Sebastián Zudaire

Alessandro Adami, Sebastian Zudaire, Ruggero Carli et al.

Constructing physically accurate simulation environments (Real2Sim) traditionally relies on manual system identification or rigid, exhaustive exploration routines. These task-agnostic pipelines often fail to leverage semantic scene context, leading to redundant physical interactions and inefficient data acquisition. In this paper, we present an autonomous, intent-driven Real2Sim framework that leverages Vision-Language Models (VLMs) for Semantic Task Decomposition. Given a high-level natural language request, an incomplete simulation description, and a visual observation, the framework autonomously identifies the minimal subset of missing physical parameters required for the simulation task. It then generates a reactive Behavior Tree (BT) composed of atomic motion and sensing primitives to selectively acquire these parameters through contact-rich robotic interaction. Extensive real-world experiments on a torque-controlled Franka Emika Panda demonstrate that our approach accurately estimates object mass, surface geometry, and derived parameters such as friction. Quantitative evaluations reveal significant operational efficiency gains compared to exhaustive baseline methods, while ablation studies confirm the robustness of the prompt architecture across different state-of-the-art VLMs. Furthermore, the reactive hierarchy of the BT acts as a deterministic safety filter, successfully mitigating generative VLM hallucinations and preventing unsafe physical anomalies. Ultimately, this work provides a scalable, efficient, and interpretable pipeline for building physics-aware digital twins directly from unstructured human intent.

Ruimin Ma, Sebastian Zudaire, Zhen Li et al.

Object 6DoF (6D) pose estimation is essential for robotic perception, especially in industrial settings. It enables robots to interact with the environment and manipulate objects. However, existing benchmarks on object 6D pose estimation primarily use everyday objects with rich textures and low-reflectivity, limiting model generalization to industrial scenarios where objects are often metallic, texture-less, and highly reflective. To address this gap, we propose a novel dataset and benchmark namely \textit{Industrial Metallic Dataset (IMD)}, tailored for industrial applications. Our dataset comprises 45 true-to-scale industrial components, captured with an RGB-D camera under natural indoor lighting and varied object arrangements to replicate real-world conditions. The benchmark supports three tasks, including video object segmentation, 6D pose tracking, and one-shot 6D pose estimation. We evaluate existing state-of-the-art models, including XMem and SAM2 for segmentation, and BundleTrack and BundleSDF for pose estimation, to assess model performance in industrial contexts. Evaluation results show that our industrial dataset is more challenging than existing household object datasets. This benchmark provides the baseline for developing and comparing segmentation and pose estimation algorithms that better generalize to industrial robotics scenarios.

Sebastián Zudaire, Leandro Nahabedian, Sebastián Uchitel

The design of systems that can change their behaviour to account for scenarios that were not foreseen at design time remains an open challenge. In this paper we propose an approach for adaptation of mobile robot missions that is not constrained to a predefined set of mission evolutions. We propose applying the MORPH adaptive software architecture to UAVs and show how controller synthesis can be used both to guarantee correct transitioning from the old to the new mission goals while architectural reconfiguration to include new software actuators and sensors if necessary. The architecture brings together architectural concepts that are commonplace in robotics such as temporal planning, discrete, hybrid and continuous control layers together with architectural concepts from adaptive systems such as runtime models and runtime synthesis. We validate the architecture flying several missions taken from the robotic literature for different real and simulated UAVs.

Tomás Liendro, Sebastián Zudaire

Robotic research over the last decades have lead us to different architectures to automatically synthesise discrete event controllers and implement these motion and task plans in real-world robot scenarios. However, these architectures usually build on existing robot hardware, generating as a result solutions that are influenced and/or restricted in their design by the available capabilities and sensors. In contrast to these approaches, we propose a design methodology that, given a specific domain of application, allowed us to build the first end-to-end implementation of an autonomous robot system that uses discrete event controller synthesis to generate assured mission plans. We validate this robot system in several missions of our target domain of application.

Sebastián Zudaire, Martín Garrett, Sebastián Uchitel

Temporal logic task planning for robotic systems suffers from state explosion when specifications involve large numbers of discrete locations. We provide a novel approach, particularly suited for tasks specifications with universally quantified locations, that has constant time with respect to the number of locations, enabling synthesis of plans for an arbitrary number of them. We propose a hybrid control framework that uses an iterator to manage the discretised workspace hiding it from a plan enacted by a discrete event controller. A downside of our approach is that it incurs in increased overhead when executing a synthesised plan. We demonstrate that the overhead is reasonable for missions of a fixed-wing Unmanned Aerial Vehicle in simulated and real scenarios for up to 700000 locations.