Skip to content
View jack2148's full-sized avatar

Block or report jack2148

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jack2148/README.md

Yeachan Kim

Robotics · Robot Learning · Manipulation

Robotics Engineering undergraduate at Hanyang University ERICA and undergraduate research intern at KITECH since July 2026. Current work focuses on teleoperation-based manipulation demonstrations, imitation learning, and data-efficient demonstration collection. Interested in hybrid robot-learning approaches that combine data-driven policies with robot kinematics and structured control.

Email

Current Research

1. Teleoperation & Manipulation Learning

OMY_FRANKA_TELEOP

Built a teleoperation pipeline from a physical OMY-L100 leader to a Franka FR3 in MuJoCo, including Cartesian pose retargeting, 6D-to-7DoF damped least-squares inverse kinematics, and null-space control. This is a simulation-stage FR3 system; deployment to physical FR3 hardware is not claimed.

2. Imitation Learning & Policy Analysis

dp-act-policy-study

Studying ACT and Diffusion Policy in LeRobot-based manipulation tasks, including Push-T analysis and FR3 MuJoCo experiments using teleoperation demonstrations. Current work investigates how execution strategy, trajectory coverage, and demonstration distribution affect policy performance.

The Push-T study includes a controlled 50-episode execution-strategy ablation. FR3 results are reported separately as fixed-initial-condition pilot evaluations, not as a generalization benchmark.

Research Interests

My broader research interest is in robotic manipulation architectures that separate learning-based decision making from kinematics- and control-based execution, combining data-driven policies with structured robot control.

Supporting Robotics Systems Work

rgbd-object-pose-estimation — RGB-D manipulation perception using an Intel RealSense D455, YOLOv8-seg, CAD meshes, and FoundationPose. The verified mean mask mAP50 is 0.929 across three industrial-part classes; this is a segmentation metric, not 6D-pose accuracy.

navigation_stack_lab — Real-hardware ROS 2 navigation and system integration with SLAM, EKF sensor fusion, Nav2, DWB/MPPI experiments, and person-following logic. MPPI computation and parameters were optimized to improve the control loop from approximately 5–6 Hz to a stable 20 Hz.

Selected Achievements

  • 1st Place — 2026 Creative Comprehensive Design Competition
  • Bronze Award — College of Engineering Capstone Design Competition
  • Finalist — KAIST Mobility Challenge 2026
  • Undergraduate Paper Award — ICROS 2026

Publications / Presentations

  • “Performance Comparison of DWB and MPPI Local Planners in ROS 2 Nav2 Environment” — ICROS 2026, poster, first author
  • “Multimodal Perception and Monitoring System for Indoor Security Patrol Robots” — ICROS 2026, poster, Undergraduate Paper Award

Technical Areas

ROS 2 · MuJoCo · LeRobot · ACT · Diffusion Policy · Python · C/C++ · Nav2 · SLAM · MPPI · DWB · RGB-D · YOLOv8 · FoundationPose

Pinned Loading

  1. dp-act-policy-study dp-act-policy-study Public

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

    Python 1

  2. OMY_FRANKA_TELEOP OMY_FRANKA_TELEOP Public

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

    Python 1

  3. navigation_stack_lab navigation_stack_lab Public

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

    Python 1

  4. rgbd-object-pose-estimation rgbd-object-pose-estimation Public

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

    Python 1