Camera-centric perception has matured into a cornerstone of modern autonomy, from self-driving cars and factory cobots to underwater and planetary exploration. This review synthesizes more than a decade of progress in vision-based robotic navigation through an engineering lens, charting the full pipeline from sensing to deployment. We first examine the expanding sensor palette—monocular and multi-camera rigs, stereo and RGB-D devices, LiDAR–camera hybrids, event cameras, and infrared systems—highlighting the complementary operating envelopes and the rise of learning-based depth inference. The advances in visual localization and mapping are then analyzed, contrasting sparse and dense SLAM approaches, as well as monocular, stereo, and visual–inertial formulations. Additional topics include loop closure, semantic mapping, and LiDAR–visual–inertial fusion, which enables drift-free operation in dynamic environments. Building on these foundations, we review the navigation and control strategies, spanning classical planning, reinforcement and imitation learning, hybrid topological–metric memories, and emerging visual language guidance. Application case studies—autonomous driving, industrial manipulation, autonomous underwater vehicles, planetary rovers, aerial drones, and humanoids—demonstrate how tailored sensor suites and algorithms meet domain-specific constraints. Finally, the future research trajectories are distilled: generative AI for synthetic training data and scene completion; high-density 3D perception with solid-state LiDAR and neural implicit representations; event-based vision for ultra-fast control; and human-centric autonomy in next-generation robots. By providing a unified taxonomy, a comparative analysis, and engineering guidelines, this review aims to inform researchers and practitioners designing robust, scalable, vision-driven robotic systems.

Mixed Reality (MR) technology is experiencing significant growth in the industrial and healthcare sectors. The headset HoloLens 2 displays virtual objects (in the form of holograms) in the user’s environment in real-time. Individuals with Autism Spectrum Disorder (ASD) exhibit, according to the DSM-5, persistent deficits in communication and social interaction, as well as a different sensitivity compared to neurotypical (NT) individuals. This study aims to propose a method for familiarizing eleven individuals with severe ASD with the HoloLens 2 headset and the use of MR technology through a tutorial. The secondary objective is to obtain quantitative learning indicators in MR, such as execution speed and eye tracking (ET), by comparing individuals with ASD to neurotypical individuals. We observed that 81.81% of individuals with ASD successfully familiarized themselves with MR after several sessions. Furthermore, the visual activity of individuals with ASD did not differ from that of neurotypical individuals when they successfully familiarized themselves. This study thus offers new perspectives on skill acquisition indicators useful for supporting neurodevelopmental disorders. It contributes to a better understanding of the neural mechanisms underlying learning in MR for individuals with ASD.

Facial movements are crucial for human interaction because they provide relevant information on verbal and non-verbal communication and social interactions. From a clinical point of view, the analysis of facial movements is important for diagnosis, follow-up, drug therapy, and surgical treatment. Current methods of assessing facial palsy are either (i) objective but inaccurate, (ii) subjective and, thus, depending on the clinician’s level of experience, or (iii) based on static data. To address the aforementioned problems, we implemented a deep learning algorithm to assess facial movements during smiling. Such a model was trained on a dataset that contains healthy smiles only following an anomaly detection strategy. Generally speaking, the degree of anomaly is computed by comparing the model’s suggested healthy smile with the person’s actual smile. The experimentation showed that the model successfully computed a high degree of anomaly when assessing the patients’ smiles. Furthermore, a graphical user interface was developed to test its practical usage in a clinical routine. In conclusion, we present a deep learning model, implemented on open-source software, designed to help clinicians to assess facial movements.

Robotic navigation is the aspect of cognition related to robot robust mobility, combining perception, some knowledge on the environment and a set of goal poses to reliably control the robot during a mission that involves displacement. Vision-based autonomous navigation is an instantiation of the latter discipline where visual perception is used to control the robot and to represent the environment. This paper presents a vision-based navigation system that uses its onboard camera to navigate and a visual path that represents the scene with a set of images. Being a memory-based system, the navigation is conceived as a concatenation of positioning tasks in the visual servoing scheme. The novelty on the proposed system relies on the generation of the images that compose the visual path which are rendered from a preobtained model of the scene. The experiments that evaluate the performance of the system are conducted over three different scenes, contemplating indoor and outdoor environments, and using a commercial Unmanned Aerial Vehicle as testbed.

Robust indoor robot navigation typically demands either costly sensors or extensive training data. We propose a cost-effective RGB-D navigation pipeline that couples feature-based relative pose estimation with a lightweight multi-layer-perceptron (MLP) policy. RGB-D keyframes extracted from human-driven traversals form nodes of a topological map; edges are added when visual similarity and geometric–kinematic constraints are jointly satisfied. During autonomy, LightGlue features and SVD give six-DoF relative pose to the active keyframe, and the MLP predicts one of four discrete actions. Low visual similarity or detected obstacles trigger graph editing and Dijkstra replanning in real time. Across eight tasks in four Habitat-Sim environments, the agent covered 190.44 m, replanning when required, and consistently stopped within 0.1 m of the goal while running on commodity hardware. An information-theoretic analysis over the Multi-Illumination dataset shows that LightGlue maximizes per-second information gain under lighting changes, motivating its selection. The modular design attains reliable navigation without metric SLAM or large-scale learning, and seamlessly accommodates future perception or policy upgrades.