# MAVP: Map-Aware Visuomotor Policies for Mobile Manipulation

arXiv: https://arxiv.org/abs/2609.26378 · HTML: https://mlsanity.com/paper/2609.26378/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes](https://mlsanity.com/paper/1806.05620/) (2018)
- [UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers](https://mlsanity.com/paper/2407.10353/) (2024)
- [Waypoint-Based Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2307.14326/) (2023)
- [HYDRA: Hybrid Robot Actions for Imitation Learning](https://mlsanity.com/paper/2306.17237/) (2023)
- [Multi-skill Mobile Manipulation for Object Rearrangement](https://mlsanity.com/paper/2209.02778/) (2022)
- [Spatial Action Maps for Mobile Manipulation](https://mlsanity.com/paper/2004.09141/) (2020)
- [VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction](https://mlsanity.com/paper/2511.19971/) (2025)
- [RoMo: Robust Motion Segmentation Improves Structure from Motion](https://mlsanity.com/paper/2411.18650/) (2024)
- [HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations](https://mlsanity.com/paper/2603.03243/) (2026)
- [Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching](https://mlsanity.com/paper/2309.03835/) (2023)
- [Mobi-π: Mobilizing Your Robot Learning Policy](https://mlsanity.com/paper/2505.23692/) (2025)
- [HoMeR: Learning In-the-Wild Mobile Manipulation via Hybrid Imitation and Whole-Body Control](https://mlsanity.com/paper/2506.01185/) (2025)
- [cuVSLAM: CUDA accelerated visual odometry and mapping](https://mlsanity.com/paper/2506.04359/) (2025)
- [Seeing the Bigger Picture: 3D Latent Mapping for Mobile Manipulation Policy Learning](https://mlsanity.com/paper/2510.03885/) (2025)
- [Teaching Robots Where To Go And How To Act With Human Sketches via Spatial Diagrammatic Instructions](https://mlsanity.com/paper/2403.12465/) (2024)
- [Bi-Manual Joint Camera Calibration and Scene Representation](https://mlsanity.com/paper/2505.24819/) (2025)

## Abstract (arXiv)

Successful mobile manipulation requires coordinated base and arm motion while maintaining accurate spatial positioning. However, demonstration-trained policies can struggle to realise the intended base motion reliably, leading to spatial misalignment and subsequent manipulation failures. We present MAVP (Map-Aware Visuomotor Policies), a framework that improves execution reliability by predicting explicit base-pose targets and tracking them using localisation feedback. MAVP reconstructs a static map from teleoperated demonstrations and expresses demonstrated base trajectories in a shared map frame, providing consistent spatial supervision across demonstrations. At execution time, the policy receives RGB observations, joint states, and the robot's current map-frame base pose, and jointly predicts target base poses, arm actions, and gripper actions. A low-level controller tracks the predicted base targets using feedforward motion and pose error feedback, enabling correction of execution deviations. We additionally use pose-noise augmentation during training to improve robustness to errors in the policy's pose input. Across six real-world manipulation tasks and three policy families, MAVP achieves higher task success rates than unanchored velocity control in all tasks. Videos and additional results are available at https://123qwedsa123.github.io/mavp/.