AffordanceGrasp-R1:Leveraging Reasoning-Based Affordance Segmentation with Reinforcement Learning for Robotic Grasping

TL;DR

AffordanceGrasp-R1 is a novel framework that combines reasoning-based affordance segmentation with reinforcement learning to improve robotic grasping, demonstrating superior performance in both benchmarks and real-world tests.

Contribution

It introduces a reasoning-driven affordance segmentation method integrated with reinforcement learning, enhancing deduction, spatial grounding, and context-aware grasping in robotic manipulation.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Shows robustness and generalization in real-world robotic grasping.

Effective in complex language-conditioned manipulation scenarios.

Abstract

We introduce AffordanceGrasp-R1, a reasoning-driven affordance segmentation framework for robotic grasping that combines a chain-of-thought (CoT) cold-start strategy with reinforcement learning to enhance deduction and spatial grounding. In addition, we redesign the grasping pipeline to be more context-aware by generating grasp candidates from the global scene point cloud and subsequently filtering them using instruction-conditioned affordance masks. Extensive experiments demonstrate that AffordanceGrasp-R1 consistently outperforms state-of-the-art (SOTA) methods on benchmark datasets, and real-world robotic grasping evaluations further validate its robustness and generalization under complex language-conditioned manipulation scenarios.