Skip to content

Diffusion Policy seems to ignore force–torque (FT) inputs — how do I make force matter? #156

@manadhruvil

Description

@manadhruvil

Hey everyone,

I’m training a Diffusion Policy for a task that requires active force feedback and correction, and I’m running into an issue.

When I include force–torque (FT) data in the low-dim observations (concatenated with end-effector position and velocity) alongside two RGB images, the policy seems to ignore the FT signals during inference. I’ve tested multiple datasets, training runs and inference runs :

Inference : The policy performs well and executes task properly.

Behavioral checks:

Zero-Force test: zeroing FT inputs leaves performance unchanged (policy still completes the task) → suggests the policy largely ignores FT.

High-Force test: injecting large FT values changes behavior drastically and the robot stops trying the task → FT is “seen” but not used in a helpful way.

Setup details:
Controller: Position Controller via UFactory XArm API
policy input : two RGB cameras + low-dimensional state (end-effector pose/velocity + FT).
Policy output: absolute Cartesian actions [X, Y, Z, Roll, Pitch, Yaw]
models used : raw diffusion policy with and without imagenet weights.

Question:

What’s the most effective way to increase the influence of FT during training so the policy actually uses it at inference?

Would be cool to have :

  1. Pointers, papers, or resources where similar problem can be found.
  2. Practical tips (architectural or training-time) that made FT signals matter in your setups.

If anyone wants to discuss this whole issue further, please feel free to reach out to me.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions