Toggle light / dark theme

Carnegie Mellon today showed off new research into the world of robotic navigation. With help from the team at Facebook AI Research (FAIR), the university has designed a semantic navigation that helps robots navigate around by recognizing familiar objects.

The SemExp system, which beat out Samsung to take first place in a recent Habitat ObjectNav Challenge, utilizes machine learning to train the system to recognize objects. That goes beyond simple superficial traits, however. In the example given by CMU, the robot is able to distinguish an end table from a kitchen table, and thus extrapolate in which room it’s located. That should be more straightforward, however, with a fridge, which is both pretty distinct and is largely restricted to a singe room.

“D-Theory of Time, or Digital Presentism, gives us a coherent picture of temporal ontology: In the absence of observers, the arrow of time doesn’t exist — there’s no cosmic flow of time. With that in mind, your timeless cosmic self resides as a hyperdimensional being outside the ordinary space-time dimensionality of your experiential self… In fact, if we are to create high fidelity first-person simulated realities that also may be part of intersubjectivity-based, multiplayer virtualities, D-Theory of Time gives us a clear-cut guiding principle for doing just that.” –Alex M. Vikoulov, The Physics of Time: D-Theory of Time & Temporal Mechanics.

This designer theme, #DTheoryofTime, is currently offered in a variety of 67 high-quality products from fancy home decor and wall art to stylish clothing, gadgetry and accessories for you to make a bold statement, to stand out from the crowd or to simply keep you excited throughout the day:

https://www.redbubble.com/shop/ap/48940097

The snake bites its tail

Google AI can independently discover AI methods.

Then optimizes them

It Evolves algorithms from scratch—using only basic mathematical operations—rediscovering fundamental ML techniques & showing the potential to discover novel algorithms.

AutoML-Zero: new research that that can rediscover fundamental ML techniques by searching a space of different ways of combining basic mathematical operations. Arxiv: https://arxiv.org/abs/2003.


Machine learning (ML) has seen tremendous successes recently, which were made possible by ML algorithms like deep neural networks that were discovered through years of expert research. The difficulty involved in this research fueled AutoML, a field that aims to automate the design of ML algorithms. So far, AutoML has focused on constructing solutions by combining sophisticated hand-designed components. A typical example is that of neural architecture search, a subfield in which one builds neural networks automatically out of complex layers (e.g., convolutions, batch-norm, and dropout), and the topic of much research.

Circa 2019


The European Space Agency (ESA) study is investigating how practical constructing a manned base on the moon only using 3D printing technology could be, given that it would rely primarily on lunar dirt for building materials.

“Terrestrial 3D printing technology has produced entire structures,” Laurent Pambaguian, who heads the project for ESA, said in a statement. “Our industrial team investigated if it could similarly be employed to build a lunar habitat.”

A new approach to designing motion plans for multiple robots grows “trees” in the search space to solve complex problems in a fraction of the time.

In one of the more memorable scenes from the 2002 blockbuster film Minority Report, Tom Cruise is forced to hide from a swarm of spider-like robots scouring a towering apartment complex. While most viewers are likely transfixed by the small, agile bloodhound replacements, a computer engineer might marvel instead at their elegant control system.

In a building several stories tall with numerous rooms, hundreds of obstacles and thousands of places to inspect, the several dozen robots move as one cohesive unit. They spread out in a search pattern to thoroughly check the entire building while simultaneously splitting tasks so as to not waste time doubling back on their own paths or re-checking places other robots have already visited.

Supergenes Play a Larger Role in Evolution Than Previously Thought

Massive blocks of genes—inherited together ‘plug and play’ style—may play a larger role in evolutionary adaption than previously thought, according to new research in Nature.

Biologists identified 37 of these so-called ‘supergenes’ in wild sunflower populations, and found they govern the modular transfer of a large range of traits important for adaptation to local habitats. Those include seed size, timing of flowering, as well as the ability to withstand environmental stresses such as drought or limited nutrient availability, among many others.