Text-to-Image (T2I) models are being increasingly adopted in diverse global communities where they create visual representations of their unique cultures. Current T2I benchmarks primarily focus on faithfulness, aesthetics, and realism of generated images, overlooking the critical dimension of cultural competence. In this work, we introduce a framework to evaluate cultural competence of T2I models along two crucial dimensions: cultural awareness and cultural diversity, and present a scalable approach using a combination of structured knowledge bases and large language models to build a large dataset of cultural artifacts to enable this evaluation. In particular, we apply this approach to build CUBE (CUltural BEnchmark for Text-to-Image models), a first-of-its-kind benchmark to evaluate cultural competence of T2I models. CUBE covers cultural artifacts associated with 8 countries across different geo-cultural regions and along 3 concepts: cuisine, landmarks, and art. CUBE consists of 1) CUBE-1K, a set of high-quality prompts that enable the evaluation of cultural awareness, and 2) CUBE-CSpace, a larger dataset of cultural artifacts that serves as grounding to evaluate cultural diversity. We also introduce cultural diversity as a novel T2I evaluation component, leveraging quality-weighted Vendi score. Our evaluations reveal significant gaps in the cultural awareness of existing models across countries and provide valuable insights into the cultural diversity of T2I outputs for underspecified prompts. Our methodology is extendable to other cultural regions and concepts and can facilitate the development of T2I models that better cater to the global population.

We consider the problem of guiding a senior user along a path using a robotic walking assistant. This is a particular type of path following problem, for which most of the solutions available in the literature require an exact localisation of the robot in the environment. An accurate localisation is obtained either with a heavy infrastructure (e.g., an active sensing system deployed in the environment or deploying landmarks in known positions) or using SLAM approaches with a massive data collection. Our key observation is that the intervention of the system (and a good level of accuracy) is only required in proximity of difficult decision points, while we can rely on the user in an environment where the only possibility is just to maintain a course (e.g., a corridor). The direct implication is that we can instrument the environment with a heavy infrastructure only in certain areas. This design strategy has to be complemented by an adequate control law that shifts the authority (i.e., the control of the actuators) between the robot and the user according to the accuracy of the information available to the robot. Such a control law is exactly the contribution of this paper.

Assistive passive robotic walkers are naturally modelled as rear-driven bicycle with control on the front steering wheels. Standard path following algorithms used for unicycle-like robots can then be readily available, e.g. using backstepping techniques, to control the walker on desired paths. However, such an approach is usually singular in the very common situation of zero velocity, e.g. whenever the vehicle starts its motion or the user stops for any reason. The paper proposes a non-singular passive path following algorithm for an assistive robotic walker equipped with front steering wheels. The control law avoids the singularities, since it is velocity-independent, and allows the designer to specify saturation limits on the steering angles. The converging properties of the non-singular velocity-independent controller in the presence of saturation constraints are firstly formally proved and tested in simulations. Then extensive experiments performed on 14 testers are presented. These tests underline the promising performance of the proposed controller and the importance of singularities-avoidance in real-world scenarios to increase human comfort along the planned trajectory.

Robotic walkers are a particular class of devices used to assist users with physical or cognitive impairments in their navigation of large public spaces. In this context, a guidance mechanism is a controller that steers the user towards the desired path when he/she deviates. Passive guidance mechanisms do not directly propel the vehicle and leave the user in control of his/her walk. The inherent safety of passive guidance and the intuitive behaviour of the device make this class of solutions preferable to any other for robot assisted walking. The possible ways to obtain a passive behaviour in robotic walkers either require complex and expensive sensors or generate potentially rough (bang-bang) manoeuvres that are detrimental to the user's comfort. The contribution of this work is a path following controller that simulates passivity using a pair of active motors operating on the rear wheels of the walker. The system estimates and tracks the velocity desired by the user and the motors generate a rotational torque only when a turn toward the path is required. The proposed solution delivers high levels of comfort, does not rely on expensive hardware and preserves all the important properties of a passive mechanism.

This paper presents a control algorithm that steers a robotic walking assistant along a planned path using electromechanical brakes. The device is modeled as a Dubins' car, i.e., a wheeled vehicle that moves only forward in the plane and has a limited turning radius. In order to reduce the cost of the hardware, no force sensor is employed. This feature hampers the application of control algorithms based on a modulated braking action. A viable solution is based on the application of on/off braking action, thus forcing the vehicle to turn with a fixed turning radius. In order to avoid the annoying chattering behaviour, which is the inevitable companion of all bang-bang solutions, we propose a hybrid controller based on three discrete states that rule the application of the braking action. The resulting feedback controller secures a gentle convergence of the user toward the planned path and his/her steady progress towards the destination. This is obtained by using two independent hystereses thresholds, the first one associated with the approaching phase and the second with the following phases. The system convergence toward the path is formally proved. Simulations and experiments show the effectiveness of the proposed approach and the good level of comfort for the user.

Which one comes first: segmentation or recognition? We propose a unified framework for carrying out the two simultaneously and without supervision. The framework combines a flexible probabilistic model, for representing the shape and appearance of each segment, with the popular “bag of visual words” model for recognition. If applied to a collection of images, our framework can simultaneously discover the segments of each image and the correspondence between such segments, without supervision. Such recurring segments may be thought of as the “parts” of corresponding objects that appear multiple times in the image collection. Thus, the model may be used for learning new categories, detecting/classifying objects, and segmenting images, without using expensive human annotation.

We propose a simple probabilistic generative model for image segmentation. Like other probabilistic algorithms (such as EM on a mixture of Gaussians) the proposed model is principled, provides both hard and probabilistic cluster assignments, as well as the ability to naturally incorporate prior knowledge. While previous probabilistic approaches are restricted to parametric models of clusters (e.g., Gaussians) we eliminate this limitation. The suggested approach does not make heavy assumptions on the shape of the clusters and can thus handle complex structures. Our experiments show that the suggested approach outperforms previous work on a variety of image segmentation tasks.

A widespread use of three-dimensional (3-D) models in cultural heritage application requires low cost equipment and technically simple modeling procedures. In this context, methods for automatic 3-D modeling of textured objects will play a central role. Such methods need fully automatic techniques for 3-D views registration and for the removal of texture artifacts. This paper proposes a contribution in this direction based on image processing approaches. The proposed procedure is very robust and simple. It does not require special equipment or skill in order to make textured 3-D models. The results of this paper, originally conceived to address the costs issues of cultural heritage modeling, can be profitably exploited also in other modeling applications.

Exporting methods and tools used in industrial areas, where the profits can justify high modeling costs, may only be a starting point for cultural heritage modeling, but not a sustainable solution in view of the economics of this application. A way to lower the costs is to automate the modeling procedure. This work presents a robust procedure for the automatic alignment of pairs of 3D views, the first problem encountered in the modeling pipeline. The results of this paper, originally conceived to address the costs issue of cultural heritage modeling, can be profitably exploited also in other modeling applications.