MEMBOT: Memory-Based Robot in Intermittent POMDP

• URL: http://arxiv.org/abs/2509.11225v1
• Date: Sun, 14 Sep 2025 12:00:52 GMT
• Title: MEMBOT: Memory-Based Robot in Intermittent POMDP
• Abstract summary: MEMBOT is a memory-based architecture designed to address intermittent partial observability in robotic control tasks.<n>We train and evaluate MEMBOT on 10 robotic manipulation benchmark tasks from MetaWorld and Robomimic.<n>Results show that MEMBOT consistently outperforms both memoryless and naively recurrent baselines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robotic systems deployed in real-world environments often operate under conditions of partial and often intermittent observability, where sensor inputs may be noisy, occluded, or entirely unavailable due to failures or environmental constraints. Traditional reinforcement learning (RL) approaches that assume full state observability are ill-equipped for such challenges. In this work, we introduce MEMBOT, a modular memory-based architecture designed to address intermittent partial observability in robotic control tasks. MEMBOT decouples belief inference from policy learning through a two-phase training process: an offline multi-task learning pretraining stage that learns a robust task-agnostic latent belief encoder using a reconstruction losses, followed by fine-tuning of task-specific policies using behavior cloning. The belief encoder, implemented as a state-space model (SSM) and a LSTM, integrates temporal sequences of observations and actions to infer latent state representations that persist even when observations are dropped. We train and evaluate MEMBOT on 10 robotic manipulation benchmark tasks from MetaWorld and Robomimic under varying rates of observation dropout. Results show that MEMBOT consistently outperforms both memoryless and naively recurrent baselines, maintaining up to 80% of peak performance under 50% observation availability. These findings highlight the effectiveness of explicit belief modeling in achieving robust, transferable, and data-efficient policies for real-world partially observable robotic systems.

Related papers

• Towards Generalizable Visually Grounded Exploration of Household Devices [74.66117923766632]
  Key bottleneck of realizing general autonomous embodied agents lies in Generalizable Visually Grounded Exploration.<n>We introduce VGEBench, a benchmark designed to evaluate the generalizable visually grounded exploration capabilities of Vision-Language Models.<n>Unlike static datasets, we construct a Logic-Driven State Machine framework. This framework simulates multi-turn interaction loops, compelling agents to achieve goals by active visual perception and feedback-driven correction.
  arXiv  Detail & Related papers  (2026-09-01T07:42:45Z)
• DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks [54.32016216994156]
  We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise.<n>To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $mathcalO(1)$ footprint for long-horizon tasks.<n>We present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training.
  arXiv  Detail & Related papers  (2026-04-13T03:19:36Z)
• Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair [5.4872967954342675]
  Learning robot control policies from demonstrations is a powerful paradigm, yet real-world data is often suboptimal, noisy, or otherwise imperfect.<n>We present a formal framework that leverages Temporal Behavior Trees (TBT) to repair suboptimal trajectories prior to their use in downstream policy learning.<n>We demonstrate the effectiveness of this framework on discrete grid-world navigation and continuous single and multi-agent reach-avoid tasks.
  arXiv  Detail & Related papers  (2026-04-05T18:49:45Z)
• ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation [66.02142169323521]
  Vision-Language-Action models and world models have recently emerged as promising paradigms for general-purpose robotic intelligence.<n>Existing benchmarks are largely simulator-centric, which provide controllability but fail to capture the reality gap caused by perception noise.<n>We introduce ManipArena, a standardized evaluation framework designed to bridge simulation and real-world execution.
  arXiv  Detail & Related papers  (2026-03-30T15:06:41Z)
• RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation [68.7948300643741]
  We propose Robot-Conditioned Normalizing Flow (RC-NF), a real-time monitoring model for robotic anomaly detection and intervention.<n>RC-NF decouples the processing of task-aware robot and object states within the normalizing flow.<n>It achieves state-of-the-art performance across all anomaly types compared to previous methods in monitoring robotic tasks.
  arXiv  Detail & Related papers  (2026-03-11T10:14:37Z)
• Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback [2.165723322157105]
  This work presents a framework for online Continual Reinforcement Learning that enables automated adaptation during deployment.<n>The proposed method leverages world model prediction residuals to detect out-of-distribution events and automatically trigger finetuning.<n>The approach is validated on a variety of contemporary continuous control problems, including a quadruped robot in high-fidelity simulation.
  arXiv  Detail & Related papers  (2026-03-04T13:07:42Z)
• Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons [69.87766750714945]
  General-purpose robot reward models are typically trained to predict absolute task progress from expert demonstrations.<n>We introduce Robometer, a scalable reward modeling framework that combines intra-trajectory progress supervision with inter-trajectory preference supervision.<n>Robometer is trained with a dual objective: a frame-level progress loss that anchors reward magnitude on expert data, and a trajectory-comparison preference loss that imposes global ordering constraints.
  arXiv  Detail & Related papers  (2026-03-02T17:38:58Z)
• RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation [47.79800816696372]
  Real-world testing of manipulation policies is labor-intensive at scale, and difficult to reproduce.<n>Existing simulation benchmarks are similarly limited, as they train and test policies within the same synthetic domains.<n>In this paper, we introduce a new benchmarking framework that overcomes these challenges by shifting VLA evaluation into large-scale simulated augmented environments.
  arXiv  Detail & Related papers  (2025-10-27T17:41:38Z)
• From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM [52.64097278841485]
  Review examines how incorporating learning and observational biases through physics-informed modeling and data strategies can guide models toward physically consistent and reliable predictions.<n>Fast adaptation methods including meta-learning and few-shot learning are reviewed alongside domain generalization techniques.
  arXiv  Detail & Related papers  (2025-09-25T14:15:43Z)
• Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis [55.13545823385091]
  Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents.<n>In real-world applications, each agent may experience slightly different transition dynamics, leading to inherent model mismatches.<n>We show that even moderate levels of information sharing significantly mitigate environment-specific errors.
  arXiv  Detail & Related papers  (2025-03-21T18:06:28Z)
• A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning [67.72413262980272]
  Pre-trained vision models (PVMs) are fundamental to modern robotics, yet their optimal configuration remains unclear.<n>We develop SlotMIM, a method that induces object-centric representations by introducing a semantic bottleneck.<n>Our approach achieves significant improvements over prior work in image recognition, scene understanding, and robot learning evaluations.
  arXiv  Detail & Related papers  (2025-03-10T06:18:31Z)
• Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning [24.079032278280447]
  We propose an approach that combines batch reinforcement learning (RL) with model-predictive control (MPC)<n>We validate the proposed approach through extensive simulated and real-world experiments on a Franka Panda robot performing the robot waiter task.
  arXiv  Detail & Related papers  (2024-11-27T03:33:42Z)
• R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models [50.19174067263255]
  We introduce prior preference learning techniques and self-revision schedules to help the agent excel in sparse-reward, continuous action, goal-based robotic control POMDP environments. We show that our agents offer improved performance over state-of-the-art models in terms of cumulative rewards, relative stability, and success rate.
  arXiv  Detail & Related papers  (2024-09-21T18:32:44Z)
• Model-Based Runtime Monitoring with Interactive Imitation Learning [30.70994322652745]
  This work aims to endow a robot with the ability to monitor and detect errors during task execution. We introduce a model-based runtime monitoring algorithm that learns from deployment data to detect system anomalies and anticipate failures. Our method outperforms the baselines across system-level and unit-test metrics, with 23% and 40% higher success rates in simulation and on physical hardware.
  arXiv  Detail & Related papers  (2023-10-26T16:45:44Z)
• DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Control [0.0]
  Delayed Markov decision processes fulfill the Markov property by augmenting the state space of agents with a finite time window of recently committed actions. We introduce a disturbance-augmented Markov decision process in delayed settings as a novel representation to incorporate disturbance estimation in training on-policy reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2023-06-15T10:11:38Z)
• Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics [11.946807588018595]
  This paper presents a unified model-based reinforcement learning framework that bridges active exploration and uncertainty-aware deployment. The two opposing tasks of exploration and deployment are optimized through state-of-the-art sampling-based MPC. We conduct experiments on both autonomous vehicles and wheeled robots, showing promising results for both exploration and deployment.
  arXiv  Detail & Related papers  (2023-05-20T17:20:12Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)
• MELD: Meta-Reinforcement Learning from Images via Latent State Models [109.1664295663325]
  We develop an algorithm for meta-RL from images that performs inference in a latent state model to quickly acquire new skills. MELD is the first meta-RL algorithm trained in a real-world robotic control setting from images.
  arXiv  Detail & Related papers  (2020-10-26T23:50:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.