Hasarindu Perera

Software Engineer, AI — Vega Innovations

• Deployed Autoware on NVIDIA AGX Orin with a Hesai XT16 LiDAR (Nebula driver).
• Built a monocular depth estimation pipeline (relative and metric) to improve point clouds for detection and mapping.
• Built a bird's-eye-view system fusing LiDAR depth, clustering, speed estimation and camera pose.
• Quadruped: LiDAR obstacle detection in a custom ROS package, so the robot stops on its own near obstacles.
• VelloPass (licence plate recognition): image enhancement research and CI/CD.

AI & Robotics Instructor (part-time) — ANKA Technologies

Classes and workshops on AI, machine learning and robotics with Python, PyTorch, TensorFlow and ROS. I guide student projects in computer vision and robot navigation.

Associate AI Engineer — Vega Innovations

• Multi-agent system for AV simulation (FLAMEGPU2, UniAD, DaveNet) and an end-to-end driving pipeline (ResNet, RegNet, BiFPN).
• Python sensor-fusion module for LiDAR, RADAR, camera, GPS and CAN data.
• Go2 quadruped: Go2 SDK + ROS 2 integration, SLAM localization with Nav2, RL control trained in Isaac Gym.
• Face recognition on Rockchip boards with RKNN; depth-based anti-spoofing cut false positives by 70%.

Intern AI Engineer — Vega Innovations

• Implemented TRPO, PPO, CPO and PCPO from scratch for safe RL in autonomous driving; experiments in CARLA and MuJoCo with TorchRL, CleanRL and OmniSafe.
• Face recognition attendance system on Raspberry Pi 4B; 98% anti-spoofing accuracy with Intel RealSense depth.
• Camera-to-BEV semantic segmentation with UNetXST (85% accuracy).

Mentee, AWS AI & ML Scholarship — Intel

Top 500 cohort. Mentored by Ali Aram, Platform Application Engineer at Intel.

Contributor — Omdena

Autism Early Detection Project with Dr. Shaista Hussain: dataset collection, literature review and experiments on neuroimaging (ABIDE I & II, fMRI and structural MRI).

Founder & Director — heartivVe (Pvt) Ltd

Built 20+ business websites and full-stack products, plus CMS-based learning platforms, mostly in Node.js and JavaScript.

Autonomous vehicle

Multi-agent simulation, an end-to-end driving pipeline and sensor fusion for Vega's autonomous vehicle. On the current car: Autoware, LiDAR integration, depth estimation and BEV perception.

Go2 quadruped

LiDAR obstacle detection as a ROS 2 package, Nav2 path planning and localization, and RL models for obstacle avoidance.

FaceRec

Face recognition with depth-based anti-spoofing that runs on cheap hardware (Raspberry Pi, Rockchip). 98% spoof detection.

Bird's-eye view

Turning camera images into semantically segmented top-down views with UNetXST, at 85% segmentation accuracy.

VegaGPT

Internal chatbot for knowledge transfer in the AI team, built on LangChain and GPT models.

Licence plate recognition

Image enhancement research to make plate recognition reliable in poor light and bad weather.