홈 › Papers

RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design

2026-03-01 · Tianxing Chen, Yuran Wang, Mingleyang Li, Yan Qin, Hao Shi, Zixuan Li, Yifan Hu, Yingsheng Zhang, Kaixuan Wang, Yue Chen, Hongcheng Wang, Renjing Xu, Ruihai Wu, Yao Mu, Yaodong Yang, Hao Dong, Ping Luo arxiv

Robotic manipulation policies have made rapid progress in recent years, yet most existing approaches give limited consideration to memory capabilities. Consequently, they struggle to solve tasks that require reasoning over historical observations and maintaining task-relevant information over time, which are common requirements in real-world manipulation scenarios. Although several memory-aware policies have been proposed, systematic evaluation of memory-dependent manipulation remains underexplored, and the relationship between architectural design choices and memory performance is still not well understood. To address this gap, we introduce RMBench, a simulation benchmark comprising 9 manipulation tasks that span multiple levels of memory complexity, enabling systematic evaluation of policy memory capabilities. We further propose Mem-0, a modular manipulation policy with explicit memory components designed to support controlled ablation studies. Through extensive simulation and real-world experiments, we identify memory-related limitations in existing policies and provide empirical insights into how architectural design choices influence memory performance. The website is available at https://rmbench.github.io/.

📄 PDF Abstract BibTeX arXiv:2603.01229

Code (0)

등록된 구현이 없습니다.

ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation

2023-03-29 · Chaitanya Mitash, Fan Wang, Shiyang Lu, Vikedo Terhuja 외

This paper introduces Amazon Robotic Manipulation Benchmark (ARMBench), a large-scale, object-centric benchmark dataset for robotic manipulation in the context of a warehouse. Automation of operations in modern warehouse…

Defect Detection Instance Segmentation Object Semantic Segmentation

HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation

2026-06-09 · Xiaoquan Sun, Ruijian Zhang, Chen Cao, Yihan Sun 외 arxiv

World Action Models (WAMs) have emerged as a new powerful paradigm for embodied intelligence, learning action-relevant visual dynamics that significantly enhance generalization and robustness. However, existing WAMs stil…

Optical Flow Estimation Causal Inference

RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control

2022-10-20 · Yanfei Xiang, Xin Wang, Shu Hu, Bin Zhu 외

Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs. The last decade has developed a long list of reinforcement learning algorithms. Recent progress benefits from deep le…

Benchmarking Data Augmentation Deep Reinforcement Learning reinforcement-learning+2

RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies

2026-03-04 · Yinpei Dai, Hongze Fu, Jayjun Lee, Yuejiang Liu 외 arxiv

Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipulating objects that become temporarily occluded. Recent vision-language-action (…

Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation

2026-06-29 · Yulin Zhou, Yimeng Wang, Nengyu Wang, Shaojia Xing 외 arxiv

General-purpose robot policies should be modeled as dynamical systems, yet many VLA and generative imitation policies still rely on present observations or short windows. This Markovian shortcut fails in memory-dependent…