Completed
Current direction
Decision / transition
Hardware risk
Data collection
Goal
Goal
project north star
Humanoid whole-body training data on G1
Objective
Collect coordinated locomotion + manipulation demonstrations on the Unitree G1 to support future whole-body policy / VLA training.
01 · Input
Human VR motion
02 · Control
Whole-body controller
03 · Capture
Demonstration data
04 · Output
VLA / policy training
Week 1–2
Upper-body
validation · sim & real
Upper-body VR teleoperation is working
Done
- Deployed upper-body teleoperation using Meta Quest 2.
- Validated in simulation and on the real G1.
Week 3
VLA
scope expansion
Extend VLA to humanoid
Start
-
Extend VLA models from arm-centric manipulation (π-series) to humanoid whole-body control (GR00T).
Week 4
Pico 4
hardware switch
New VR device for teleoperation
Purchase done
- Meta Quest covered hands & head, but has no official leg motion tracker.
- Switched to Pico 4 + body trackers so whole-body teleoperation has full-pose input.
Week 5–6
Option A
IK upper · RL lower
Option A — IK upper body + RL lower body
Hardware risk
Method
Upper bodyIK-based joint-position control
Lower bodypretrained RL locomotion policy
- Accurate hand tracking, but unnatural motion — the lower body struggled to maintain balance during manipulation.
- Robot damage occurred during data collection runs.
Decision
Not suitable as the main data-collection method.
Week 7–8
Option B
SONIC deployment
Option B — One policy for whole-body
Current main direction
Method
PolicySONIC · pretrained whole-body motion tracking
InputVR device motion / VLA command
Outputcoordinated full-body G1 motion
Dimension
IK + RL Policy
SONIC
Hand accuracy
High
Medium
Whole-body naturalness
Low
High
Balance during manipulation
Weak
Better
Suitability for data collection
Risky
Promising
Decision
Use SONIC as the current main whole-body teleoperation direction for data collection.
Week 9
Collecting
first-person demos
First-person VLA data collection
Data collecting
- Target data: human teleoperation command + first-person visual observations.
- Goal scope: ~300 trajectories to fine-tune a locomotion + manipulation policy.
Week 10
Camera
OAK switch
New camera for humanoid VLA
Purchase done
- Onboard RealSense 435 has a narrow field of view.
- Switched to the OAK camera, used by recent egocentric humanoid VLA datasets such as EgoScale.
Week 11
Lower locked
upper-body data only
Lock lower body, collect data
Hardware risk
- Humanoid keeps warning right ankle overheating after ~5 minutes of walking.
- Workaround: lock the lower body and continue collecting upper-body manipulation data.
- New right humanoid leg has shipped from Hong Kong — ETA ~3 weeks.
Week 12
Psi0 VLA
policy deployed
Psi0 VLA policy works
Done
- Fine-tuned and deployed Psi0 VLA for upper-body manipulation on G1.
- Fully autonomous, no teleoperation — the policy drives the arms directly from on-board observations.
Milestone
First end-to-end VLA policy running on the G1 from collected demonstrations — validates the data-collection pipeline from Weeks 1–11.
Summary
Summary
timeline takeaway
Timeline summary
Takeaway
- SONIC is the main teleoperation direction — IK + RL was tested first but proved unstable and damaged the robot.
- Hardware reliability is the main constraint — a right-ankle thermal issue currently limits collection to upper-body data.
-
Psi0 VLA policy deployed — first autonomous rollout on G1 from collected demonstrations, validating the full pipeline.
End · Week 12