arXiv subjects

Ruchi Choudhary

Publications and source records attributed to Ruchi Choudhary.

12 recordsLinked to original sources

arXiv2025

Annotation-Free One-Shot Imitation Learning for Multi-Step Manipulation Tasks

Recent advances in one-shot imitation learning have enabled robots to acquire new manipulation skills from a single human demonstration. While existing methods achieve strong performance on single-step tasks, they remain limited in their ability to handle long-horizon, multi-step tasks without additional model training or manual annotation. We propose a method that can be applied to this setting provided a single demonstration without additional model training or manual annotation. We evaluated our method on multi-step and single-step manipulation tasks where our method achieves an average success rate of 82.5% and 90%, respectively. Our method matches and exceeds the performance of the baselines in both these cases. We also compare the performance and computational efficiency of alternative pre-trained feature extractors within our framework.

cs.RO↗

arXiv2025

Adapting to Change: A Comparison of Continual and Transfer Learning for Modeling Building Thermal Dynamics under Concept Drifts

Transfer Learning (TL) is currently the most effective approach for modeling building thermal dynamics when only limited data are available. TL uses a pretrained model that is fine-tuned to a specific target building. However, it remains unclear how to proceed after initial fine-tuning, as more operational measurement data are collected over time. This challenge becomes even more complex when the dynamics of the building change, for example, after a retrofit or a change in occupancy. In Machine Learning literature, Continual Learning (CL) methods are used to update models of changing systems. TL approaches can also address this challenge by reusing the pretrained model at each update step and fine-tuning it with new measurement data. A comprehensive study on how to incorporate new measurement data over time to improve prediction accuracy and address the challenges of concept drifts (changes in dynamics) for building thermal dynamics is still missing. Therefore, this study compares several CL and TL strategies, as well as a model trained from scratch, for thermal dynamics modeling during building operation. The methods are evaluated using 5--7 years of simulated data representative of single-family houses in Central Europe, including scenarios with concept drifts from retrofits and changes in occupancy. We propose a CL strategy (Seasonal Memory Learning) that provides greater accuracy improvements than existing CL and TL methods, while maintaining low computational effort. SML outperformed the benchmark of initial fine-tuning by 28.1\% without concept drifts and 34.9\% with concept drifts.

eess.SY↗

arXiv2025

Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models

Foundation models for natural language processing have many coherent definitions of hallucination and methods for its detection and mitigation. However, analogous definitions and methods do not exist for multi-variate time-series (MVTS) foundation models. We propose new definitions for MVTS hallucination, along with new detection and mitigation methods using a diffusion model to estimate hallucination levels. We derive relational datasets from popular time-series datasets to benchmark these relational hallucination levels. Using these definitions and models, we find that open-source pre-trained MVTS imputation foundation models relationally hallucinate on average up to 59.5% as much as a weak baseline. The proposed mitigation method reduces this by up to 47.7% for these models. The definition and methods may improve adoption and safe usage of MVTS foundation models.

cs.LG↗

arXiv2025

The value of hedging against energy storage uncertainties when designing energy parks

Energy storage is needed to match renewable generation to industrial loads in energy parks. However, the future performance of bulk storage technologies is currently highly uncertain. Due to the urgency of decarbonization targets, energy park projects must be designed and begun now. But, as uncertainty in storage performance reduces, a different technology than identified during initial design may turn out cheaper. Enabling flexibility so that design adaptations can be made as better information becomes available would lower the cost of decarbonizing industry. But having this flexibility is itself costly. This raises the question, "Is it worth it?" This study quantifies the benefit of retaining flexibility to adapt energy park designs and optionality over storage technology choice as uncertainty reduces, to determine whether it is economically worthwhile. It applies the Value of Information analysis framework to the sizing of wind, solar, and storage in an illustrative energy park model based on a real-world proposal near Rotterdam, considering uncertainty in storage efficiency, lifetime, and capital cost. Updating asset sizings after storage uncertainty reduced is found to reduce total costs by 18% on average. Having the option to switch storage technology choice as well reduces costs by a further 13%, which is substantially greater than the cost of providing storage optionality. Using two storage technologies in the energy park reduces costs by 14%, and in this case storage optionality is not worthwhile. These results are robust to the level of uncertainty reduction in storage performance, and the risk aversion of the system designer.

eess.SY↗

arXiv2024

Quantifying the benefit of load uncertainty reduction for the design of district energy systems under grid constraints using the Value of Information

Load uncertainty must be accounted for during design to ensure building energy systems can meet energy demands during operation. Reducing building load uncertainty allows for improved designs with less compromise to be identified, reducing the cost of decarbonizing energy usage. However, the building monitoring required to reduce load uncertainty is costly. This study uses Value of Information analysis (VoI) to quantify the economic benefit of practical building monitoring for supporting energy system design decisions, and determine if its benefits outweigh its cost. An extension of the VoI framework, termed 'On-Policy' VoI, is proposed, which admits complex decision making tasks where decision policies are required. This is applied to a case study district energy system design problem, where a Linear Program model is used to size solar-battery systems and grid connection capacity under uncertain building loads, modelled using historic electricity metering data. Load uncertainty is found to significantly impact both system operating costs ($\pm$30%) and the optimal system design ($\pm$20%). However, using building monitoring data to improve the design of the district reduces overall costs by less than 1.5% on average. As this is less than the cost of measurement, using monitoring is not economically worthwhile in this case. This provides the first numerical evidence to support the sufficiency of using standard building load profiles for energy system design. Further, reducing only uncertainty in mean load is found to provide most of the available decision support benefit, meaning using hourly measurement data provides little benefit for energy retrofit design.

eess.SY↗

arXiv2024

Rationalising data collection for supporting decision making in building energy systems using Value of Information analysis

The use of data collection to support decision making through the reduction of uncertainty is ubiquitous in the management, operation, and design of building energy systems. However, no existing studies in the building energy systems literature have quantified the economic benefits of data collection strategies to determine whether they are worth their cost. This work demonstrates that Value of Information analysis (VoI), a Bayesian Decision Analysis framework, provides a suitable methodology for quantifying the benefits of data collection. Three example decision problems in building energy systems are studied: air-source heat pump maintenance scheduling, ventilation scheduling for indoor air quality, and ground-source heat pump system design. Smart meters, occupancy monitoring systems, and ground thermal tests are shown to be economically beneficial for supporting these decisions respectively. It is proposed that further study of VoI in building energy systems would allow expenditure on data collection to be economised and prioritised, avoiding wastage.

eess.SY↗

arXiv2024

Impact of data for forecasting on performance of model predictive control in buildings with smart energy storage

Data is required to develop forecasting models for use in Model Predictive Control (MPC) schemes in building energy systems. However, data is costly to both collect and exploit. Determining cost optimal data usage strategies requires understanding of the forecast accuracy and resulting MPC operational performance it enables. This study investigates the performance of both simple and state-of-the-art machine learning prediction models for MPC in multi-building energy systems using a simulated case study with historic building energy data. The impact on forecast accuracy of measures to improve model data efficiency are quantified, specifically for: reuse of prediction models, reduction of training data duration, reduction of model data features, and online model training. A simple linear multi-layer perceptron model is shown to provide equivalent forecast accuracy to state-of-the-art models, with greater data efficiency and generalisability. The use of more than 2 years of training data for load prediction models provided no significant improvement in forecast accuracy. Forecast accuracy and data efficiency were improved simultaneously by using change-point analysis to screen training data. Reused models and those trained with 3 months of data had on average 10% higher error than baseline, indicating that deploying MPC systems without prior data collection may be economic.

eess.SY↗

arXiv2023

Energy Modelling and Forecasting for an Underground Agricultural Farm using a Higher Order Dynamic Mode Decomposition Approach

This paper presents an approach based on higher order dynamic mode decomposition (HODMD) to model, analyse, and forecast energy behaviour in an urban agriculture farm situated in a retrofitted London underground tunnel, where observed measurements are influenced by noisy and occasionally transient conditions. HODMD is a data-driven reduced order modelling method typically used to analyse and predict highly noisy and complex flows in fluid dynamics or any type of complex data from dynamical systems. HODMD is a recent extension of the classical dynamic mode decomposition method (DMD), customised to handle scenarios where the spectral complexity underlying the measurement data is higher than its spatial complexity, such as is the environmental behaviour of the farm. HODMD decomposes temporal data as a linear expansion of physically-meaningful DMD-modes in a semi-automatic approach, using a time-delay embedded approach. We apply HODMD to three seasonal scenarios using real data measured by sensors located at at the cross-sectional centre of the the underground farm. Through the study we revealed three physically-interpretable mode pairs that govern the environmental behaviour at the centre of the farm, consistently across environmental scenarios. Subsequently, we demonstrate how we can reconstruct the fundamental structure of the observed time-series using only these modes, and forecast for three days ahead, as one, compact and interpretable reduced-order model. We find HODMD to serve as a robust, semi-automatic modelling alternative for predictive modelling in Digital Twins.

cs.LG↗

arXiv2023

Value of Information Analysis for rationalising information gathering in building energy analysis

The use of monitored data to improve the accuracy of building energy models and operation of energy systems is ubiquitous, with topics such as building monitoring and Digital Twinning attracting substantial research attention. However, little attention has been paid to quantifying the value of the data collected against its cost. This paper argues that without a principled method for determining the value of data, its collection cannot be prioritised. It demonstrates the use of Value of Information analysis (VoI), which is a Bayesian Decision Analysis framework, to provide such a methodology for quantifying the value of data collection in the context of building energy modelling and analysis. Three energy decision-making examples are presented: ventilation scheduling, heat pump maintenance scheduling, and ground source heat pump design. These examples illustrate the use of VoI to support decision-making on data collection.

eess.SY↗

arXiv2023

A physics-based domain adaptation framework for modelling and forecasting building energy systems

State-of-the-art machine-learning-based models are a popular choice for modeling and forecasting energy behavior in buildings because given enough data, they are good at finding spatiotemporal patterns and structures even in scenarios where the complexity prohibits analytical descriptions. However, their architecture typically does not hold physical correspondence to mechanistic structures linked with governing physical phenomena. As a result, their ability to successfully generalize for unobserved timesteps depends on the representativeness of the dynamics underlying the observed system in the data, which is difficult to guarantee in real-world engineering problems such as control and energy management in digital twins. In response, we present a framework that combines lumped-parameter models in the form of linear time-invariant (LTI) state-space models (SSMs) with unsupervised reduced-order modeling in a subspace-based domain adaptation (SDA) framework. SDA is a type of transfer-learning (TL) technique, typically adopted for exploiting labeled data from one domain to predict in a different but related target domain for which labeled data is limited. We introduce a novel SDA approach where instead of labeled data, we leverage the geometric structure of the LTI SSM governed by well-known heat transfer ordinary differential equations to forecast for unobserved timesteps beyond observed measurement data. Fundamentally, our approach geometrically aligns the physics-derived and data-derived embedded subspaces closer together. In this initial exploration, we evaluate the physics-based SDA framework on a demonstrative heat conduction scenario by varying the thermophysical properties of the source and target systems to demonstrate the transferability of mechanistic models from a physics-based domain to a data domain.

cs.LG↗

arXiv2021

Continuous calibration of a digital twin: comparison of particle filter and Bayesian calibration approaches

Assimilation of continuously streamed monitored data is an essential component of a digital twin; the assimilated data are used to ensure the digital twin is a true representation of the monitored system. One way this is achieved is by calibration of simulation models, whether data-derived or physics-based, or a combination of both. Traditional manual calibration is not possible in this context hence new methods are required for continuous calibration. In this paper, a particle filter methodology for continuous calibration of the physics-based model element of a digital twin is presented and applied to an example of an underground farm. The methodology is applied to a synthetic problem with known calibration parameter values prior to being used in conjunction with monitored data. The proposed methodology is compared against static and sequential Bayesian calibration approaches and compares favourably in terms of determination of the distribution of parameter values and analysis run-times, both essential requirements. The methodology is shown to be potentially useful as a means to ensure continuing model fidelity.

cs.CE↗

arXiv2020

Slipping through the net: can data science approaches help target clean cooking policy interventions?

Reliance on solid biomass cooking fuels in India has negative health and socio-economic consequences for households, yet policies aimed at promoting uptake of LPG for cooking have not always been effective at promoting sustained transition to cleaner cooking amongst intended beneficiaries. This paper uses a two step approach combining predictive and descriptive analyses of the IHDS panel dataset to identify different groups of households that switched stove between 2004/5 and 2011/12. A tree-based ensemble machine learning predictive analysis identifies key determinants of a switch from biomass to non-biomass stoves. A descriptive clustering analysis is used to identify groups of stove-switching households that follow different transition pathways. There are three key findings of this study: Firstly non-income determinants of stove switching do not have a linear effect on stove switching, in particular variables on time of use and appliance ownership which offer a proxy for household energy practices; secondly location specific factors including region, infrastructure availability, and dwelling quality are found to be key determinants and as a result policies must be tailored to take into account local variations; thirdly clean cooking interventions must enact a range of measures to address the barriers faced by households on different energy transition pathways.

physics.soc-ph↗