INITIALIZING NEURAL CORE

> MOUNTING SENSOR ARRAY ................ OK

> CALIBRATING IMU ..................... OK

> SPINNING UP LIDAR .................... OK

> LOADING ROS2 WORKSPACE ............... OK

> STARTING SLAM PIPELINE ............... OK

> ESTABLISHING TELEMETRY LINK .......... OK

> POWERING DRIVE MOTORS ............... OK

SYSTEM ONLINE

STATUS: ONLINE | MODE: AUTONOMOUS | LAT 17.3850°N  LON 78.4867°E

< AUTONOMOUS SYSTEMS ENGINEER />

BUILDING MACHINES THAT THINK

>

0 YEARS ROS2
0 ROBOTS BUILT
0 PUBLIC RELEASES
0 ROS PACKAGES

01 ABOUT

// SYSTEM PROFILE

unit:~$ core_dump --profile

root@robot:~$ ./init --role roboticist

> Loading profile ... done

> NAME : HARSH BHARGAV

> FOCUS : SLAM / PATH PLANNING / CONTROL

> STACK : ROS2 · C++ · PYTHON · GAZEBO

> MODALITY : PERCEPTION → NAV → ACTUATION

> STATUS : READY FOR DEPLOYMENT

 

I design autonomous systems that perceive their world, plan

their path, and move with intent. From indoor SLAM pipelines

to outdoor GPS-denied navigation on ArduPilot UAVs, I turn

sensor streams into decisions.

 

> PRESS_SKILL_MATRIX ▮

FULL-STACK ROBOTICS

I bridge the gap between raw silicon and autonomous behavior — writing drivers, fusing sensors, solving the localization problem, and closing the loop with motion control.

PERCEPTION

Vision + LiDAR + IMU fusion. SLAM, VIO, and semantic understanding that map the world into a model the robot can trust.

PLANNING

A*, RRT*, and model-predictive controllers that choose paths under uncertainty — fast, safe, and real-time.

ACTUATION

PID and cascaded controllers on real hardware — brushed motors, ESCs, servo joints — with safety limits that never quit.

02 SKILL MATRIX

// CAPABILITY REPORT

01

PERCEPTION

ORB-SLAM30%
LiDAR SLAM (LOAM)0%
Visual-Inertial Odometry0%
OpenCV / Sensor Fusion0%
02

NAVIGATION

ROS2 Nav20%
Path Planning (A*, RRT*)0%
ArduPilot / MAVLink0%
Kalman / EKF Filters0%
03

CONTROL

PID / Cascaded Control0%
MPC / LQR0%
Simulation (Gazebo)0%
Embedded C / Firmware0%
C++
PYTHON
ROS2
PCL
EIGEN
PYTORCH
DOCKER
LINUX

03 SYSTEMS BUILT

// DEPLOYED PAYLOADS

DEPLOYED PRJ-001
SLAM::ACTIVE

ORB-SLAM3 INTEGRATION FOR UAV

Monocular + inertial SLAM ported to a custom ROS2 driver on an ArduPilot quad, enabling GPS-denied state estimation in indoor warehouses.

C++ROS2ORB-SLAM3ArduPilot
IN PROGRESS PRJ-002
NAV2::PLANNING

AUTONOMOUS MOWER WITH NAV2

Full-stack outdoor robot running ROS2 Nav2 — costmap-based global and local planners, recovery behaviors, and EKF-fused odometry for 4-hour missions.

ROS2Nav2EKFGazebo
RESEARCH PRJ-003
VIO::TRACKING

VISUAL-INERTIAL ODOMETRY PIPELINE

Kalibr-calibrated camera–IMU rig with tightly-coupled VIO, evaluated against ground truth on TUM/EuRoC-style trajectories for drift characterization.

KalibrVIOEigenC++

04 ROBOT ARM LAB

// LIVE KINEMATICS SIMULATOR

FK::COMPUTING
EE: x=0.00 y=0.00 z=0.00
JOINT CONTROLLER MANUAL
BASE YAW
SHOULDER
ELBOW
WRIST
GRIPPER OPEN

> Drag sliders to command joints

05 TRAJECTORY LOG

// DEPLOYMENT HISTORY

2025 — PRESENT

ROS2 / SLAM RESEARCH ASSOCIATE

Building visual-inertial SLAM systems on ArduPilot UAVs; benchmarked drift at 0.6% over 1.2 km indoor loops.

C++ORB-SLAM3ArduPilot
2024 — 2025

ROBOTICS SOFTWARE ENGINEER

Shipped Nav2-based navigation stack for an autonomous mower; cut mapping time 40% via optimized costmap layers.

ROS2Nav2Gazebo
2023 — 2024

MECHATRONICS INTERN

Designed PID controllers and telemetry dashboards for 6-DOF manipulator arms; reduced settling time by 35%.

PIDEmbedded CPython
2022 — 2023

COMPETITION ROBOTICS LEAD

Led a 6-member team to a national win; designed swerve-drive kinematics and vision-based gate detection.

ROSOpenCVKinematics

06 OPEN COMM LINK

// ESTABLISH CONTACT