Does TD-MPC run on UFACTORY xArm?

Capabilities

Caveats

• Evidence is the FOWM authors' real xArm 7 experiments with their own codebase; the public FOWM repo runs only the simulated xArm tasks, and LeRobot's tdmpc port documents no real-robot use.
• The real-robot results come from offline pretraining followed by online RL finetuning with task rewards (about 20 trials per task), not from pure imitation learning.

Evidence 2 sources; the cell shows the highest tier

1. T1 · upstream documentedpapersource 2023-10-24verified 2026-10-24 (1d ago)

   FOWM (the method LeRobot's tdmpc policy implements) is pretrained offline and finetuned online on three visuo-motor tasks on a real xArm 7 with a jaw gripper and RealSense camera input.

   “The agent controls an xArm 7 robot with a jaw gripper using positional control”

   https://arxiv.org/abs/2310.16029
2. T1 · upstream documentedsource-codesource 2026-08-03verified 2026-10-24 (1d ago)lerobot 0.6.1

   LeRobot's tdmpc policy is an implementation of FOWM, linking the grid policy to the FOWM paper's xArm results.

   “Implementation of Finetuning Offline World Models in the Real World.”

   https://github.com/huggingface/lerobot/blob/v0.6.1/src/lerobot/policies/tdmpc/modeling_tdmpc.py