Few-Shot Adaptation to Non-Stationary Environments via Latent Trend Embedding for Robotics

• URL: http://arxiv.org/abs/2603.10373v1
• Date: Wed, 11 Mar 2026 03:36:52 GMT
• Title: Few-Shot Adaptation to Non-Stationary Environments via Latent Trend Embedding for Robotics
• Abstract summary: This paper proposes a latent Trend ID-based framework for few-shot adaptation in non-stationary environments.<n>We introduce temporal regularization and a state transition model that enforces smooth evolution of the latent space.
• Score: 2.6989861363357
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Robotic systems operating in real-world environments often suffer from concept shift, where the input-output relationship changes due to latent environmental factors that are not directly observable. Conventional adaptation methods update model parameters, which may cause catastrophic forgetting and incur high computational cost. This paper proposes a latent Trend ID-based framework for few-shot adaptation in non-stationary environments. Instead of modifying model weights, a low-dimensional environmental state, referred to as the Trend ID, is estimated via backpropagation while the model parameters remain fixed. To prevent overfitting caused by per-sample latent variables, we introduce temporal regularization and a state transition model that enforces smooth evolution of the latent space. Experiments on a quantitative food grasping task demonstrate that the learned Trend IDs are distributed across distinct regions of the latent space with temporally consistent trajectories, and that few-shot adaptation to unseen environments is achieved without modifying model parameters. The proposed framework provides a scalable and interpretable solution for robotics applications operating across diverse and evolving environments.

Related papers

• Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control [55.01272784312405]
  We propose a context-aware dynamics model based on neural ordinary differential equations.<n>We validate the approach across diverse robotic platforms, including a quadrotor in simulation, as well as a Sphero BOLT robot and a Fanuc manipulator in real-world experiments.
  arXiv  Detail & Related papers  (2026-06-13T20:55:46Z)
• Robust Embodied Perception in Dynamic Environments via Disentangled Weight Fusion [19.79804703621505]
  We propose a domain-id and exemplar-free incremental learning framework for embodied multimedia systems.<n>The proposed method significantly reduces catastrophic forgetting in a completely exemplar-free and domain-id free setting.
  arXiv  Detail & Related papers  (2026-04-02T06:15:07Z)
• Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments [61.62036321848316]
  Graph neural networks (GNNs) have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs.<n>Existing GNNs exhibit poor ability under distribution shifts, which is inevitable in dynamic scenarios.<n>This paper proposes Evolving Graph Learning framework for evolving graph generalization (Evoal) by environment-aware invariant pattern recognition.
  arXiv  Detail & Related papers  (2025-11-04T08:22:29Z)
• Detecting Model Drifts in Non-Stationary Environment Using Edit Operation Measures [45.88028371034407]
  This paper proposes a novel framework to detect such drifts by analyzing the distributional changes in sequences of agent behavior.<n>We introduce a suite of edit operation-based measures to quantify deviations between state-action trajectories generated under stationary and perturbed conditions.<n>Our experiments demonstrate that these measures can effectively distinguish drifted from non-drifted scenarios, even under varying levels of noise.
  arXiv  Detail & Related papers  (2025-09-14T17:48:06Z)
• Spatial Reasoners for Continuous Variables in Any Domain [49.83744014336816]
  We present a framework to perform spatial reasoning over continuous variables with generative denoising models.<n>We provide interfaces to control variable mapping from arbitrary data domains, generative model paradigms, and inference strategies.
  arXiv  Detail & Related papers  (2025-07-14T19:46:54Z)
• SPARTAN: A Sparse Transformer Learning Local Causation [63.29645501232935]
  Causal structures play a central role in world models that flexibly adapt to changes in the environment. We present the SPARse TrANsformer World model (SPARTAN), a Transformer-based world model that learns local causal structures between entities in a scene. By applying sparsity regularisation on the attention pattern between object-factored tokens, SPARTAN identifies sparse local causal models that accurately predict future object states.
  arXiv  Detail & Related papers  (2024-11-11T11:42:48Z)
• Nonstationary Time Series Forecasting via Unknown Distribution Adaptation [22.915008205203886]
  As environments evolve, temporal distribution shifts can degrade time series forecasting performance.<n>Some methods disentangle stationary and nonstationary components by assuming uniform distribution shifts, but it is impractical since when the distribution changes is unknown.<n>We propose the textbfUnknown textbfDistribution textbfAdaptation (textbfUDA) model for nonstationary time series forecasting.
  arXiv  Detail & Related papers  (2024-02-20T07:16:12Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• FREE: The Foundational Semantic Recognition for Modeling Environmental Ecosystems [56.0640340392818]
  We introduce a framework, FREE, that enables the use of varying features and available information to train a universal model.<n>The core idea is to map available environmental data into a text space and then convert the traditional predictive modeling task in environmental science to a semantic recognition problem.<n>Our evaluation on two societally important real-world applications, stream water temperature prediction and crop yield prediction, demonstrates the superiority of FREE over multiple baselines.
  arXiv  Detail & Related papers  (2023-11-17T00:53:09Z)
• Prediction under Latent Subgroup Shifts with High-Dimensional Observations [30.433078066683848]
  We introduce a new approach to prediction in graphical models with latent-shift adaptation. Our novel form of RPM identifies causal latent structure in the source environment, and adapts properly to predict in the target.
  arXiv  Detail & Related papers  (2023-06-23T12:26:24Z)
• Towards Fair Disentangled Online Learning for Changing Environments [28.207499975916324]
  We argue that changing environments in online learning can be attributed to partial changes in learned parameters that are specific to environments. We propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations. A novel regret is proposed in which it takes a mixed form of dynamic and static regret metrics followed by a fairness-aware long-term constraint.
  arXiv  Detail & Related papers  (2023-05-31T19:04:16Z)
• Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning [12.76337275628074]
  In this work, we propose a variational dynamic model based on the conditional variational inference to model the multimodality andgenerativeity. We derive an upper bound of the negative log-likelihood of the environmental transition and use such an upper bound as the intrinsic reward for exploration. Our method outperforms several state-of-the-art environment model-based exploration approaches.
  arXiv  Detail & Related papers  (2020-10-17T09:54:51Z)
• Lifelong Incremental Reinforcement Learning with Online Bayesian Inference [11.076005074172516]
  A long-lived reinforcement learning agent is to incrementally adapt its behavior as its environment changes. We propose LifeLong Reinforcement Learning (LLIRL), a new incremental algorithm for efficient lifelong adaptation to dynamic environments.
  arXiv  Detail & Related papers  (2020-07-28T13:23:41Z)

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.