Saved in:
Bibliographic Details
Main Authors: Shen, Yu-Hong, Wu, Chuan-Yu, Yang, Yi-Ru, Tai, Yen-Ling, Chen, Yi-Ting
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.13055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908579931357184
author Shen, Yu-Hong
Wu, Chuan-Yu
Yang, Yi-Ru
Tai, Yen-Ling
Chen, Yi-Ting
author_facet Shen, Yu-Hong
Wu, Chuan-Yu
Yang, Yi-Ru
Tai, Yen-Ling
Chen, Yi-Ting
contents We investigate the use of Multimodal Large Language Models (MLLMs) with in-context learning for closed-loop task planning in instruction-following manipulation. We identify four essential requirements for successful task planning: quantity estimation, reachability analysis, relative positioning, and collision avoidance. However, existing benchmarks fail to support holistic evaluation across all these aspects. To address this gap, we introduce \textbf{QuARC} (Quantity, Analysis, Relative positioning, Collision), a new benchmark based on a food preparation scenario that integrates all four challenges. Using QuARC, we reveal two major limitations of current MLLMs: cross-modal distraction and geometric infeasibility. To tackle these, we adapt Chain-of-Thought with Self-Consistency to mitigate reasoning loss from cross-modal distractions and incorporate an affordance predictor to guide planning based on geometric feasibility. Our comprehensive evaluation analyzes performance across multiple baselines and explains sources of improvement. Our method achieves a 76.7\% success rate on the benchmark, significantly outperforming the ViLa baseline (36.7\%), without requiring additional finetuning. Code and dataset are available at https://hcis-lab.github.io/Affordance-Guided-Self-Consistent-MLLM.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13055
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation
Shen, Yu-Hong
Wu, Chuan-Yu
Yang, Yi-Ru
Tai, Yen-Ling
Chen, Yi-Ting
Robotics
Artificial Intelligence
We investigate the use of Multimodal Large Language Models (MLLMs) with in-context learning for closed-loop task planning in instruction-following manipulation. We identify four essential requirements for successful task planning: quantity estimation, reachability analysis, relative positioning, and collision avoidance. However, existing benchmarks fail to support holistic evaluation across all these aspects. To address this gap, we introduce \textbf{QuARC} (Quantity, Analysis, Relative positioning, Collision), a new benchmark based on a food preparation scenario that integrates all four challenges. Using QuARC, we reveal two major limitations of current MLLMs: cross-modal distraction and geometric infeasibility. To tackle these, we adapt Chain-of-Thought with Self-Consistency to mitigate reasoning loss from cross-modal distractions and incorporate an affordance predictor to guide planning based on geometric feasibility. Our comprehensive evaluation analyzes performance across multiple baselines and explains sources of improvement. Our method achieves a 76.7\% success rate on the benchmark, significantly outperforming the ViLa baseline (36.7\%), without requiring additional finetuning. Code and dataset are available at https://hcis-lab.github.io/Affordance-Guided-Self-Consistent-MLLM.
title Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2503.13055