# What Foundation Models can Bring for Robot Learning in Manipulation : A Survey

arXiv: https://arxiv.org/abs/2404.18201 · HTML: https://mlsanity.com/paper/2404.18201/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2024.

## Built on by (most cited first, 19 of 19)

- [RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete](https://mlsanity.com/paper/2502.21257/) (2025)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2508.13073/) (2025)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration](https://mlsanity.com/paper/2505.03673/) (2025)
- [MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation](https://mlsanity.com/paper/2407.11682/) (2024)
- [Orient Anything V2: Unifying Orientation and Rotation Understanding](https://mlsanity.com/paper/2601.05573/) (2026)
- [REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation](https://mlsanity.com/paper/2512.19562/) (2025)
- [VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning](https://mlsanity.com/paper/2508.04043/) (2025)
- [Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy](https://mlsanity.com/paper/2411.18289/) (2024)
- [Synergistic Prompting for Robust Visual Recognition with Missing Modalities](https://mlsanity.com/paper/2507.07802/) (2025)
- [From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation](https://mlsanity.com/paper/2605.11951/) (2026)
- [Learning Primitive Embodied World Models: Towards Scalable Robotic Learning](https://mlsanity.com/paper/2508.20840/) (2025)
- [Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning](https://mlsanity.com/paper/2506.06856/) (2025)
- [Team Samsung-RAL: Technical Report for 2024 RoboDrive Challenge-Robust Map Segmentation Track](https://mlsanity.com/paper/2405.10567/) (2024)
- [OmniDexVLG: Learning Dexterous Grasp Generation from Vision Language Model-Guided Grasp Semantics, Taxonomy and Functional Affordance](https://mlsanity.com/paper/2512.03874/) (2025)
- [Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills](https://mlsanity.com/paper/2608.01851/) (2026)
- [RefGuard: Identity-Aware Language-Guided Robot Manipulation via Joint Target-Anchor-Frame Grounding](https://mlsanity.com/paper/2609.06221/) (2026)

## Abstract (arXiv)

The realization of universal robots is an ultimate goal of researchers. However, a key hurdle in achieving this goal lies in the robots' ability to manipulate objects in their unstructured surrounding environments according to different tasks. The learning-based approach is considered an effective way to address generalization. The impressive performance of foundation models in the fields of computer vision and natural language suggests the potential of embedding foundation models into manipulation tasks as a viable path toward achieving general manipulation capability. However, we believe achieving general manipulation capability requires an overarching framework akin to auto driving. This framework should encompass multiple functional modules, with different foundation models assuming distinct roles in facilitating general manipulation capability. This survey focuses on the contributions of foundation models to robot learning for manipulation. We propose a comprehensive framework and detail how foundation models can address challenges in each module of the framework. What's more, we examine current approaches, outline challenges, suggest future research directions, and identify potential risks associated with integrating foundation models into this domain.