Paper Detail

MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning

Mingke Lu, Anxing Xiao, David Hsu

arxiv Score 16.3

Published 2026-09-21 · First seen 2026-09-22

General AI

Abstract

Understanding natural human instructions is crucial for deploying robots in human-centric environments. We study multimodal instruction grounding, where language and gesture provide complementary but uncertain cues. We present MIGU, a modular framework that combines semantic and geometric evidence into a unified grounding belief and connects it to manipulation planning. MIGU constructs a 3D geometric likelihood by propagating viewing-direction and depth uncertainty through eye-finger geometry while accounting for hand-direction estimation error. A vision-language model (VLM) provides semantic priors over candidate objects and regions, which are combined with the geometric likelihood through Bayes-inspired fusion. The resulting belief supports behavior planning to either proceed directly to downstream planning or request clarification. Grounded targets then define goals for mobile manipulation and tabletop task-and-motion planning. On a real-world benchmark, MIGU outperforms all evaluated baselines, while ablations support the benefit of explicit multimodal uncertainty modeling. Project website: multimodal-instruction.github.io

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{lu2026migu,
  title = {MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning},
  author = {Mingke Lu and Anxing Xiao and David Hsu},
  year = {2026},
  abstract = {Understanding natural human instructions is crucial for deploying robots in human-centric environments. We study multimodal instruction grounding, where language and gesture provide complementary but uncertain cues. We present MIGU, a modular framework that combines semantic and geometric evidence into a unified grounding belief and connects it to manipulation planning. MIGU constructs a 3D geometric likelihood by propagating viewing-direction and depth uncertainty through eye-finger geometry wh},
  url = {https://arxiv.org/abs/2609.24995},
  keywords = {cs.RO},
  eprint = {2609.24995},
  archiveprefix = {arXiv},
}

Metadata

{}