics, reinforcement learning and hardware design.

I've worked on non-GPS navigation for high-altitude UAVs and on both electronics and software for bipedal robots. I enjoy open-source collaboration to tackle challenges from space exploration to terrestrial automation.

I also dabble in high-energy particle and quantum physics; after all, who doesn't like questioning reality before breakfast?

dependencies
  • C++ / Python ★★★★★
  • ROS / ROS2 ★★★★★
  • Isaac Sim ★★★★☆
  • Reinforcement Learning ★★★★☆
  • Control Systems (MPC, PINN) ★★★★☆
  • PyTorch / OpenCV ★★★★☆
  • Ardupilot / PX4 ★★★★★
  • Embedded (STM32, RTOS) ★★★★☆

02. Experience

My professional journey

Head of Technology

@ Summon

Mar 2025 — Present

Leading electronics and software stack for humanoid robotics in the cleaning industry.

  • Working on Isaac Sim, Isaac Lab, VLA models, and RL-based controllers (PINN)
  • Developing real-time AI-assisted long-range teleoperation systems
  • Implementing genetic algorithms, H-GAIL, Actor-Critic, VLAs, ACT for bipedal legged control
  • Designing electrical circuits and power management for bipedal humanoids
  • Bimanual mobile manipulation for cleaning applications

Senior Control Engineer

@ Airbotix Technology

Jul 2024 — Mar 2025

Developed navigation and controls stack for Underwater AUV under IdEX project.

  • Implemented PINN-based MPC, behavior trees, and various controllers
  • Built state estimators for underwater vehicle localization
  • Leading computer vision, controls, and mathematical modeling for High Altitude Aerostat

Firmware Engineer

@ Airbotix Technology

Jan 2024 — Jun 2024

Led software development for collision-free swarm algorithms for drone show stack.

  • Modified and developed Ardupilot codebase for company requirements
  • Worked on perception, trajectory planning, and control designs
  • Developed long-range communication and antenna modeling for one-to-multi communication

GSoC Contributor

@ Ardupilot

May 2024 — Aug 2024

Developed High Altitude Non-GPS Position Estimation algorithm for UAVs.

  • Designed transformer and optimization-based localization and mapping algorithms
  • Developed custom computer vision and deep learning solutions
  • Technologies: C++, Python, OpenCV, PyTorch, Lua, Embedded software

Technical Advisor

@ CUAV Tech

Sep 2023 — Present

Developed a low-cost precision landing solution using monocular camera and offboard computer approach.

  • Deployed image processing, PyMavlink, and autonomous capabilities on UAV
  • Implemented vision-based landing algorithms for high-accuracy landings

Intern

@ General Aeronautics

Dec 2022 — Sep 2023

Developing terrain following algorithm for Agriculture UAVs.

  • Designed simulated worlds and multiple terrain models
  • Used advanced control systems and advanced robotics
  • Deployed image processing, control systems and autonomous capability on UAV

GSoC Contributor

@ Ardupilot

May 2022 — Sep 2022

Updated ROS integration for Non-GPS navigation and autonomous path-planning.

  • Developed LiDAR-equipped quadrotor with Ardupilot FCU
  • Updated base code for Cartographer SLAM tuning parameters and control algorithms
  • Integrated offboard object avoidance with ArduPilot Auto mode

03. Projects

Some things I've built

space-station-os

Space Station OS — GNC & AOCS

Contributions to the Guidance, Navigation, and Control (GNC) and Attitude & Orbit Control Systems (AOCS) for an open-source space station operating system. Designed behavior tree architecture for autonomous operations and GNC/AOCS physics backend with SSOS SITL.

C++ ROS2 GNC/AOCS Behavior Trees Simulation
humanoid-control

Humanoid Control & Teleoperation

Comprehensive software and hardware stack for a bipedal humanoid. Real-time AI-assisted long-range teleoperation, advanced control systems (RL, PINN, VLAs), and bimanual mobile manipulation, tested in Isaac Sim and deployed on hardware.

Isaac Sim RL (PPO, SAC) PINN ROS2 VLA Models
non-gps-nav

High-Altitude Non-GPS Navigation

GSoC project for Ardupilot enabling UAV position estimation at high altitudes without GPS. Leverages downward-facing camera, fusing transformer-based Visual Positioning System (VPS) with Visual-Inertial Odometry (VIO).

C++ Python OpenCV PyTorch UAVs
drone-swarm

Drone Swarm Show System

Designed and implemented ArduPilot-based synchronized drone swarm control and long-range wireless communications for drone light shows.

Ardupilot Swarm Control Wireless Comms
isro-cansat

ISRO CanSat

National finalist entry for ISRO CANSAT competition. Developed satellite with active 2-axis attitude stabilization using reaction wheels and LQR controllers.

Control Systems LQR Embedded
precision-landing

Precision Landing System

Monocular vision-based landing system for UAVs using PyMavlink, grid map, and OpenCV for high-accuracy landings.

OpenCV PyMavlink Computer Vision
sahaya-humanoid

Sahaya Humanoid

ROS-based humanoid robot for elderly care, capable of autonomously mapping and navigating homes, providing medicine and water. Developed perception software and 3D printed face.

ROS Navigation 3D Printing
mini-quadruped

Mini Quadruped

4-legged autonomous robot with kinematic and control model written from scratch on indigenous microcontroller (Vega processor). Capable of walking and AI interaction.

Kinematics Embedded Control Systems

04. Achievements

Recognition and competitions

🏆

ISRO CANSAT 2023

National Finalist for developing a CANSAT with active attitude stabilisation using reaction wheels and LQR controllers.

🥇

Microsoft Imagine Cup 2023

India Regional Finalist for developing a blockchain-based drone aggregator platform.

🏅

Smart India Hackathon 2022

Led a team of 6 to National Finals organized by Ministry of Education, Government of India.

🥈

eYRC Robotics Competition

National Level Runner-up in IIT Bombay competition for custom flight controller and ROS-based delivery drone.

🏆

Tekathon'22

Winner at Chandigarh University competition for Sahaya humanoid project.

🌍

International Hackathons

1st Rank winner in Quellie Hacks, StemWarriorHacks, RoboHacks, and HackKu (hardware and overall categories).

05. Education

Academic background

Bachelor of Engineering in Mechatronics

Chandigarh University

Participated and won multiple recognized national and international robotics competitions. Served as IEEE RAS Treasurer.

CGPA: 8.12/10 2020 — 2024

06. Mentorship

Giving back to the community

Google Summer of Code & Ardupilot

Guiding the Next Generation of Developers

Actively contributing and mentoring contributors in the Ardupilot community, focusing on projects like non-GPS absolute LiDAR positioning and the implementation of Software-in-the-Loop (SITL) with Reinforcement Learning for advanced autonomous systems.

07. Publications

Peer-reviewed research and papers under review

Under Review

ModelFabric: Explainability-Guided Selective Shielding for Secure Vision-Language Action Models on Edge Robots

Xiaolong Wu, Sanket Sharma, Sarah Pendhari, Xiangyu Shi, Min Xu
ICML 2026 International Conference on Machine Learning Carnegie Mellon University
Vision-Language Models Edge Robotics AI Safety
Under Review

NGPS: GPS-Denied Aerial Geo-Localization and 2.5D Reconstruction via Deep Satellite Image Matching and Multi-Rate Sensor Fusion

Sanket Sharma, et al.
IROS 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems
Geo-Localization Sensor Fusion 3D Reconstruction

08. Talks & Presentations

Conference presentations and invited talks

High Altitude Non-GPS Position Estimation

Ardupilot Developer Conference 2024, Japan

Watch

Autonomous Non-GPS Control for Indoor Navigation

PX4 Developer Summit 2023, USA

Watch
bash — contact@portfolio
$ send_message --to "sanket"

I'm always seeking new challenges and opportunities to collaborate on ambitious projects. Whether you have a question, a proposal, or just want to say hello, my inbox is always open.

sharma.sanket272@gmail.com