For several tasks, ranging from manipulation to inspection, it is beneficial for robots to localize a target object in their surroundings. In this paper, we propose an approach that utilizes coarse point clouds obtained from miniaturized VL53L5CX Time-of-Flight (ToF) sensors (tiny LiDARs) to localize a target object in the robot’s workspace. We first conduct an experimental campaign to calibrate the dependency of sensor readings on relative range and orientation to targets. We then propose a probabilistic sensor model, which we validate in an object pose estimation task using a Particle Filter (PF). The results show that the proposed sensor model improves the performance of the localization of the target object with respect to two baselines: one that assumes measurements are free from uncertainty and one in which the confidence is provided by the sensor datasheet.

Testing and validating Autonomous Vehicle (AV) performance in safety-critical and diverse scenarios is crucial before real-world deployment. However, manually creating such scenarios in simulation remains a significant and time-consuming challenge. This work introduces a novel method that generates dynamic temporal scene graphs corresponding to diverse traffic scenarios, on-demand, tailored to user-defined preferences, such as AV actions, sets of dynamic agents, and criticality levels. A temporal Graph Neural Network (GNN) model learns to predict relationships between ego-vehicle, agents, and static structures, guided by real-world spatiotemporal interaction patterns and constrained by an ontology that restricts predictions to semantically valid links. Our model consistently outperforms the baselines in accurately generating links corresponding to the requested scenarios. We render the predicted scenarios in simulation to further demonstrate their effectiveness as testing environments for AV agents.

Developing 3D semantic occupancy prediction models often relies on dense 3D annotations for supervised learning, a process that is both labor and resource-intensive, underscoring the need for label-efficient or even label-free approaches. To address this, we introduce MinkOcc, a multi-modal 3D semantic occupancy prediction framework for cameras and LiDARs that proposes a two-step semi-supervised training procedure. Here, a small dataset of explicitly 3D annotations warm-starts the training process; then, the supervision is continued by simpler-to-annotate accumulated LiDAR sweeps and images – semantically labelled through vision foundational models. MinkOcc effectively utilizes these sensor-rich supervisory cues and reduces reliance on manual labeling by 90% while maintaining competitive accuracy. In addition, the proposed model incorporates information from LiDAR and camera data through early fusion and leverages sparse convolution networks for real-time prediction. With its efficiency in both supervision and computation, we aim to extend MinkOcc beyond curated datasets, enabling broader real-world deployment of 3D semantic occupancy prediction in autonomous driving.

Foundation models (FMs) trained with different objectives and data learn diverse representations, making some more effective than others for specific downstream tasks. Existing adaptation strategies, such as parameter-efficient fine-tuning, focus on individual models and do not exploit the complementary strengths across models. Probing methods offer a promising alternative by extracting information from frozen models, but current techniques do not scale well with large feature sets and often rely on dataset-specific hyperparameter tuning. We propose Combined backBones (ComBo), a simple and scalable probing-based adapter that effectively integrates features from multiple models and layers. ComBo compresses activations from layers of one or more FMs into compact token-wise representations and processes them with a lightweight transformer for task-specific prediction. Crucially, ComBo does not require dataset-specific tuning or backpropagation through the backbone models. However, not all models are equally relevant for all tasks. To address this, we introduce a mechanism that leverages ComBo’s joint multi-backbone probing to efficiently evaluate each backbone’s task-relevance, enabling both practical model comparison and improved performance through selective adaptation. On the 19 tasks of the VTAB-1k benchmark, ComBo outperforms previous probing methods, matches or surpasses more expensive alternatives, such as distillation-based model merging, and enables efficient probing of tuned models. Our results demonstrate that ComBo offers a practical and general-purpose framework for combining diverse representations from multiple FMs.

This paper proposes a task-oriented co-design framework that integrates communication, computing, and control to address the key challenges of bandwidth limitations, noise interference, and latency in mission-critical industrial Cyber-Physical Systems (CPS). To improve communication efficiency and robustness, we design a task-oriented Joint Source-Channel Coding (JSCC) using Information Bottleneck (IB) to enhance data transmission efficiency by prioritizing task-specific information. To mitigate the perceived End-to-End (E2E) delays, we develop a Delay-Aware Trajectory-Guided Control Prediction (DTCP) strategy that integrates trajectory planning with control prediction, predicting commands based on E2E delay. Moreover, the DTCP is co-designed with task-oriented JSCC, focusing on transmitting task-specific information for timely and reliable autonomous driving. Experimental results in the CARLA simulator demonstrate that, under an E2E delay of 1 second (20 time slots), the proposed framework achieves a driving score of 48.12, which is 31.59 points higher than using Better Portable Graphics (BPG) while reducing bandwidth usage by 99.19%.

This paper is about 3D pose estimation on LiDAR scans with extremely minimal storage requirements to enable scalable mapping and localisation. We achieve this by clustering all points of segmented scans into semantic objects and representing them only with their respective centroid and semantic class. In this way, each LiDAR scan is reduced to a compact collection of four-number vectors. This abstracts away important structural information from the scenes, which is crucial for traditional registration approaches. To mitigate this, we introduce an object-matching network based on self- and cross-correlation that captures geometric and semantic relationships between entities. The respective matches allow us to recover the relative transformation between scans through weighted Singular Value Decomposition (SVD) and RANdom SAmple Consensus (RANSAC). We demonstrate that such representation is sufficient for metric localisation by registering point clouds taken under different viewpoints on the KITTI dataset, and at different periods of time localising between KITTI and KITTI-360. We achieve accurate metric estimates comparable with state-of-the-art methods with almost half the representation size, specifically 1.33 kB on average.

This paper adapts a general dataset representation technique to produce robust Visual Place Recognition (VPR) descriptors, crucial to enable real-world mobile robot localisation. Two parallel lines of work on VPR have shown, on one side, that general-purpose off-the-shelf feature representations can provide robustness to domain shifts, and, on the other, that fused information from sequences of images improves performance. In our recent work on measuring domain gaps between image datasets, we proposed a Visual Distribution of Neuron Activations (VDNA) representation to represent datasets of images. This representation can naturally handle image sequences and provides a general and granular feature representation derived from a general-purpose model. Moreover, our representation is based on tracking neuron activation values over the list of images to represent and is not limited to a particular neural network layer, therefore having access to high- and low-level concepts. This work shows how VDNAs can be used for VPR by learning a very lightweight and simple encoder to generate task-specific descriptors. Our experiments show that our representation can allow for better robustness than current solutions to serious domain shifts away from the training data distribution, such as to indoor environments and aerial imagery.

This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling (MIM) approach, which is robust to augmentation hyper-parameters and simpler than previous techniques. For neural networks used in safety-critical applications, bias in the training data can lead to errors; therefore it is crucial to understand a network’s limitations at run time and act accordingly. To this end, we test our proposed method on a number of test domains including the SAX Segmentation benchmark, which includes labelled test data from dense urban, rural and off-road driving domains. The proposed method consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark.

Learning autonomous driving capabilities requires diverse and realistic training data. This has led to exploring generative techniques as an alternative to real-world data collection. In this paper we propose a method for synthesising photo-realistic urban driving scenes, along with semantic, instance and depth ground-truth. Our model relies on Bird’s Eye View (BEV) representations due to their compositionality and scene content control capabilities, reducing the need for traditional simulators. We employ a two-stage process: first, a 3D scene representation is extracted from BEV semantic, instance and style maps using a neural field. After rendering the semantic, instance, depth and style maps from a ground-view perspective, a second stage based on a diffusion model is used to generate the photo-realistic scene. We extend our prior work - NeuralFloors, to include multiple-view outputs, style manipulation for finer control at the object level through instance-wise style maps and cross-frame consistency via auto-regressive training. The proposed system is evaluated extensively on the KITTI-360 dataset, showing improved realism and semantic alignment for generated images.

This paper introduces RobotCycle, a novel ongoing project that leverages Autonomous Vehicle (AV) research to investigate how road infrastructure influences cyclist behaviour and safety during real-world journeys. The project’s requirements were defined in collaboration with key stakeholders, including city planners, cyclists, and policymakers, informing the design of risk and safety metrics and the data collection criteria. We propose a data-driven approach relying on a novel, rich dataset of diverse traffic scenes and scenarios captured using a custom-designed wearable sensing unit. By analysing road-user trajectories, we identify normal path deviations indicating potential risks or hazardous interactions related to infrastructure elements in the environment. Our analysis correlates driving profiles and trajectory patterns with local road segments, driving conditions, and road-user interactions to predict traffic behaviours and identify critical scenarios. Moreover, by leveraging advancements in AV research, the project generates detailed 3D High-Definition Maps (HD Maps), traffic flow patterns, and trajectory models to provide a comprehensive assessment and analysis of the behaviour of all traffic agents. These data can then inform the design of cyclist-friendly road infrastructure, ultimately enhancing road safety and cyclability. The project provides valuable insights for enhancing cyclist protection and advancing sustainable urban mobility.

There is a growing academic interest as well as commercial exploitation of millimetre-wave scanning radar for autonomous vehicle localisation and scene understanding. Although several datasets to support this research area have been released, they are primarily focused on urban or semi-urban environments. Nevertheless, rugged offroad deployments are important application areas which also present unique challenges and opportunities for this sensor technology. Therefore, the Oxford Offroad Radar Dataset (OORD) presents data collected in the rugged Scottish highlands in extreme weather. The radar data we offer to the community are accompanied by GPS/INS reference – to further stimulate research in radar place recognition. In total we release over 90 GiB of radar scans as well as GPS and IMU readings by driving a diverse set of four routes over 11 forays, totalling approximately 154 km of rugged driving. This is an area increasingly explored in literature, and we therefore present and release examples of recent open-sourced radar place recognition systems and their performance on our dataset. This includes a learned neural network, the weights of which we also release. The data and tools are made freely available to the community at oxford-robotics-institute.github.io/oord-dataset

Knowing when a trained segmentation model is encountering data that is different to its training data is important. Understanding and mitigating the effects of this play an important part in their application from a performance and assurance perspective-this being a safety concern in applications such as autonomous vehicles (AVs). This work presents a segmentation network that can detect errors caused by challenging test domains without any additional annotation in a single forward pass. As annotation costs limit the diversity of labelled datasets, we use easy-to-obtain, uncurated and unlabelled data to learn to perform uncertainty estimation by selectively enforcing consistency over data augmentation. To this end, a novel segmentation benchmark based on the SAX Dataset is used, which includes labelledtestdata spanning three autonomous-driving domains, ranging in appearance from dense urban to off-road. The proposed method, named$\mathrm{\gamma }{-}\rm{SSL}$, consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark-by up to 10.7% in area under the receiver operating characteristic (ROC) curve and 19.2% in area under the precision-recall (PR) curve in the most challenging of the three scenarios.

Selecting appropriate datasets is critical in modern computer vision. However, no general-purpose tools exist to evaluate the extent to which two datasets differ. For this, we propose representing images - and by extension datasets - using Distributions of Neuron Activations (DNAs). DNAsfit distributions, such as histograms or Gaussians, to activations of neurons in a pre-trained feature extractor through which we pass the imager s) to represent. This extractor is frozen for all datasets, and we rely on its generally expressive power in feature space. By comparing two DNAs, we can evaluate the extent to which two datasets differ with granular control over the comparison attributes of interest, providing the ability to customise the way distances are measured to suit the requirements of the task at hand. Furthermore, DNAs are compact, representing datasets of any size with less than 15 megabytes. We demonstrate the value of DNAs by evaluating their applicability on several tasks, including conditional dataset comparison, synthetic image evaluation, and transfer learning, and across diverse datasets, ranging from synthetic cat images to celebrity faces and urban driving scenes.

This work explores scene graphs as a distilled representation of high-level information for autonomous driving, applied to future driver-action prediction. Given the scarcity and strong imbalance of data samples, we propose a self-supervision pipeline to infer representative and well-separated embeddings. Key aspects are interpretability and explainability; as such, we embed in our architecture attention mechanisms that can create spatial and temporal heatmaps on the scene graphs. We evaluate our system on the ROAD dataset against a fully-supervised approach, showing the superiority of our training regime.

This work proposes a fast deployment pipeline for visually-servoed robots which does not assume anything about either the robot - e.g. sizes, colour or the presence of markers - or the deployment environment. Specifically, we apply a learning based approach to reliably estimate the pose of a robot in the image frame of a 2D camera upon which a visual servoing control system can be deployed. To alleviate the time-consuming process of labelling image data, we propose a weakly supervised pipeline that can produce a vast amount of data in a small amount of time. We evaluate our approach on a dataset of remote camera images captured in various indoor environments demonstrating high tracking performances when integrated into a fully-autonomous pipeline with a simple controller. With this, we then analyse the data requirement of our approach, showing how it is possible to deploy a new robot in a new environment in fewer than 30.00 min.

The metaverse has the potential to revolutionize the next generation of the Internet by supporting highly interactive services with satisfactory user experience. The synchronization between devices in the physical world and their digital models in the metaverse is crucial. This work proposes a sampling, communication and prediction co-design framework to minimize the communication load subject to a constraint on the tracking error. To optimize the sampling rate and the prediction horizon, we exploit expert knowledge and develop a constrained deep reinforcement learning algorithm. We validate our framework on a prototype composed of a real-world robotic arm and its digital model. The results show that our framework achieves a better trade-off between the average tracking error and the average communication load compared with a communication system without sampling and prediction. For example, the average communication load can be reduced up to 87% when the average track error constraint is 0.007°. In addition, our policy outperforms the benchmark with the static sampling rate and prediction horizon optimized by exhaustive search, in terms of the tail probability of the tracking error. Furthermore, with the assistance of expert knowledge, the proposed algorithm achieves better convergence time, stability, communication load, and average tacking error.

In this paper we present a compositing image synthesis method that generates RGB canvases with well aligned segmentation maps and sparse depth maps, coupled with an in-painting network that transforms the RGB canvases into high quality RGB images and the sparse depth maps into pixel-wise dense depth maps. We benchmark our method in terms of structural alignment and image quality, showing an increase in mIoU over SOTA by 3.7 percentage points and a highly competitive FID. Furthermore, we analyse the quality of the generated data as training data for semantic segmentation and depth completion, and show that our approach is more suited for this purpose than other methods.

Masking by Moving (MByM), provides robust and accurate radar odometry measurements through an exhaustive correlative search across discretised pose candidates. However, this dense search creates a significant computational bottleneck which hinders real-time performance when high-end GPUs are not available. Utilising the translational invariance of the Fourier Transform, in our approach, Fast Masking by Moving (f-MByM), we decouple the search for angle and translation. By maintaining end-to-end differentiability a neural network is used to mask scans and trained by supervising pose prediction directly. Training faster and with less memory, utilising a decoupled search allows f-MbyM to achieve significant run-time performance improvements on a CPU (168 %) and to run in real-time on embedded devices, in stark contrast to MbyM. Throughout, our approach remains accurate and competitive with the best radar odometry variants available in the literature – achieving an end-point drift of 2.01 % in translation and 6.3 deg /km on the Oxford Radar RobotCar Dataset.

This paper is about extremely robust and lightweight localisation using LiDAR point clouds based on instance segmentation and graph matching. We model 3D point clouds as fully-connected graphs of semantically identified components where each vertex corresponds to an object instance and encodes its shape. Optimal vertex association across graphs allows for full 6-Degree-of-Freedom (DoF) pose estimation and place recognition by measuring similarity. This representation is very concise, condensing the size of maps by a factor of 25 against the state-of-the-art, requiring only 3 kB to represent a 1.4 MB laser scan. We verify the efficacy of our system on the SemanticKITTI dataset, where we achieve a new state-of-the-art in place recognition, with an average of 88.4 % recall at 100 % precision where the next closest competitor follows with 64.9 %. We also show accurate metric pose estimation performance - estimating 6-DoF pose with median errors of 10cm and 0.33 deg.

Extreme precipitation events, such as violent rainfall and hail storms, routinely ravage economies and livelihoods around the developing world. Climate change further aggravates this issue. Data-driven deep learning approaches could widen the access to accurate multi-day forecasts, to mitigate against such events. However, there is currently no benchmark dataset dedicated to the study of global precipitation forecasts. In this paper, we introduce RainBench, a new multi-modal benchmark dataset for data-driven precipitation forecasting. It includes simulated satellite data, a selection of relevant meteorological data from the ERA5 reanalysis product, and IMERG precipitation data. We also release PyRain, a library to process large precipitation datasets efficiently. We present an extensive analysis of our novel dataset and establish baseline results for two benchmark medium-range precipitation forecasting tasks. Finally, we discuss existing data-driven weather forecasting methodologies and suggest future research avenues.

In this work, a neural network is trained to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected. This is made possible by leveraging an OoD dataset with a novel contrastive objective and data augmentation scheme. By including unknown classes in the training data, a more robust feature representation is learned with known classes represented distinctly from those unknown. In comparison, when presented with unknown classes or conditions, many current approaches for segmentation frequently exhibit high confidence in their inaccurate segmentations and cannot be trusted in many operational environments. We validate our system on a real-world dataset of unusual driving scenes, and show that by selectively segmenting scenes based on what is predicted as OoD, we can increase the segmentation accuracy by an IoU of 0.2 with respect to alternative techniques.

In the latest years, Light Emitting Diode (LED)-based lighting systems have revolutionarized architectural and design applications. The setup of a complex lighting system is a typically time-consuming task due to the number of manual operations that can it requires. In this paper, we introduce a LED-display system that aims at an automatic self-configuration while allowing a simple and effortless deployment. The proposed system is based on the careless deployment (in terms of positioning) of LED strips where each LED can be individually controlled and enlightened with the desired color. Since the position of every LED is not known during the deployment, we devised an automatic configuration procedure based on computer vision to determine the position of each LED, so that the LED can act as pixels to display a generic image. The different components of the system interact by exchanging messages with the Message Queue Telemetry Transport (MQTT) protocol. An example of application is provided that shows simple images displayed using the proposed display system.

This paper presents a system for robust, large-scale topological localisation using Frequency-Modulated Continuous-Wave scanning radar which extends the state-of-the-art by an efficient, learning-based approach to handle radar data for localisation. We learn a metric space for embedding polar radar scans using CNN and NetVLAD architectures traditionally applied to the visual domain. However, we tailor the feature extraction for more suitability to the polar nature of radar scan formation using cylindrical convolutions, anti-aliasing blurring, and azimuth-wise max-pooling; all in order to bolster the rotational invariance. The enforced metric space is then used to encode a reference trajectory, serving as a map, which is queried for nearest neighbour for recognition of places at run-time. We demonstrate the performance of our topological localisation system over the course of many repeat forays using the largest radar-focused mobile autonomy dataset released to date, totalling 280 km of urban driving, a small portion of which we also use to learn the weights of the modified architecture. As this work represents a novel application for radar, we analyse the utility of the proposed method via a comprehensive set of metrics which provide insight into the efficacy when used in a realistic system, showing improved performance over the root architecture even in the face of random rotational perturbation.

This paper discusses ongoing work in demonstrating research in mobile autonomy in challenging driving scenarios. In our approach, we address fundamental technical issues to overcome critical barriers to assurance and regulation for large-scale deployments of autonomous systems. To this end, we present how we build robots that (1) can robustly sense and interpret their environment using traditional as well as unconventional sensors; (2) can assess their own capabilities; and (3), vitally in the purpose of assurance and trust, can provide causal explanations of their interpretations and assessments. As it is essential that robots are safe and trusted, we design, develop, and demonstrate fundamental technologies in real-world applications to overcome critical barriers which impede the current deployment of robots in economically and socially important areas. Finally, we describe ongoing work in the collection of an unusual, rare, and highly valuable dataset.

This paper presents an efficient annotation procedure and an application thereof to end-to-end, rich semantic segmentation of the sensed environment using Frequency-Modulated Continuous-Wave scanning radar. We advocate radar over the traditional sensors used for this task as it operates at longer ranges and is substantially more robust to adverse weather and illumination conditions. We avoid laborious manual labelling by exploiting the largest radar-focused urban autonomy dataset collected to date, correlating radar scans with RGB cameras and LiDAR sensors, for which semantic segmentation is an already consolidated procedure. The training procedure leverages a state-of-the-art natural image segmentation system which is publicly available and as such, in contrast to previous approaches, allows for the production of copious labels for the radar stream by incorporating four camera and two LiDAR streams. Additionally, the losses are computed taking into account labels to the radar sensor horizon by accumulating LiDAR returns along a pose-chain ahead and behind of the current vehicle position. Finally, we present the network with multi-channel radar scan inputs in order to deal with ephemeral and dynamic scene objects.

This paper is about fast motion estimation with scanning radar. We use weak supervision to train a focus of attention policy which actively down-samples the measurement stream before data association steps are undertaken. At training, we avoid laborious manual labelling by exploiting short-term sensor coherence from multiple poses in the presence of an external ego-motion estimator (for example, wheel odometry). In this way, we generate copious annotated measurements which can be used for training a learning algorithm in a weakly-supervised fashion. We demonstrate the validity of the approach in the context of a Radar Odometry (RO) task, pre-filtering raw data with a popular image segmentation network trained as presented. We evaluate our system against 26 km of data collected in Central Oxford and show consistent motion estimation with greatly reduced radar processing times (by a factor of 2.36).

Unintentional falls can cause severe injuries to a person, and even death, especially when no immediate assistance is provided. The aim of Fall Detection Systems (FDSs) is to detect the occurrence of a fall and to automatically and promptly request the necessary assistance. This work proposes a FDS based on wearable sensors - i.e., accelerometers and gyroscopes - and Machine Learning (ML), for sensor signal processing and detection. The process extracts a number of features on portions of the signal and classifies them as falls or regular daily activities. The classifier is a Support Vector Machine (SVM) that is trained using a manually labelled dataset, where human activities are distinguished between falls and regular activities. The method is assessed on the publicly available SisFall dataset, with extended annotation, and compared with the results obtained in the literature for the same dataset; the proposed method largely outperforms the original analysis technique proposed for the SisFall dataset, with an F1 score higher than 97% and a recall higher than 99.7%.

Received Signal Strength Indication (RSSI) is commonly used to provide distance estimates in range-based localization. In most cases, the localization systems use RSS at short range where the distance estimates are more reliable or use RSS alongside other techniques such as Time of Flight (ToF). This is so, since RSSI measurements have relatively high variance at long range and are strongly influenced by occlusions and interference in the deployment region of the Radio Frequency (RF) devices. This paper presents an overview of common filtering techniques that can be used to process RSSI readings in order to improve the accuracy of range computation from raw RSSI with minimal computational overhead. The range estimates computed from the filtered data are compared with expected values of the perturbed range/distance expressed in terms of the Cramér-Rao Lower Bound (CRLB) for RSS distance estimation. Results show that filtering can significantly improve the accuracy of range estimation, highlighting the pros and cons of the presented filtering methods at different range values.

Fuzzy logic is a powerful modelling approach to build control applications and to generate knowledge-based evaluation indices.In both cases, however, the applicability to complex systems is limited by the effort required to formulate the rules, whose number grows rapidly with the number of input variables and membership functions.This work presents a framework that implements the F-IND fuzzy model to simplify the formulation of fuzzy indices, where the rules are automatically generated on the basis of the specification of best and worst cases on the membership functions of each input variable.The paper discusses the method and presents the organization of the framework that allows automatic code generation, targeting the efficient execution of the calculations on an embedded system.The framework has been tested and validated on real hardware.

This article addresses the application of real-time scheduling to the reduction of the peak load of power consumption generated by electric loads in Cyber-Physical Energy Systems (CPES). The goal is to reduce the peak load while achieving a desired Quality of Service of the physical system under control. The considered physical processes are characterized by integrator dynamics and modelled as sporadic real-time activities. Timing constraints are obtained from physical parameters and are used to manage the activation of electric loads by a real-time scheduling algorithm. As a main contribution, an algorithm derived from the multi-processor real-time scheduling domain is proposed to efficiently deal with a high number of physical processes (i.e., electric loads), making its scalability suitable for large CPES, such as smart energy grids. The cyber-physical nature of the proposed method arises from the tight interaction between the physical processes operated by the electric loads, and the applied scheduling. To allow the use of the proposed approach in practical applications, modelling approximations and uncertainties on physical parameters are explicitly included in the model. An adaptive control strategy is proposed to guarantee the requirements on physical values under control in presence of modelling and measurement uncertainties. The compensation for such uncertainties is done by dynamically adapting the values of timing parameters used by the scheduler. Formal results have been derived to put into relationship the values of quantities describing the physical process with real-time parameters used to model and to schedule the activation of loads. The performance of the method is evaluated by means of physically accurate simulations of thermal systems, showing a remarkable reduction of the peak load and a robust enforcement of the desired physical requirements.