AffordanceGrasp-R1:Leveraging Reasoning-Based Affordance Segmentation with Reinforcement Learning for Robotic Grasping
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 42 of its 60 references that are in the map. First posted on arXiv 3 Feb 2026.
Builds on
42 of 60 references.
Closest ancestors · 3
Same direction, newest first
- 2025Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model8 Aug
- 2025Free-form language-based robotic reasoning and grasping17 Mar
- 2025AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter2 Mar
Other references · 39
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2023GPT-4 Technical Reportcited by 18,132
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
- 2025Qwen3 Technical Reportcited by 8,195
- 2025Qwen2.5-VL Technical Reportcited by 5,418
- 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
- 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
- 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
27 more
- 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
- 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
- 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 655
- 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
- 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 446
- 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
- 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Roboticscited by 242
- 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcementcited by 234
- 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
- 2023PixelLM: Pixel Reasoning with Large Multimodal Modelcited by 220
- 2024Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learningcited by 158
- 2025LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMscited by 145
- 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 129
- 2024One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videoscited by 99
- 2022Learning Affordance Grounding from Exocentric Imagescited by 82
- 2023LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Modelcited by 70
- 2024AffordanceLLM: Grounding Affordance from Vision Language Modelscited by 55
- 2023Going Denser with Open-Vocabulary Part Segmentationcited by 51
- 2023HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructionscited by 47
- 2023AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Posecited by 47
- 2023One-Shot Open Affordance Learning with Foundation Modelscited by 45
- 2023Understanding 3D Object Interaction from a Single Imagecited by 33
- 2025SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learningcited by 31
- 2025RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Graspingcited by 11
- 2024What does CLIP know about peeling a banana?cited by 9
- 2025Language-Guided Grasp Detection with Coarse-to-Fine Learning for Robotic Manipulationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation
- 2024GLOVER: Generalizable Open-Vocabulary Affordance Reasoning for Task-Oriented Grasping
- 2024Affordance-Guided Reinforcement Learning via Visual Prompting
- 2026Affordance2Action: Task-Conditioned Scene-level Affordance Grounding for Real-Time Manipulation ↗
- 2026PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
- 2021Contrastively Learning Visual Attention as Affordance Cues from Demonstrations for Robotic Grasping
- 2026AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
- 2026AffordTrajDP: Dynamic Affordance-Guided Visuomotor Policy Learning for Robotic Manipulation