Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Dynamic Resilient Spatio-Semantic Memory with Hybrid Localization for Mobile Manipulation

About

Reliable mobile manipulation in dynamic indoor environments requires a scene representation that remains geometrically consistent, semantically queryable, and computationally bounded as the environment changes. Existing systems often rely on pre-built maps, static-scene assumptions, or highly accurate camera poses, which can lead to stale or misaligned scene information when target objects are relocated or pose estimates are corrected. This paper presents DREAM, a real-robot mobile manipulation framework that integrates perception, memory, localization, navigation, and manipulation in previously unseen indoor environments without a pre-built map. DREAM constructs an online spatio-semantic voxel memory from RGB-D observations registered by a LiDAR-inertial-visual SLAM backend. It further introduces pose-graph-aware Redundancy-Aware Memory Pruning (RMP) to update historical observations after pose corrections while keeping long-horizon observation history bounded. For target localization and reacquisition, DREAM combines language-conditioned 3D retrieval, open-vocabulary image detection, and multimodal large language model based semantic verification. Real-robot experiments in four dynamic indoor laboratory scenes show that DREAM improves long-horizon task success rates from 40%-60% with DynaMem to 55%-70%, while maintaining a memory footprint of 0.37-0.63 GB and an online memory-update time of 0.43-0.53 s across scenes.

Zhijie Yan, Shufei Li, Ze Zhang, Xin Liu, Yuhang Zheng, Zuoxu Wang• 2026

Related benchmarks

TaskDatasetResultRank
Long-term SuccessDynamic Mobile Manipulation Scene S1
Success Rate70
2
Long-term SuccessDynamic Mobile Manipulation Scene S2
Success Rate65
2
Long-term SuccessDynamic Mobile Manipulation Scene S3
Success Rate60
2
Long-term SuccessDynamic Mobile Manipulation Scene S4
Success Rate55
2
NavigationDynamic Mobile Manipulation Scene S1
Success Rate89.2
2
NavigationDynamic Mobile Manipulation Scene S2
Success Rate86.1
2
NavigationDynamic Mobile Manipulation Scene S3
Success Rate83.8
2
NavigationDynamic Mobile Manipulation Scene S4
Success Rate80
2
PickupDynamic Mobile Manipulation Scene S1
Success Rate94.4
2
PickupDynamic Mobile Manipulation Scene S2
Success Rate94.1
2
Showing 10 of 16 rows

Other info

Follow for update