# FUSE: Active Functional Affordance Grounding through Adaptive Semantic-Geometric Evidence Acquisition

arXiv: https://arxiv.org/abs/2608.12683 · HTML: https://mlsanity.com/paper/2608.12683/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics](https://mlsanity.com/paper/1703.09312/) (2017)
- [ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects](https://mlsanity.com/paper/2006.13171/) (2020)
- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes](https://mlsanity.com/paper/2103.14127/) (2021)
- [A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets](https://mlsanity.com/paper/2406.12080/) (2024)
- [Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Grasping](https://mlsanity.com/paper/2011.06431/) (2020)
- [Robot Object Retrieval with Contextual Natural Language Queries](https://mlsanity.com/paper/2006.13253/) (2020)
- [TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation](https://mlsanity.com/paper/2210.10775/) (2022)
- [What Object Should I Use? - Task Driven Object Detection](https://mlsanity.com/paper/1904.03000/) (2019)
- [Affordance-Driven Next-Best-View Planning for Robotic Grasping](https://mlsanity.com/paper/2309.09556/) (2023)
- [VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility](https://mlsanity.com/paper/2503.12609/) (2025)
- [ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model](https://mlsanity.com/paper/2511.12795/) (2025)
- [EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization](https://mlsanity.com/paper/2506.17516/) (2025)
- [GCNGrasp-VP: Affordance-Guided View Planning for Efficient Task-Oriented Grasping](https://mlsanity.com/paper/2606.19091/) (2026)

## Abstract (arXiv)

Embodied agents must often identify and interact with objects based on their function rather than their identity, requiring them to actively acquire observations that reveal discriminative functional evidence. Existing affordance grounding methods operate from fixed viewpoints and lack mechanisms for deciding where to look when functional cues are occluded or incomplete. We introduce Active Functional Affordance Grounding, a new task in which an agent sequentially explores a scene to identify and spatially ground an object satisfying a functional query. To address this problem, we propose FUSE, an adaptive semantic-geometric evidence acquisition framework that combines explicit uncertainty-driven exploration with a learned amortized planner to efficiently select informative viewpoints. We further introduce a Habitat-based benchmark for evaluating active functional grounding. Experiments show that FUSE achieves the highest observed non-oracle grounding performance while reducing computation by 1.33x relative to fully explicit exploration, and remains effective across multiple affordance knowledge sources.