cs.RONov 16, 2026

ReuseMem: One Memory, Multiple Goals in Robot Manipulation

Authors: Yoonseok Kang, Dayeon Jung, Seunghoon Jeon, Wonjib Kim, Dongchul Park

Organizations: Chung-Ang University

Abstract

Robots that work alongside people should be able to use what they have seen when new requests arise. The same experience may later support identifying an object or returning it to its original location, although these uses were unknown during observation. ReuseMem learns to use one visual memory for multiple later manipulation goals. It records visual features independently of future goals, retrieves complementary evidence for each request, and combines it with the current scene through a lightweight action interface. Retrieval is supervised by how well candidate evidence supports expert-action prediction across different current states, linking memory selection to its use in manipulation. Repeated visual features are stored once, and memory computations that remain unchanged during action generation are reused. Experiments on four simulation tasks and two physical scenarios demonstrate reuse of a common recording across different requests. With matched action adaptation, ReuseMem improves joint goal completion on the benchmark tasks by 24.5 percentage points over uniform memory. These findings show that one memory can support multiple later manipulation goals as the scene changes.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. REMM: Revisable Embodied Memory for Manipulation

    Oct 8, 2026Revanth Krishna Senthilkumaran, Ruwan Wickramarachchi, Alessandro Oltramari +1Long-Term Memory for Embodied AgentsMemory-Augmented Agents

  2. MessyMem: Learning-from-Doing Memory for Mobile Manipulation

    Sep 14, 2026Anuva Banwasi, William Muckelroy, Priya Sundaresan +3Long-Horizon Robotic ManipulationMobile Manipulation

  3. T2^2Mem: Learning Test-Time Memory for Robotics

    Sep 29, 2026Yize Liu, Huang Huang, Yining Hong +4Robot Policy LearningTest-Time Adaptation of VLAs