> INITIALIZING SYSTEM...

> LOADING AUTONOMY MODULES...

> CALIBRATING SENSORS...

> ESTABLISHING NEURAL LINK...

> SYSTEM READY

SYSTEM ONLINE // URBANA, IL

AUTONOMY
ARCHITECT

> CURRENT_TASK: Master's_Robotics_UIUC

> FOCUS: VLA Models, Cross-Embodiment Learning, Safe Trajectory Optimization

> STATUS: Developing Intelligent Systems

01

SYSTEM_SPECIFICATIONS

AUTONOMY_STACK

ROS 2 / Nav2 SLAM (VINS-Fusion, ORB-SLAM3) Motion Planning (MoveIt, OMPL, RRT*) Trajectory Optimization (ProxQP, CHOMP) A* Planning / Stanley Control Sensor Fusion (Kalman Filters) Control Barrier Functions (CBF)

AI_&_PERCEPTION

VLA Models Vision-Language Models (GPT-4o) Vision Transformers (ViT, Cross-Attention) Transformers (CLIP, Whisper) Computer Vision (OpenCV, SAM, YOLO) Deep Learning (PyTorch, TensorFlow) Contrastive Learning Reinforcement Learning (PPO) 6D Pose Estimation Point Cloud Processing

EMBEDDED_&_HW

Embedded C / C++ / Rust STM32 / ESP32 Firmware PCB Design (KiCad, Altium) Comms (I2C, SPI, UART, CAN, MAVLink) Fusion 360 / SolidWorks
02

MISSION_LOGS

RUNTIME_HISTORY (WORK)

May 2024 - May 2025

Embedded Engineering Intern

Dimension Six Technologies, Mumbai
  • Engineered firmware with battery management and regenerative braking, extending vehicle range by 40%
  • Designed a 4-layer PCB in KiCad for a custom ESC, optimizing power stage layout to reduce losses by 15% under peak load.
  • Deployed IoT stack on ESP32S3 with RFID authentication, enabling remote monitoring and contactless payments over MQTT.
Jan 2024 - Jun 2024

Robotics Research Intern

IIT Bombay
  • Built SLAM-based autonomous navigation stack with path planning, achieving 95% accuracy in dynamic indoor environments.
  • Fused IMU, GPS, and RGB-D camera data via Extended Kalman Filter, improving localization accuracy by 20%.
  • Deployed YOLOv3 for real-time human detection and designed an adaptive gait controller for robust stair-climbing traversal.

KERNEL_VERSIONS (EDUCATION)

Aug 2025 - Present

Master's in Autonomy and Robotics

University of Illinois Urbana-Champaign
  • Coursework: Humanoid Robots, Robot Planning, Control & Dynamics, Autonomous Systems, Computer Vision, Deep Learning
  • Key Lab Work: Working with humanoids, manipulators and GEM autonomous platforms.
Dec 2021 - Jun 2025

B.Tech. in Electronics & Telecom

Sardar Patel Institute of Technology
  • Specialization in Embedded Systems and Robotics.
  • Minors in Management (S.P. Jain Institute).
03

PROJECT_MODULES

Terrain-Aware Navigation

Elevation MappingROS2

Developed a perception pipeline converting depth clouds to elevation maps for quadruped footstep placement.

RL Locomotion + Safety

PPOControl Barrier Functions

Trained terrain-adaptive locomotion with PPO and integrated CBF as a real-time safety filter. Achieved zero-fall locomotion with 99% unsafe action rejection.

Quadruped Locomotion (RL)

PPOIsaac GymPython

Trained ANYmal quadruped policies using Proximal Policy Optimization. Achieved robust traversal on irregular terrain with 0-fall safety constraints.

VIO + Footstep Planning

ROS2VINS-FusionNav2

Fused Visual-Inertial Odometry with footstep planning. Enabled autonomous navigation in GPS-denied environments with <10cm drift.

EMG Prosthetic Arm Demo

EMG-Controlled Prosthetic Arm

ESP32 TinyML Fusion 360 XGBoost

Built a 5-DOF prosthetic arm controlled via EMG signals. Deployed real-time gesture classification on ESP32 using XGBoost, achieving 96% accuracy.

04

VISION_PROTOCOL

vision.md

> # WHAT I'M BUILDING TOWARD

Robots that learn tasks from watching humans, then execute them safely in the real world.


> # CURRENT FOCUS

Building cross-embodiment learning systems that enable vision-language-action models to transfer across robot morphologies. Combining trajectory optimization safety layers with kinematic-conditioned visual representations to bridge internet-scale knowledge and physical manipulation.


> # THE BIGGER PICTURE

General-purpose robots need a skill layer - modular, verifiable behaviors that can be composed, transferred, and deployed across platforms. I'm focused on making that layer learnable from real-world data, morphology-agnostic, and safe by construction, using physics-based optimization and control-theoretic safety guarantees.

05

ESTABLISH_UPLINK

EMAIL_TRANSMISSION LINKEDIN_NETWORK GITHUB_REPO