RGB-D 6D object pose estimation pipeline using RealSense D455, YOLOv8-seg, FoundationPose, and ROS 2.

Physical OMY-L100 to MuJoCo Franka FR3 teleoperation with Cartesian retargeting, DLS IK, and null-space control.

ACT and Diffusion Policy experiments for manipulation, from Push-T policy analysis to teleoperation-derived FR3 learning.

ROS 2 autonomous navigation and patrol system with SLAM, AMCL, Nav2, DWB/MPPI evaluation, and real-robot debugging.