Projects

GateNet — Vision-Based Gate Segmentation for Drone Racing

A compact U-Net that replaces privileged simulator segmentation with RGB-only gate prediction, closing the sim-to-real perception gap for DreamerV3 drone racing. Achieves 0.93 mean IoU and 1.0 median IoU on held-out validation.

Computer Vision Sim-to-Real Deep Learning Reinforcement Learning Aerial Robotics PyTorch

View on GitHub ↗

active ▶ Video

Isaac Drone Racer 2

Modernized autonomous drone racing RL framework for Isaac Sim 5.1 and Isaac Lab 2.3.2. Supports vision-based gate tracking, semantic segmentation, swarm racing with multiple agents, and multi-objective reward functions for high-speed navigation.

Reinforcement Learning Isaac Sim Aerial Robotics Vision-Based Control Swarm Robotics Autonomous Racing

View on GitHub ↗

completed ▶ Video

Adaptive Quaternion Sliding Mode Control for Nano Quadrotors

A globally stable, computationally efficient adaptive SMC framework for nano quadrotors. Validated in 130+ hardware flight trials on a 32 g Crazyflie, enabling flip maneuvers and 3g accelerations.

Robust Control Quadrotor Embedded Systems

View on GitHub ↗

completed

Local LLM-Driven 6-DoF Robotic Manipulation with ROS2 and 3D Vision

A ROS2-based robotic manipulation pipeline integrating a locally deployed LLM via Ollama with 3D vision perception to interpret natural-language commands, reason about object-level tasks, and generate executable motion commands for a robotic arm.

Robot Learning ROS2 LLM 3D Vision Manipulation

completed

Dual-Arm Space Robotic Manipulation with Deep Reinforcement Learning

A PyBullet-based dual-arm robotic manipulation framework using PPO and SAC for coordinated target reaching, collision avoidance, and noisy-observation robustness, with task-specific reward functions and multi-objective evaluation metrics.

Reinforcement Learning Manipulation PyBullet PPO SAC Space Robotics

completed

Photorealistic SITL Pipeline for Spatial AI and Autonomous Navigation

Unreal Engine / AirSim / PX4 SITL simulation infrastructure for autonomous UAV navigation, integrating visual-inertial SLAM (ORB-SLAM3) and sensor-realistic simulation for evaluating perception, localization, and control algorithms in GPS-denied environments.

Simulation AirSim SLAM PX4 Spatial AI UAV

completed ▶ Video

LiDAR-Inertial Mapping with FAST-LIO2 and Livox Avia

ROS 2 Humble workspace integrating the Livox Avia LiDAR with FAST-LIO2 for real-time LiDAR-inertial odometry and dense 3D mapping. Fuses LiDAR and IMU data via an incremental k-d tree for efficient, drift-resilient state estimation on Ubuntu 22.04.

ROS 2 LiDAR SLAM State Estimation 3D Mapping Autonomous Robotics

View on GitHub ↗

completed

Nonlinear MPC for Tiltrotor Quadrotors

Model predictive control with feasible control allocation for tiltrotor quadrotors, enabling smooth transitions between multirotor and fixed-wing flight modes.

MPC Tiltrotor Optimization