Proxemics theory argues for the importance of people regulating the distance they maintain from each other, allowing for the construction of a personal space boundary which, when violated, generates discomfort. This distance is regulated by a complex analysis mechanism that involves the fusion of cultural elements with a set of non-verbal factors, such as kinesics, haptics, and visual cues. Human comfort distance should also be considered in interactions with robotic agents. In the workplace, humans tend to tolerate variations in classic social distances (intimate, personal, social, and public) when engaging in common activities with clearly defined work-related goals. This study investigates the hypothesis that comfort distance with a robotic agent is also flexible when a joint action is underway. To test this hypothesis, an experiment involving interaction between a human participant and a collaborative robot (cobot) was conducted, in which a sense of shared interest was established through a card game. In addition to quantitative data, such as robot distance, the experiment also generates qualitative data through participants’ responses to a questionnaire about their impressions of the interaction. The findings are particularly relevant to industrial settings, where the use of cobot is increasingly in demand.

Naturally occurring events are generally characterized by dynamic states that are mostly unpredictable and undergo temporal changes. Mapping such events is essential to pursuing studies of their temporal states and eventually being able to understand and map the event occurrence. This is especially required when studying celestial events like high-velocity flybys to small bodies or performing planetary defense activities. In this work, we propose a methodology for ascertaining the optimal positions of agents to capture the most certain event occurrence fulfilled by functional agreements. To validate our methodology, we perform evaluations and comparisons with other samplers, as well as simultaneous experiments within a simulation environment and a physical analog environment at the Tartu Observatory to observe proxy cometary flyby instantaneously. The work has the potential to augment relative spacecraft positioning for intercepting pristine targets as proposed by the Comet Interceptor mission, towards optimal positioning for observing the aftermath of the DART mission or towards endeavors for sighting Apophis.

Abstract The article presents the automation of radiation surveys in the Super Proton Synchrotron (SPS) accelerator using autonomous robotic navigation techniques. The mission plan includes precise radiation monitoring along beam components; navigation along walls; crossing safety doors; maneuvering in open spaces (e.g., entrances and the beam dump area); deploying a manipulator-mounted radiation sensor; and docking or undocking at charging stations for long-term operations. Two mobile manipulators are deployed underground and operated via a multimodal telerobotic graphical user interface (GUI), which enables mission launches in Autopilot mode, supervision of operations, parameter adjustments (e.g., velocity, distances, positions), and manual intervention when required. The core contribution is the development of navigation techniques that enable fully autonomous radiation surveys, thereby enhancing safety, reducing operator workload, and standardizing measurements. Key features include an Autopilot system for the SPS arc tunnel that leverages LiDAR mapping, clustering, and visual segmentation. The article also presents solutions for automated gate crossing and parking. In complex areas—such as the beam dump area and the six access points—the SLAM Karto algorithm enables goal-directed navigation. Mapping results and techniques are discussed. Finally, the article highlights additional applications, including the use of the Autopilot during the Measurement and Inspection Robot for Accelerators (MIRA) test campaign at the DESY institute.

This paper presents the modeling, optimization and validation of a magnetic mechanism for the wall-climbing robots. Magnetic wall-climbing robots have great potential application due to the unique characteristics such as large adhesive force and loading capacity. However, researches have seldom focused on the analytical modeling and optimization of the magnetic adhesive characteristics for the adhesive mechanism, which may influence the loading capacity and motion flexibility of the whole robot greatly. Therefore, the magnetic field and adhesive force of the wall-climbing robot are systematically investigated in analytical, numerical and experimental ways, which is used for the design and optimization of adhesive mechanism. The schematic structure of the wall-climbing robot and the magnet pattern are presented. Then, the magnetic field and adhesive force are formulated based on magnetic scalar potential. Subsequently, the derived mathematical models are validated with numerical simulations, and design optimization is carried out based on the analytical models. Finally, one research prototype of the wall-climbing robot is developed, and experiments are conducted to verify the theoretical results and evaluate the adhesive performance of magnetic mechanism.

Abstract This paper presents a collision-free motion planning method for truck-trailer vehicles that integrates road networks to enable efficient exploration of large partially structured environments. It is used for autonomous maneuvering that often requires sophisticated solution strategies. Complex environments imply combinatorial search problems, which can be solved by global path planners that divide the task into multiple smaller trajectory planning steps and a graph search on a higher abstraction layer. Existing lattice-based approaches assume an unstructured environment, whereas realistic company sites usually contain isolated road networks and maneuvering spaces in a hybrid manner. Hence, in this paper, maneuvering and the use of a road network are treated at the same hierarchical level and are embedded in the global lattice planner. When the underlying graph search establishes a connection to the road network, all reachable sections of the network are explored and integrated into the graph search simultaneously. Due to the structural properties of roads, higher traveling velocities are possible and collision avoidance in presence of other moving vehicles is simplified significantly. Thus, safety, efficiency and the subjective motion quality are increased when a road network is used. Therefore an augmented graph definition is derived, as well as an adapted heuristic that preserves the optimality guarantees of lattice planners. Further expansion types are presented to improve the exploration of straight segments and to incorporate dedicated direction changes for improved executability.

Visual Simultaneous Localization and Mapping (SLAM) algorithms relying on cameras have gained significant attention with advancements in computer vision. However, existing approaches often depend on high-performance hardware, limiting their applicability in resource-constrained scenarios. This study addresses indoor planar motion applications, such as service robots and automated guided vehicles (AGV), by proposing a cost-effective Visual-Inertial SLAM(VI-SLAM) framework tailored for low-performance platforms using a low-cost binocular camera and an inertial measurement unit (IMU). A localization module is developed to enhance feature stability through inertial prediction and reprojection cross validation, using grayscale images, depth images, and IMU data. A map correction module is introduced to integrate backend optimized poses, loop closure detection, and depth information, enabling the generation of globally consistent probability grid maps via submap stitching and multi-state depth image conversion. Comprehensive evaluations are conducted on public datasets and real-world environments. The results demonstrate the accuracy, robustness, and feasibility of our approach for low-performance and low-cost devices, highlighting its potential for commercialization and practical applications.

Abstract The increasing integration of Unmanned Aerial Vehicles (UAVs) into complex projects, driven by their versatility and accessibility, requires robust mechanisms for interaction with various elements of the system during sophisticated tasks such as monitoring large-scale infrastructure and environmental inspection. This trend demands flexible integration solutions. This paper presents an open-source Ground Control Station (GCS) that serves as a crucial intermediary module, enabling the seamless integration of multi-UAV fleets with external applications working as Control Centers (CC). The GCS facilitates end-to-end automated workflows: from receiving high-level task assignments from the CC, through optimized mission planning and coordinated execution across heterogeneous UAV fleets (e.g., multicopters, VTOLs, fixed-wing, etc.), to data acquisition, processing, and the delivery of consolidated results back to the CC. Unlike many existing GCS solutions, often tied to specific autopilots or lacking straightforward integration capabilities with higher-level command systems, our approach provides a flexible and application-agnostic layer. The capabilities of the system were validated in real-world scenarios, including automated tower and power line inspections. These tests demonstrated that tasks commanded by the CC via the GCS platform were executed automatically and efficiently, as expected.

Robot grasping is a critical area of research in robotics, which aims to develop algorithms and strategies that enable robots towards reliable grasping and manipulation of objects in various environments. The ability to grasp and handle objects dexterously has wide-ranging applications in manufacturing, logistics, and healthcare. Recent advances in deep learning have paved the way for learning-based approaches toward autonomous grasping and intelligent manipulation in structured and unstructured environments. However, majority of the existing methods are designed for two-finger robotic grippers and cannot be extended towards application on three-finger robotic grippers. Three-finger grippers can perform a wide variety of grasps, and thereby require more nuanced grasp representation as compared to existing approaches. In this work, we propose a novel method towards representing underactuated three-finger grasps. A new grasp data set is also presented, specifically designed to train and evaluate three-finger robotic grasps using the proposed novel representation. A state-of-the-art deep learning architecture was trained on the dataset towards developing an end-to-end grasp planning pipeline. The proposed pipeline uses color and depth images as inputs to predict the ideal grasp pose for a three-finger robotic gripper to grasp the target object. The trained network was validated through simulation and hardware experiments, and the results were compared with an existing state-of-the-art grasp planning approach to highlight the potential of this new technique for grasp representation and planning.

Multi-task planning for diverse UAVs and missions can be approached as a Constraint Satisfaction Problem (CSP) where the Temporal CSP (TCSP) method adds time-based sequential task modeling. The Enhanced Temporal Constraint Satisfaction Problem (ETCSP) method innovatively merges dynamic domain features with a MIQP (Mixed Integer Quadratic Programming) based scoring system to optimally assign UAVs to tasks, moving beyond traditional greedy algorithms. This approach includes an enhanced forward checking method that evaluates task suitability and UAV compatibility in real-time using dynamic programming, thus refining search precision. The ETCSP model was tested in two phases, initially assigning various tasks and then employing CSP methods to monitor task changes over time. Results show that the generic TCSP method requires 61 UAVs to complete 70 tasks, while the Enhanced TCSP achieves the same with only 48 UAVs—which is roughly a 21% reduction in UAV usage. Similarly, the Enhanced method completes the task package in about 3800 min and with 1142 L of fuel, compared to 4855 min and 1615 L for the TCSP method, translating to approximately a 22% reduction in time and a 29% reduction in fuel consumption.

Abstract This paper presents a seamless indoor-outdoor localization approach for autonomous mobile robots by integrating multiple technologies: Ultra-Wideband (UWB) for high-precision indoor positioning, Global Positioning System (GPS) for outdoor global navigation, odometry for detailed granularity, and an Inertial Measurement Unit (IMU) for responsive motion tracking. The method employs loosely coupled Extended Kalman Filters (EKFs) to fuse these data sources, dynamically adjusting based on signal quality to ensure continuous and reliable localization in transition areas. Through extensive validation in simulation environments, the proposed system demonstrates the ability to mitigate the challenges posed by incomplete localization coverage in indoor-outdoor transition zones. The results show significant improvement in localization accuracy, enabling safer and more efficient robot navigation across diverse environments. Quantitative comparisons with recent studies demonstrate that our method achieves localization performance similar to tightly-coupled approaches, yet with significantly lower computational complexity, simpler implementation, greater flexibility in sensor integration, and enhanced robustness to individual sensor failures.