Several real-world tasks have sparse rewards and this poses challenges for the development of reinforcement learning (RL) algorithms. A solution to this problem is to allow an agent to autonomously create a reward for itself, making rewards denser and more suitable...
Researchers at the Reconfigurable Robotics Lab (RRL) of École Polytechnique Fédèrale de Lausanne (EPFL) have recently developed a new approach for the reconfiguration of modular robots that is inspired by the art of origami. This method, outlined in a paper published...
A team of researchers at Yale University has recently developed a robotic system capable of representing, learning and inferring ownership relations and norms. Their study, pre-published on arXiv, addresses some of the complex challenges associated with teaching...
A team of researchers at Yamagata University and Teikyo University of Science, in Japan, have recently developed a new roving biologger, or whale rover, which can travel along a sperm whale's body surface and collect valuable behavioral data. Biologging entails the...
Researchers at Cornell University and the University of California, Berkeley, have developed an a method to automatically generate motions with which robots can express their inability to complete a given task. These generated motions clearly communicate both what...
Every day, millions of articles are published on social media and other platforms, receiving a vast amounts of clicks and shares from users navigating the web. Many of these articles contain useful information that, if extracted, could be used to compile knowledge...
A team of researchers at North Carolina State University has recently carried out an empirical analysis of the executable status of Python code snippets shared on GitHub. Their study, pre-published on arXiv, also presents Gistable, a new database of executable Python...
Humans have the innate ability to predict the effect of collisions, merely using their common sense. In many cases, humans can even predict the results of similar collisions in situations in which mass, friction, or other factors vary. Could machines also attain a...
Over the past few years, classical convolutional neural networks (cCNNs) have led to remarkable advances in computer vision. Many of these algorithms can now categorize objects in good quality images with high accuracy.
Hybrid systems are systems that exhibit both continuous and discrete dynamic behavior, allowing more flexibility in modeling dynamic phenomena. Hybrid systems modeling languages are widely used for the development of cyber-physical systems, in which control software...