Publications

Ordinary Portland cement (OPC) is a cost-effective and conventional binder that is widely adopted in brownfield site remediation and redevelopment. However, the substantial carbon dioxide emission during OPC production and the concerns about its undesirable retention capacity for potentially toxic elements strain this strategy. To tackle this objective, we herein tailored four alternative binders (calcium aluminate cement, OPC-activated ground-granulated blast-furnace slag (GGBFS), white-steel-slag activated GGBFS, and alkaline-activated GGBFS) for facilitating immobilization of high Pb content pyrite ash, with the perspectives of enhancing Pb retention and mitigating anthropogenic carbon dioxide emissions. The characterizations revealed that the incorporation of white steel slag efficiently benefits the activity of GGBFS, herein facilitating the hydration products (mainly ettringite and calcium silicate hydrates) precipitation and Pb immobilization. Further, we quantified the cradle-to-gate carbon footprint and cost analysis attributed to each binder-Pb contaminants system, finding that the application of these alternative binders could be pivotal in the envisaged carbon-neutral world if the growth of the OPC-free roadmap continues. The findings suggest that the synergistic use of recycled white steel slag and GGBFS can be proposed as a profitable and sustainable OPC-free candidate to facilitate the management of lead-contaminated brownfield sites. The overall results underscore the potential immobilization mechanisms of Pb in multiple OPC-free/substitution binder systems and highlight the urgent need to bridge the zero-emission insights to sustainable in-situ solidification/stabilization technologies.

Autonomous mobile robots can rely on several human motion detection and prediction systems for safe and efficient navigation in human environments, but the underline model architectures can have different impacts on the trustworthiness of the robot in the real world. Among existing solutions for context-aware human motion prediction, some approaches have shown the benefit of integrating symbolic knowledge with state-of-the-art neural networks. In particular, a recent neuro-symbolic architecture (NeuroSyM) has successfully embedded context with a Qualitative Trajectory Calculus (QTC) for spatial interactions representation. This work achieved better performance than neural-only baseline architectures on offline datasets. In this paper, we extend the original architecture to provide neuROSym, a ROS package for robot deployment in real-world scenarios, which can run, visualise, and evaluate previous neural-only and neuro-symbolic models for motion prediction online. We evaluated these models, NeuroSyM and a baseline SGAN, on a TIAGo robot in two scenarios with different human motion patterns. We assessed accuracy and runtime performance of the prediction models, showing a general improvement in case our neuro-symbolic architecture is used. We make the neuROSym package 1 publicly available to the robotics community.

Deploying robots in human-shared environments requires a deep understanding of how nearby agents and objects interact. Employing causal inference to model cause-and-effect relationships facilitates the prediction of human behaviours and enables the anticipation of robot interventions. However, a significant challenge arises due to the absence of implementation of existing causal discovery methods within the ROS ecosystem, the standard de-facto framework in robotics, hindering effective utilisation on real robots. To bridge this gap, in our previous work we proposed ROS-Causal, a ROS-based framework designed for onboard data collection and causal discovery in human-robot spatial interactions. In this work, we present an experimental evaluation of ROS-Causal both in simulation and on a new dataset of human-robot spatial interactions in a lab scenario, to assess its performance and effectiveness. Our analysis demonstrates the efficacy of this approach, showcasing how causal models can be extracted directly onboard by robots during data collection. The online causal models generated from the simulation are consistent with those from lab experiments. These findings can help researchers to enhance the performance of robotic systems in shared environments, firstly by studying the causal relations between variables in simulation without real people, and then facilitating the actual robot deployment in real human environments. ROS-Causal: https://lcastri.github.io/roscausal

The study of cause and effect is of the utmost importance in many branches of science, but also for many practical applications of intelligent systems. In particular, identifying causal relationships in situations that include hidden factors is a major challenge for methods that rely solely on observational data for building causal models. This article proposes CAnDOIT, a causal discovery method to reconstruct causal models using both observational and interventional time-series data. The use of interventional data in the causal analysis is crucial for real-world applications, such as robotics, where the scenario is highly complex and observational data alone are often insufficient to uncover the correct causal structure. Validation of the method is performed initially on randomly generated synthetic models and subsequently on a well-known benchmark for causal structure learning in a robotic manipulation environment. The experiments demonstrate that the approach can effectively handle data from interventions and exploit them to enhance the accuracy of the causal analysis. A Python implementation of CAnDOIT is developed and is publicly available on GitHub: https://github.com/lcastri/causalflow.

This article describes a novel technology for preserving audio documents archived on open-reel magnetic tapes forming the core of the Audio Recording Preservation (ARP) international standard. ARP is part of the Moving Picture, Audio, and Data Coding by Artificial Intelligence (MPAI) Context-based Audio Enhancement (CAE) standard, adopted by the IEEE Standard Association as IEEE 3302-2022 in December 2022. Leveraging automated Artificial Intelligence (AI) tools, ARP analyzes and extracts relevant information from digitized audio and video files of the tape’s corresponding digital Preservation Copy. This process includes identifying speed variations and surface irregularities on the tape, automatically rectifying errors to generate a restored Access Copy. By utilizing the ARP standard, archives gain a potent tool for expediting and optimizing the description of the preservation conditions of the tape, as well as automatically correcting any errors that may have occurred during the digitization process. This technology offers an efficient solution for managing both small and large collections of digitized analog items, marking a substantial advancement in the preservation of audio documents.

In SLAM (Simultaneous localization and mapping) problems, Pose Graph Optimization (PGO) is a technique to refine an initial estimate of a set of poses (positions and orientations) from a set of pairwise relative measurements. The optimization procedure can be negatively affected even by a single outlier measurement, with possible catastrophic and meaningless results. Although recent works on robust optimization aim to mitigate the presence of outlier measurements, robust solutions capable of handling large numbers of outliers are yet to come. This paper presents IPC, acronym for Incremental Probabilistic Consensus, a method that approximates the solution to the combinatorial problem of finding the maximally consistent set of measurements in an incremental fashion. It evaluates the consistency of each loop closure measurement through a consensus-based procedure, possibly applied to a subset of the global problem, where all previously integrated inlier measurements have veto power. We evaluated IPC on standard benchmarks against several state-of-the-art methods. Although it is simple and relatively easy to implement, IPC competes with or outperforms the other tested methods in handling outliers while providing online performances. We release with this paper an open-source implementation of the proposed method.

Object pose estimation is a fundamental computer vision task exploited in several robotics and augmented reality applications. Many established approaches rely on predicting 2D-3D keypoint correspondences using RANSAC (Random sample consensus) and estimating the object pose using the PnP (Perspective-n-Point) algorithm. Being RANSAC non-differentiable, correspondences cannot be directly learned in an end-to-end fashion. In this letter, we address the stereo image-based object pose estimation problem by i) introducing a differentiable RANSAC layer into a well-known monocular pose estimation network; ii) exploiting an uncertainty-driven multi-view PnP solver which can fuse information from multiple views. We evaluate our approach on a challenging public stereo object pose estimation dataset and a custom-built dataset we call Transparent Tableware Dataset (TTD), yielding state-of-the-art results against other recent approaches. Furthermore, in our ablation study, we show that the differentiable RANSAC layer plays a significant role in the accuracy of the proposed method. We release with this letter the code of our method and the TTD dataset.