Daniel Seo 서다니엘
or hold R

Teaching a robotto cross the road.

Portrait of Daniel Seo in round glasses and a charcoal sweatshirt in a robotics workshop

Daniel SeoPerception lead, Gilmok Robotics, Seoul

I build the vision system of a sidewalk delivery robot: stereo depth, detection and tracking, so it can read a street the way people do and cross when it is safe.

Gilmok's white six-wheeled delivery robot waiting at a zebra crossing on a wet Seoul street at blue hour, people walking past
Euljiro, Seoul. Blue hour, after rain.STEREO 30 HZ · LIDAR 10 HZ · 5 TRACKS · LATENCY 41 MSSituation: the crossing
  • What the robot doesIt reads each person at the kerb and predicts where they will be in the next three seconds. It waits for a gap in people, not for an empty road.
  • What changedHesitations at crossings fell from 1 in 9 to 1 in 40 crossings after intent prediction shipped in 2024.
  • Rule it never breaksBelow 0.8 confidence at a crossing it waits, and a remote operator can take over at any time.
  • FiguresFrom field logs.

A scooter left across the kerb ramp.

Shared scooters get parked wherever the ride ends. Seen flat, the ramp looks blocked. In depth, there is often a gap the robot can use.

Two shared electric scooters parked across a kerb ramp on a Seoul sidewalk, the delivery robot approaching
Seongsu-dong, Seoul. Weekday morning.DEPTH 0.4 TO 18 M · FREE SPACE MAP 5 CM CELLSSituation: the blocked ramp
  • What the robot doesBuilds a free-space map from stereo depth and finds the 66 cm it needs to pass. If there is no gap, it waits and asks a remote operator.
  • What changedRemote help requests per 100 km fell from 9.1 to 2.4 once free space replaced flat detection boxes.

Puddles are not holes.

At night, wet asphalt mirrors every shop sign. Stereo depth used to read those reflections as holes a metre deep, and the robot stopped for puddles.

A narrow Seoul alley at night in the rain, neon signs reflected in puddles, the delivery robot rolling through
Euljiro alley, Seoul. 22:10, rain.REFLECTIONS REJECTED 14 · UMBRELLA SPLIT 1Situation: night glare
  • What the robot doesChecks stereo depth against lidar returns and the ground plane. When they disagree on flat ground, the ground wins.
  • What changedFalse stops at night fell 71 percent across the 2025 rainy season.
  • Also fixedUmbrellas used to merge two walkers into one track; the tracker now splits them by what it sees below the umbrella line.
The robot's stereo camera bar alone on black: two round lenses and a small infrared emitter, a ribbon cable trailing off
Stereo bar S2, 12 cm baseline

What it still cannot do

It cannot read a police officer's hand signals. At road works and accidents the robot stops, says so on its screen, and a person drives it remotely until it is clear.

I build the robot's eyes, then I go out and check them.

Daniel crouching on a Seoul sidewalk at dusk, holding a checkerboard calibration target in front of the robot's cameras while watching a laptop on the pavement
Morning calibration, on the kerb.CALIBRATION PASS · 4 MIN 12 S · REPROJECTION 0.18 PXWork: calibration

I lead perception at Gilmok Robotics in Seoul, a team of five. Our stack is called Nunchi, the Korean word for reading a room, because that is the job: read a street and act politely in it.

Calibration used to take an hour in the lab. Now the robot recalibrates on the kerb every morning in about four minutes, against a checkerboard and a lidar target, and leaves only when reprojection error is under 0.3 px.

Now: training depth on our own rain recordings from Seoul, at night and in the wet. Tools: PyTorch for training, TensorRT on the robot, ROS 2 for the plumbing.

Path

  • 2021 to nowPerception leadGilmok Robotics, Seoul
  • 2018 to 2021Computer vision engineerSaebyeok Mobility, Pangyo
  • 2018MS, RoboticsKAIST
  • 2016BS, Electrical EngineeringHanyang University

Talks and writing

  • 2025Puddles are not holesTalk on night depth for sidewalk robots
  • 2024Nunchi: reading pedestrians at crossingsWorkshop paper
  • 2024Calibrating on the kerbTalk and write-up

Build a question.

Pick a topic, what you want to know and a detail, or type it. The answer lands as a row on the robot's spec sheet and marks the part it concerns.

1 · TOPIC
2 · WHAT
3 · DETAIL

Answers from Daniel's notes. Scripted replies, not Daniel.

PART OR MODELANSWER
  1. No rows yet. Build a question above, or try “What changed at crossings?”
Gilmok G3 delivery robot on black: off-white body, red light strip, stereo bar at the front, a camera mast on top and six black wheels
Gilmok G3, studioNo part selected

Hiring conversations, or a lab visit.

The team is hiring a perception engineer and a data engineer in Seoul. Lab visits are on Thursday afternoons in Seongsu-dong, where you can watch the morning recordings and ride along on a test loop.

What would you like?
Replies within two working days.

REQUEST GM-0000 LOGGED

Thank you.

Daniel will reply within two working days.