The design of a robust perception method is a substantial component towards achieving underwater human–robot collaboration. However, in complex environments such as the oceans, perception is still a challenging issue. Data‐fusion of different sensing modalities can improve perception in dynamic and unstructured ocean environments. This study addresses the control of a highly maneuverable autonomous underwater vehicle for diver tracking based on visual and acoustic signals data fusion measured by low‐cost sensors. The underwater vehicle U‐CAT tracks a diver using a 3‐degree‐of‐freedom fuzzy logic Mamdani controller. The proposed tracking approach was validated through open water real‐time experiments. Combining acoustic and visual signals for underwater target tracking provides several advantages compared to previously done related research. The obtained results suggest that the proposed solution ensures effective detection and tracking in poor visibility operating conditions.

Traversing through challenging, unstructured environments, particularly in mining scenarios characterized by dust concentration, darkness, and lack of communication presents formidable obstacles for traditional sensing technologies. Drawing inspiration from naked mole rats, characterized as being skilled subterranean navigators that depend heavily on touch to navigate their environment, this study introduces a new whisker-sensing disk designed for 3D mapping in unstructured environments. The disk comprises a circular array of 32 whisker sensors, each featuring a slender flexible plastic rod attached to a compliant base housing a 3D Hall-effect sensor. The whisker sensor is modeled using both analytical and data-driven approaches to predict rotation angles based on magnetic field measurements. The validation and comparison of both models are performed by evaluating data from other whisker sensors. Additionally, a series of experiments demonstrates the whisker disk’s capability in performing 3D-mapping tasks, along with successful implementation on diverse robotic platforms, highlighting its future potential for effective 3D mapping in complex and unstructured subterranean environments.

Object detection models rely on large-scale, high-quality annotated datasets, which are often expensive, scarce, or restricted due to privacy concerns. Synthetic data generation has emerged as an alternative, yet existing approaches have limitations: generative models lack structured annotations and precise spatial control, while game-engine-based datasets suffer from inaccuracies due to 3D bounding box projections, limited scene diversity, and poor handling of articulated objects. We propose PCGOD, an Unreal Engine-based framework that combines photorealistic rendering with comprehensive domain randomization to bridge the synthetic-to-real (sim2real) domain gap. PCGOD employs a marker-based extremity projection method that places markers at key points on object geometries and projects only visible markers to create tight-fitting bounding boxes. For articulated objects, our approach dynamically tracks skeletal pose changes, ensuring annotations adapt to varied configurations. The framework addresses sim2real transfer through six-dimensional randomization: background environments, model textures and poses, landscape textures, weather conditions, camera perspectives, and procedural scene composition. Evaluations using YOLOv11 and Salience-DETR in an object detection task demonstrate that our marker-based approach achieves up to 41.61% improvement in annotation accuracy over conventional methods. Models trained with just 10% real data supplemented by our synthetic data achieve over 80% of the performance of models trained on 100% real data. Moreover, mixed datasets containing 25% synthetic and 75% real data outperform pure real-data training by up to 5.1%. These results confirm that our approach significantly enhances synthetic data utility for object detection, offering an effective solution for domains with limited training data availability.

This work introduces a robot prototype designed to explore locomotion, perception, and navigation in unstructured terrains. The focus of this paper is on the robot’s locomotion, from concept design to realization, as well as modelling and control. The robot’s locomotion system, comprising four individually controlled archimedean screw actuators, allows holonomic planar motion control. Testing on various yielding and hard grounds has demonstrated the system’s efficacy. Additionally, 3-DOF kinematic and dynamic models were developed for pose estimation, control allocation, and numerical simulations on various terrains. Although dynamic models of archimedean screw locomotion systems have been proposed in the past, they have not been used for motion control or pose estimation. Experimental validation of the dynamic model demonstrates good performance for pose estimation, providing potential for future work on online model identification and model-based control. Furthermore, a trajectory tracking control scheme was evaluated on two distinct terrains, revealing valuable insights into the effectiveness and limitations of the proposed locomotion and trajectory tracking control scheme, and highlighting areas for future research.