Grounded Vision-Language Interpreter for Integrated Task and Motion Planning

TL;DR

This paper introduces ViLaIn-TAMP, a hybrid planning framework combining vision-language interpretation with symbolic and geometric planning, enhancing safety, interpretability, and success rates in robot task execution.

Contribution

It presents a novel hybrid framework that integrates vision-language models with symbolic and geometric planning, including a feedback loop for refinement, improving robot planning reliability.

Findings

Outperforms baseline by 18% in success rate

Adding corrective planning boosts success by 32%

Effective in complex cooking manipulation tasks

Abstract

While recent advances in vision-language models have accelerated the development of language-guided robot planners, their black-box nature often lacks safety guarantees and interpretability crucial for real-world deployment. Conversely, classical symbolic planners offer rigorous safety verification but require significant expert knowledge for setup. To bridge the current gap, this paper proposes ViLaIn-TAMP, a hybrid planning framework for enabling verifiable, interpretable, and autonomous robot behaviors. ViLaIn-TAMP comprises three main components: (1) a Vision-Language Interpreter (ViLaIn) adapted from previous work that converts multimodal inputs into structured problem specifications, (2) a modular Task and Motion Planning (TAMP) system that grounds these specifications in actionable trajectory sequences through symbolic and geometric constraint reasoning, and (3) a corrective planning (CP) module which receives concrete feedback on failed solution attempts and feed them with constraints back to ViLaIn to refine the specification. We design challenging manipulation tasks in a cooking domain and evaluate our framework. Experimental results demonstrate that ViLaIn-TAMP outperforms a VLM-as-a-planner baseline by 18% in mean success rate, and that adding the CP module boosts mean success rate by 32%.