NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulation

TL;DR

NaturalVLM introduces a new benchmark and a step-by-step learning framework enabling robots to understand and execute complex, fine-grained natural language instructions for diverse 3D object manipulation tasks, advancing robotic perception and manipulation capabilities.

Contribution

The paper presents NrVLM, a comprehensive benchmark with annotated tasks, and a novel learning framework that integrates visual and linguistic cues for multi-step manipulation guided by natural language.

Findings

Our approach outperforms baselines on the NrVLM benchmark.

Explicit cross-modality alignment improves manipulation accuracy.

Fine-grained instructions enable complex multi-step tasks.

Abstract

Enabling home-assistant robots to perceive and manipulate a diverse range of 3D objects based on human language instructions is a pivotal challenge. Prior research has predominantly focused on simplistic and task-oriented instructions, i.e., "Slide the top drawer open". However, many real-world tasks demand intricate multi-step reasoning, and without human instructions, these will become extremely difficult for robot manipulation. To address these challenges, we introduce a comprehensive benchmark, NrVLM, comprising 15 distinct manipulation tasks, containing over 4500 episodes meticulously annotated with fine-grained language instructions. We split the long-term task process into several steps, with each step having a natural language instruction. Moreover, we propose a novel learning framework that completes the manipulation task step-by-step according to the fine-grained instructions. Specifically, we first identify the instruction to execute, taking into account visual observations and the end-effector's current state. Subsequently, our approach facilitates explicit learning through action-prompts and perception-prompts to promote manipulation-aware cross-modality alignment. Leveraging both visual observations and linguistic guidance, our model outputs a sequence of actionable predictions for manipulation, including contact points and end-effector poses. We evaluate our method and baselines using the proposed benchmark NrVLM. The experimental results demonstrate the effectiveness of our approach. For additional details, please refer to https://sites.google.com/view/naturalvlm.