Skip to content

After full fine-tuning, policy reaches the target but never closes the gripper #48

Description

@xiangbobo666

Summary

I full-fine-tuned LingBot-VLA on a single-task pick (cx001_select_banana) with the vision tower, QwenVL backbone, and action expert all trainable (freeze_vision_encoder=false, train_expert_only=false). Training loss and open-loop MAE look fine, but in closed-loop inference the policy reliably approaches the target object and then stalls — the end-effector hovers in a near-correct pre-grasp pose and the gripper never closes, so the pick is never completed.

Setup

  • Base: LingBot-VLA (75-D), task cx001_select_banana (dual-arm 14-D, 12 pose + 2 grippers).
  • Loss: flow-matching, chunk_size=30, lr=3.5e-5, 50k steps, 8×H100 FSDP2.
  • 14-D action zero-padded to max_action_dim=75 to keep base ckpt's action_in_proj / action_out_proj weights intact.
  • Dataset minmax-normalize on; gripper range fixed [0, 4.5].
  • Inference: VR + real robot, ODE steps 4 / 10, ckpts 50k / 100k — same symptom.

Observation

Gripper channel (idx 6 / 13, 0≈closed, ~4.5≈open) collapses to ~0 almost immediately and stops varying in any task-meaningful way, even when the arm is correctly positioned over the object:

[..., -0.013] [..., 0.987] [..., 0.000] [..., 0.019] [..., 0.000] ...

Questions

  1. For single-task fine-tuning on small data, is full unfreezing (vision + VLM + expert) actually recommended, or should freeze_vision_encoder=true be the default?
  2. Is the 14→75 zero-pad expected to be safe for the gripper dim end-to-end? With 61/75 channels permanently 0, could the loss be effectively down-weighting the 2 gripper dims and pushing them toward the dataset mean?
  3. Any known recipe / mask / loss weighting for the gripper channel to avoid this "approach-but-no-grasp" collapse?

Happy to share configs, loss curves, and a rollout video.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions