Natural pollinators, particularly honey bees, are disappearing at an unprecedented rate. This poses serious risks for agriculture, the economy, and the sustenance of humans and animals. Bees are the primary pollinators of a vast variety of crops, so their...
Researchers at CSIRO & Queensland University of Technology have recently carried out a study aimed at automatically evolving the physical structure of robots to enhance their performance in different environments. This project, funded by CSIRO's Active Integrated...
Electrical and electronic scrap (e-scrap) is now one of the fastest growing types of waste. E-scrap includes a wide array of old electronic devices that includes large household appliances such as refrigerators or air-conditioning systems, smartphones, computers and...
Researchers at Facebook have recently compiled a dataset of 5 million personas and 700 million persona-based dialogues. This database could be used to train end-to-end dialogue systems, resulting in more engaging and rich dialogues between computer agents and humans.
AI or not AI: that is the question.
Researchers at the Robert Bosch Center for Data Science and Artificial Intelligence and Center for Computational Brain Research, Indian Institute of Technology Madras, and Purdue University have recently developed a new method of reducing computational requirements...
A team of researchers at Pyrofex Corporation recently introduced Casanova, a leaderless optimistic consensus algorithm suited for use in a blockchain. Rather than producing a chain, Casanova produces blocks in a directed acyclic graph (DAG), which is essentially a...
Researchers at the Institute for Robotics and Intelligent Machines (IRIM) of the Georgia Institute of Technology have recently proposed a new framework for aggressive driving using only a monocular camera, IMU sensors and wheel speed sensors. Their approach, presented...
Researchers at ETH Zürich's Autonomous Systems Lab have recently developed a map management process for visual localization systems, specifically designed for operations in outdoor environments involving several vehicles. Their study, presented at this year's...
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...