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
ESR Post Blog
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
Expressing Emotions through Dialogue
Human beings often display empathy when talking to one another. They take into account the speaker’s facial expression and what they are saying to respond to them empathetically. If the speaker smiles, the human listening smiles back. If the speaker is expressing discontent or sadness, the listener listens patiently and tells the speaker that things … Continue reading Expressing Emotions through Dialogue
User’s perception of teachable robots
In Human-Robot interaction, particularly within educational settings, understanding the most effective ways to teach and interact with robots has become increasingly important. Recent research delves into the intricate dynamics of teaching methods, the complexity of tasks, and individual user characteristics, providing a comprehensive overview of how these factors influence our engagement with educational robots. This … Continue reading User’s perception of teachable robots
How to teach a robot?
In the rapidly advancing field of robotics, the ability to efficiently teach robots through various forms of feedback is revolutionizing how these machines learn and adapt to our world. Unlike traditional programming methods, which require extensive coding to modify behaviour, feedback-based teaching methods offer a more intuitive and dynamic approach. This efficiency in feedback not … Continue reading How to teach a robot?
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
Theory of Mind for Autonomous Systems
With the last two blogs, we have seen that Theory of Mind (ToM) has been extensively analyzed in psychological research to explore how people infer their own and others’ mental states. However, there is currently a growing interest in the application of ToM in robotics, particularly in social robotics that interact with humans. The idea … Continue reading Theory of Mind for Autonomous Systems
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.