DEV
GOTI
The real world doesn't come with a manual. I build robots that figure it out anyway. Systems that perceive, plan, and navigate environments that weren't designed to be easy.
Get to know me
About Me
Dev Goti

I'm a Robotics Engineer working on autonomous systems. How robots perceive their environment, estimate where they are, plan where to go, and execute reliably when things don't go as planned.

At Texas A&M, my work spans SLAM pipelines, RL based planners for drones and robotic arms, LiDAR camera fusion, and safe autonomous navigation. The thread connecting all of it is the same question: how do you build a system that holds up outside the lab?

Before grad school, I spent four years at NIT Karnataka building robots for ABU Robocon. I started as a programmer on the electronics team and finished as Vice Captain, leading a 40 person team through a full competition cycle. That experience taught me that the gap between a robot that works and one that doesn't is almost never the algorithm.

When I'm away from the lab, I'm usually on a trail. I trek, I photograph, and I document places. The same instinct to observe carefully and bring something back, just applied to mountains instead of sensor data.

Career Journey
Work Experience
Summer Research Intern
May 2024 – Jul 2024
Indian Institute of Space Science and Technology  ·  Thiruvananthapuram, India
  • Received Indian Academy of Science Summer Research Fellowship.
  • Developed a PPO-based DRL trajectory planner for a 7-DOF robotic arm enabling collision-aware, smooth goal-directed motion in continuous state-action spaces.
  • Evaluated learned policies using reward convergence, target accuracy, and trajectory smoothness metrics.
Portfolio
Featured Projects
A showcase of robotics and AI systems demonstrating expertise in perception, planning, and autonomous navigation.
LiDAR Fusion
LiDAR–Camera Fusion for 3D Obstacle Detection
Fusion pipeline using RANSAC, voxel downsampling, and DBSCAN on KITTI. Extrinsic calibration with IoU-based 3D bounding box evaluation.
LiDARRANSACDBSCAN
View Project
Autonomous Navigation
Autonomous Navigation using Deep RL
TD3-based DRL system integrating LiDAR and ROS 2 for real-time obstacle avoidance and goal-directed mobile robot navigation.
TD3ROS 2LiDAR
View Project
Visual SLAM
Robust Outlier Rejection in Visual SLAM
GNC-TLS loop closure outlier rejection achieving 94% trajectory error reduction and 290× faster runtime vs RANSAC on KITTI dataset.
SLAMGNC-TLSKITTIRANSAC
View Project
CBF Quadrotor
CBF for Safe RL Quadrotor Control
Motor-level CBF safety filters reducing safety violations by 2.4× across PPO and adaptive policies in high-fidelity drone simulations.
CBFSafe RLPPOQuadrotor
View Project
Image Editing
Spatially-Aware Image Editing
VLM-orchestrated pipeline using DINO+SAM grounding. 99.3% intent accuracy and SSIM 0.976 via hybrid LaMa + SDXL blending.
VLMSAMInpaintingSDXL
View Project
PRM Nav
PRM-Nav
PRM path planner with k-NN construction and Dijkstra search. Includes path smoothing, unreachable goal handling, and RViz visualization.
ROS 2PRMDijkstraRViz
View Project
7DOF Arm
7DOF Robotic Arm Trajectory Planning
PPO-based RL for collision-aware planning of Kinova JACO2 arm. Evaluated via reward convergence and trajectory smoothness in Gazebo.
PPOROSGazebo
View Project
Person Tracking
LiDAR-Based Person Detection and Tracking
ROS2 system detecting people from 2D laser scans, clustering LiDAR points into human-sized shapes and tracking them with consistent IDs and RViz trails.
ROS 2LiDARTrackingRViz
View Project
Low Light
Low Light Image Enhancement
MIRNet-based enhancement deployed on Arduino Nano 33 BLE Sense for edge AI applications in resource-constrained environments.
MIRNetEdge AIArduino
View Project
Segment Visitation
Segment Visitation Controller
Hybrid path planning combining heuristic strategies with local 2-opt optimization for efficient multi-segment navigation.
Heuristics2-optPlanning
View Project
Technical Arsenal
Skills & Technologies
Languages
Python
C++
C
CUDA
MATLAB
Tools & Frameworks
ROS/ROS2
Gazebo
Isaac Sim
RViz
Docker
Linux
Git
Simulink
VS Code
Jupyter
ML & AI
PyTorch
TensorFlow
Keras
OpenCV
Scikit-learn
NumPy
Pandas
Matplotlib
Gymnasium
Stable Baselines
Open3D
PCL
Core Expertise
SLAM
Motion Planning
Sensor Fusion
State Estimation
Trajectory Opt.
Autonomy
Localization
Safe RL
Sim2Real
Kalman Filter
Object Detection
Academic Background
Education
Texas A&M University
Aug 2025 – May 2027
College Station, Texas, USA
Master of Science in Electrical Engineering  ·  GPA: 4.0/4.0
Coursework - Robotics & Spatial Intelligence, Visual Navigation and Foundation Models of Autonomy, Computer Vision and Perception, Reinforcement Learning
National Institute of Technology Karnataka, Surathkal
Dec 2021 – May 2025
Mangalore, Karnataka, India
B.Tech in Electrical & Electronics Engineering  ·  GPA: 8.70/10  ·  Minor in Management
Undergraduate Researcher — REHAB Group, Dept of EEE
Vice Captain — CSD Robocon NITK
Achievements
Competitions
ABU Robocon
CSD Robocon NITK  ·  Mangalore, India  ·  Visit Team Website →
Started as electronics and programming systems member, later mentored juniors and coordinated across subsystems. Stepped up as Vice Captain, guiding a 40+ member team to the ABU Robocon stage.
Get in Touch
Contact
Open to research collaborations, robotics roles, and interesting problems. Feel free to reach out.