TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies

Key points

• Vision-Language-Action (VLA) models are effective at understanding what task to perform, but provide limited control over how it should be executed, such as moving quickly or slowly.1
• TempoBridge extracts tempo cues from contextual VLM representations, aligns them with task progress through a causal phase router, and modulates nominal motion commands during execution.1
• It also preserves near-baseline performance when no tempo cue is present and generalizes to unseen tempo expressions without additional training.1
• Experiments on a physical robot further demonstrate language-conditioned tempo modulation in real-world manipulation.1

Sources (1)

• [1]TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:07 AM

  We introduce TempoBridge, a lightweight framework that uses frozen VLA representations to modulate actions according to tempo cues in the instruction at each task phase, without additional tempo-conditioned robot demonstrations or tempo-specific base-policy fine-tuning.

  Vision-Language-Action (VLA) models are effective at understanding what task to perform, but provide limited control over how it should be executed, such as moving quickly or slowly.

Extractive summary: sentences quoted from the sources.