Reconstructing from parts

Human pose reconstruction using transformer architecture from partially masked data represents a chellenging task in computer vision research. Transformers, originally developed for natural language processing tasks, have shown remarkable potential in handling sequential data with long-range dependencies, making them suitable for tasks like human pose estimation. In this context, partially masked data refers to images … Continue reading Reconstructing from parts

Human behavior estimation in human robot interaction

In the realm of robotics, the interaction between humans and robots has garnered significant attention due to its potential to revolutionize various sectors such as healthcare, manufacturing, and daily living assistance. Central to this interaction is the accurate estimation of human behavior, which plays a pivotal role in enabling robots to understand and respond effectively … Continue reading Human behavior estimation in human robot interaction

Risk Assessment in AI Deployment

The deployment of Artificial Intelligence (AI) technologies is a double-edged sword. While the benefits are vast and varied, ranging from efficiency gains to new capabilities, the risks associated with AI deployment cannot be overlooked, mostly in the wake of the AI Act. Effective risk assessment is crucial to ensure that AI systems are safe, reliable, … Continue reading Risk Assessment in AI Deployment

Decoding Deception in Human-Robot Interaction

In the rapidly evolving field of Human-Robot Interaction (HRI), understanding the nuances of deception plays a pivotal role in shaping ethical frameworks and guiding responsible development. As robots increasingly become part of our daily lives, from social companions to assistive technologies, the potential for deceptive practices within these interactions warrants a closer examination. This blog … Continue reading Decoding Deception in Human-Robot Interaction

The AI Act: an Overview

The European Union (EU) AI Act represents a pioneering step towards regulating artificial intelligence (AI) across Europe, setting a global benchmark for the ethical and safe development of AI technologies. As the digital age propels us forward, the need for robust frameworks to govern AI's expansive capabilities has never been more critical. The Genesis of … Continue reading The AI Act: an Overview

One is not enough: Multimodal learning for richer information.

Unimodal deep learning focuses on processing, analyzing, and generating data from a single modality. For example, this could involve training neural nets on images, text, or audio to classify, regress, or generate on only images, text, or audio. Multimodal deep learning, on the other hand, involves integrating and jointly processing data from multiple modalities. This … Continue reading One is not enough: Multimodal learning for richer information.

Personalized robots: the ethical issues

Personalized robots learn about each user’s specific needs and abilities, to adapt their behaviors accordingly (Matarić & Scassellati, 2016). Robots that can adapt and personalize their behaviors come with advantages, but they also raise several ethical issues. This article offers a brief overview on some of the ethical challenges surrounding personalized robots, focusing on privacy, … Continue reading Personalized robots: the ethical issues

SOCIAL ROBOTS AND FACIAL EMOTIONS​

Humans express emotion through various media. Humans use their faces to present internal affective states. Humans use speech to express emotion as well. Among various types of expressions of emotions, facial expressions are predominant. Various expressions displayed on humans' faces represent different cognitive processes. In communicative or interactive conditions, humans can recognize the emotion being … Continue reading SOCIAL ROBOTS AND FACIAL EMOTIONS​

How Theory of Mind Enhances Transparency in Human-Robot Interaction

Imagine a world where robots are as common as smartphones. These robots help us with daily tasks, work alongside us, and even provide companionship. However, as much as they are part of our lives, there is often a disconnect. We see them move, act, and decide, yet we wonder, "Why did it do that?" One … Continue reading How Theory of Mind Enhances Transparency in Human-Robot Interaction

Dialogue Exchange During Vision-and-Language Navigation

Smart agents must possess the ability to interact with humans or other agents in their environment. We have proposed a computational model that can efficiently interact with an oracle while navigating in an unknown indoor environment. In this model, when the agent gets confused regarding where it should go, it prompts the dialogue model to … Continue reading Dialogue Exchange During Vision-and-Language Navigation