Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. The latest version of the self-solving Rubik's Cube is adorable in how it tries to throw itself off of the table it's solving itself on: Not exactly an optimised solve, but we'll forgive it, because that just means we get to watch it for longer. And here's what it looks like if you're holding it: When you think of robotics, you likely think of something rigid, heavy, and built for a specific purpose.

For those outside the fold, the Rubik's cube is cognitive kryptonite. Until this week, I'd certainly never solved one. Even now, saying that I solved a Rubik's cube feels like a grievous overstatement of my accomplishments. The truth is that we--a patient pre-teen "cuber" whose solve time is 47 seconds, her slightly-less-patient middle school teacher (whose solve time, she's embarrassed to admit, is closer to a minute and a half), and me--completed a cube together. The site of my public humiliation could not have been more incongruous with the task at hand.

Aging population ratios are rising significantly. Meanwhile, smart home based health monitoring services are evolving rapidly to become a viable alternative to traditional healthcare solutions. Such services can augment qualitative analyses done by gerontologists with quantitative data. Hence, the recognition of Activities of Daily Living (ADL) has become an active domain of research in recent times. For a system to perform human activity recognition in a real-world environment, multiple requirements exist, such as scalability, robustness, ability to deal with uncertainty (e.g., missing sensor data), to operate with multi-occupants and to take into account their privacy and security. This paper attempts to address the requirements of scalability and robustness, by describing a reasoning mechanism based on modular spatial and/or temporal context models as a network of ontologies. The reasoning mechanism has been implemented in a smart home system referred to as Arianna+. The paper presents and discusses a use case, and experiments are performed on a simulated dataset, to showcase Arianna+'s modularity feature, internal working, and computational performance. Results indicate scalability and robustness for human activity recognition processes.

While the machine learning literature dedicated to fully automated reasoning algorithms is abundant, the number of methods enabling the inference process on the basis of previously defined knowledge structures is scanter. Fuzzy Cognitive Maps (FCMs) are neural networks that can be exploited towards this goal because of their flexibility to handle external knowledge. However, FCMs suffer from a number of issues that range from the limited prediction horizon to the absence of theoretically sound learning algorithms able to produce accurate predictions. In this paper, we propose a neural network system named Short-term Cognitive Networks that tackle some of these limitations. In our model weights are not constricted and may have a causal nature or not. As a second contribution, we present a nonsynaptic learning algorithm to improve the network performance without modifying the previously defined weights. Moreover, we derive a stop condition to prevent the learning algorithm from iterating without decreasing the simulation error.

Independent component analysis (ICA) is a statistical method for transforming an observable multi-dimensional random vector into components that are as statistically independent as possible from each other. Usually the ICA framework assumes a model according to which the observations are generated (such as a linear transformation with additive noise). ICA over finite fields is a special case of ICA in which both the observations and the independent components are over a finite alphabet. In this thesis we consider a formulation of the finite-field case in which an observation vector is decomposed to its independent components (as much as possible) with no prior assumption on the way it was generated. This generalization is also known as Barlow's minimal redundancy representation and is considered an open problem. We propose several theorems and show that this hard problem can be accurately solved with a branch and bound search tree algorithm, or tightly approximated with a series of linear problems. Moreover, we show that there exists a simple transformation (namely, order permutation) which provides a greedy yet very effective approximation of the optimal solution. We further show that while not every random vector can be efficiently decomposed into independent components, the vast majority of vectors do decompose very well (that is, within a small constant cost), as the dimension increases. In addition, we show that we may practically achieve this favorable constant cost with a complexity that is asymptotically linear in the alphabet size. Our contribution provides the first efficient set of solutions to Barlow's problem with theoretical and computational guarantees. Finally, we demonstrate our suggested framework in multiple source coding applications.

A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art results in various environments. We also train our agent entirely inside of an environment generated by its own internal world model, and transfer this policy back into the actual environment. Interactive version of paper at https://worldmodels.github.io

In this paper, we investigate the problem of synthesizing strategies for linear temporal logic (LTL) specifications that are interpreted over finite traces -- a problem that is central to the automated construction of controllers, robot programs, and business processes. We study a natural variant of the finite LTL synthesis problem in which strategy guarantees are predicated on specified environment behavior. We further explore a quantitative extension of LTL that supports specification of quality measures, utilizing it to synthesize high-quality strategies. We propose new notions of optimality and associated algorithms that yield strategies that best satisfy specified quality measures. Our algorithms utilize an automata-game approach, positioning them well for future implementation via existing state-of-the-art techniques.

From facial recognition for unlocking our smartphones to speech recognition and intent analysis for voice assistance, artificial intelligence is all around us today. In the business world, AI is helping us uncover new insight from data and enhance decision-making. For example, online retailers use AI to recommend new products to consumers based on past purchases. And, banks use conversational AI to interact with clients and enhance their customer experiences. However, most of the AI in use now is "narrow AI," meaning it is only capable of performing individual tasks. In contrast, general AI – which is not available yet – can replicate human thought and function, taking emotions and judgment into account.

Donald Trump has a lot more to worry about than just Robert Mueller. That much has been clear since April, when details began to emerge from public court filings regarding the FBI raid on Trump's personal attorney, Michael Cohen, who pleaded guilty on Tuesday to a number of criminal charges, including some stemming from his work for Trump. Instead, it was carried out by FBI agents acting in coordination with Robert S. Khuzami, a deputy U.S. attorney in the Southern District of New York. Mueller had referred the Cohen case to Khuzami's office, but that was as far as his involvement apparently went. As I wrote at the time, the distribution of the investigation to a second office served to "potentially inoculate [it] from Trump's attacks against Mueller and potential meddling in the broader Russia investigation." Samuel W. Buell, the former lead Enron prosecutor, told me that would make it much more difficult to kill the investigation with a Saturday Night Massacre–style firing spree.