Panos Trahanias

Critical raw material (CRM) exploration increasingly combines Earth Observation, geophysics, geochemistry, mineral prospectivity mapping, probabilistic modelling, and autonomous sensing. However, these capabilities are commonly developed or deployed as separate components, while the explicit coupling of observation, uncertainty-aware geological inference, and subsequent exploration decisions remains comparatively underdeveloped. This paper presents Closed-Loop Mineral Intelligence (CLMI) as a conceptual and methodological framework for organising these capabilities within an iterative Observe–Model–Decide process. The contribution does not propose a new stand-alone learning algorithm or claim an operationally validated exploration system. Instead, it formalises a reference architecture in which heterogeneous observations update probabilistic geological representations, uncertainty informs the prioritisation of subsequent observations, and expert oversight remains part of the decision loop. The framework is examined through an illustrative lithium-bearing pegmatite scenario that specifies the intended information flow, candidate data sources, modelling functions, decision points, and human intervention without reporting empirical performance. A validation roadmap is further defined to make the framework testable in future case studies, including requirements for benchmark baselines, uncertainty calibration, information-gain assessment, exploration-efficiency metrics, computational feasibility, and human–AI interaction. By distinguishing established technological components from the proposed system-level integration, the paper positions CLMI as a research framework and agenda for adaptive, uncertainty-aware mineral exploration rather than as a demonstrated replacement for current professional practice.

We present INDOOR-LIDAR, a comprehensive hybrid dataset of indoor 3D LiDAR point clouds designed to advance research in robot perception. Existing indoor LiDAR datasets often suffer from limited scale, inconsistent annotation formats, and human-induced variability during data collection. INDOOR-LIDAR addresses these limitations by integrating simulated environments with real-world scans acquired using autonomous ground robots, providing consistent coverage and realistic sensor behavior under controlled variations. Each sample consists of dense point cloud data enriched with intensity measurements and KITTI-style annotations. The annotation schema encompasses common indoor object categories within various scenes. The simulated subset enables flexible configuration of layouts, point densities, and occlusions, while the real-world subset captures authentic sensor noise, clutter, and domain-specific artifacts characteristic of real indoor settings. INDOOR-LIDAR supports a wide range of applications including 3D object detection, bird's-eye-view (BEV) perception, SLAM, semantic scene understanding, and domain adaptation between simulated and real indoor domains. By bridging the gap between synthetic and real-world data, INDOOR-LIDAR establishes a scalable, realistic, and reproducible benchmark for advancing robotic perception in complex indoor environments.

Task space trajectory tracking for quadruped robots plays a crucial role on achieving dexterous maneuvers in unstructured environments. To fulfill the control objective, the robot should apply forces through the contact of the legs with the supporting surface, while maintaining its stability and controllability. In order to ensure the operation of the robot under these conditions, one has to account for the possibility of unstable contact of the legs that arises when the robot operates on partially or globally slippery terrains. In this work, we propose an adaptive trajectory tracking controller for quadruped robots, which involves two prioritized layers of adaptation for avoiding possible slippage of one or multiple legs. The adaptive framework is evaluated through simulations and validated through experiments.

During pressure support ventilation (PSV), excessive assist results in weak inspiratory efforts and promotes diaphragm atrophy and delayed weaning. The aim of this study was to develop a classifier using a neural network to identify weak inspiratory efforts during PSV, based on the ventilator waveforms. Recordings of flow, airway, esophageal and gastric pressures from critically ill patients were used to create an annotated dataset, using data from 37 patients at 2–5 different levels of support, computing the inspiratory time and effort for every breath. The complete dataset was randomly split, and data from 22 patients (45,650 breaths) were used to develop the model. Using a One-Dimensional Convolutional Neural Network, a predictive model was developed to characterize the inspiratory effort of each breath as weak or not, using a threshold of 50 cmH₂O*s/min. The following results were produced by implementing the model on data from 15 different patients (31,343 breaths). The model predicted weak inspiratory efforts with a sensitivity of 88%, specificity of 72%, positive predictive value of 40%, and negative predictive value of 96%. These results provide a ‘proof-of-concept’ for the ability of such a neural-network based predictive model to facilitate the implementation of personalized assisted ventilation.

Visual Simultaneous Localization and Mapping (vSLAM)is the method of employing an optical sensor to map the robot’s observable surroundings while also identifying the robot’s pose in relation to that map. The accuracy and speed of vSLAM calculations can have a very significant impact on the performance and effectiveness of subsequent tasks that need to be executed by the robot, making it a key building component for current robotic designs. The application of vSLAM in the area of humanoid robotics is particularly difficult due to the robot’s unsteady locomotion. This paper introduces a pose graph optimization module based on RGB (ORB) features, as an extension of the KinectFusion pipeline (a well-known vSLAM algorithm), to assist in recovering the robot’s stance during unstable gait patterns when the KinectFusion tracking system fails. We develop and test a wide range of embedded MPSoC FPGA designs, and we investigate numerous architectural improvements, both precise and approximation, to study their impact on performance and accuracy. Extensive design space exploration reveals that properly designed approximations, which exploit domain knowledge and efficient management of CPU and FPGA fabric resources, enable real-time vSLAM at more than 30 fps in humanoid robots with high energy-efficiency and without compromising robot tracking and map construction. This is the first FPGA design to achieve robust, real-time dense SLAM operation targeting specifically humanoid robots. An open source release of our implementations and data can be found in [1].

In this work we present a novel Supervised Learning scheme for executing sensitive Force-based manipulation tasks. The proposed scheme, termed SLF, is formulated as a three-stage process: (a) supervised trial-execution in simulation to acquire sufficient training data; (b) training to facilitate grasp learning with suitable robot-arm pose and lifting force; (c) grasp execution in simulation. Consequently, following sim-to-real transfer, operation in real environments is achieved in addition to simulated ones, generalizing also for objects not included in the trial sessions. The proposed learning scheme is demonstrated in object lifting tasks where the applied force varies for different objects with similar contact friction coefficients, and likewise the grasping pose. Experimental results on the manipulator YuMi show that the robot is able to effectively reproduce demanding lifting and manipulation tasks after learning is accomplished.

In the next few years, new demanding applications will be supported on mobile platforms by reconciling two conflicting requirements: high performance (often with real-time limitations) and low power consumption. The objective of the vipGPU project is to develop hardware and software technology to provide efficient support for two such application scenarios, namely (a) simultaneous localization and mapping (SLAM) in mobile robotics systems, and (b) virtual reality (VR) in portable devices to simulate serious games with emphasis on simulating surgical interventions and medical training in general. In this project, we aim at developing a new heterogeneous platform consisting of hardware accelerators for low power embedded systems optimized (at the hardware and software level) for the implementation of the two applications mentioned above.

This letter presents a novel cascade state estimation framework for the three-dimensional (3-D) center of mass (CoM) estimation of walking humanoid robots. The proposed framework, called State Estimation RObot Walking (SEROW), fuses effectively joint encoder, inertial, feet pressure, and visual odometry measurements. Initially, we consider the humanoid's Newton-Euler dynamics and rigorously derive the nonlinear CoM estimator. The latter accurately estimates the 3D-CoM position, velocity, and external forces acting on the CoM, while directly considering the presence of uneven terrain and the body's angular momentum rate and, thus, effectively coupling the frontal with the lateral plane dynamics. Furthermore, we extend an established floating mass estimator to take into account the support foot pose, yielding in such a way the mandatory, for CoM estimation, affine transformations and forming a cascade state estimation scheme. Subsequently, we quantitatively and qualitatively assess the proposed scheme by comparing it to other estimation structures in terms of accuracy and robustness to disturbances, both in simulation and on an actual NAO robot walking outdoors over an inclined terrain. To facilitate further research endeavors, our implementation is offered as an open-source ROS/C++ package.