Deep learning has revolutionised many fields, but it is still challenging to transfer its success to small mobile robots with minimal hardware. Specifically, some work has been done to this effect in the RoboCup humanoid football domain, but results that are performant and efficient and still generally applicable outside of this domain are lacking. We propose an approach conceptually different from those taken previously. It is based on semantic segmentation and does achieve these desired properties. In detail, it is being able to process full VGA images in real-time on a low-power mobile processor. It can further handle multiple image dimensions without retraining, it does not require specific domain knowledge for achieving a high frame rate and it is applicable on a minimal mobile hardware.

Evidence in probabilistic reasoning may be `hard' or `soft', that is, it may be of yes/no form, or it may involve a strength of belief, in the unit interval [0,1]. Reasoning with soft, $[0,1]$-valued evidence is important in many situations but may lead to different, confusing interpretations. This paper intends to bring more mathematical clarity to the field by shifting the existing focus from specification of soft evidence to accomodation of soft evidence. There are two main approaches, known as Jeffrey's rule and Pearl's method, which give different outcomes on soft evidence. This paper describes these two approaches as different ways of updating with soft evidence, highlighting their differences, similarities and applications. This account is based on a novel channel-based approach to Bayesian probability. Proper understanding of these two update mechanisms is highly relevant for inference, decision tools and probabilistic programming languages.

Computational tools to support this through proof checking, automatic theorem proving, and computer algebra are well-established, though they require formal, computationally explicit, content as input. However, the existing mathematical literature, particularly informal mathematical dialogues, and expository texts, is opaque to such systems, which cannot currently handle the variety of activities typically involved in producing such knowledge and proofs, such as, for example, exposition and argument that concerns making conjectures, forming concepts, and discussing examples and counterexamples. Our goal is to bridge this gap through devising an expressive modelling language that is closely related to the way mathematics is actually done. Our approach to modelling such content is inspired by the general-purpose argument modelling formalism Inference Anchoring Theory (IAT), introduced by Reed and Budzynska (2010). As its name suggests, IAT anchors logical inferences in discourse. IAT has been applied to mediation (Janier and Reed, 2017), debates (Budzynska et al, 2014b), and to paradoxes in ethotic argumentation (Budzynska, 2013), along with other real-world dialogues (Budzynska et al, 2013).

In the past few years, the area of Machine Learning (ML) has witnessed tremendous advancements, becoming a pervasive technology in a wide range of applications. One area that can significantly benefit from the use of ML is Combinatorial Optimization. The three pillars of constraint satisfaction and optimization problem solving, i.e., modeling, search, and optimization, can exploit ML techniques to boost their accuracy, efficiency and effectiveness. In this survey we focus on the modeling component, whose effectiveness is crucial for solving the problem. The modeling activity has been traditionally shaped by optimization and domain experts, interacting to provide realistic results. Machine Learning techniques can tremendously ease the process, and exploit the available data to either create models or refine expert-designed ones. In this survey we cover approaches that have been recently proposed to enhance the modeling process by learning either single constraints, objective functions, or the whole model. We highlight common themes to multiple approaches and draw connections with related fields of research.

The field of statistical relational learning aims at unifying logic and probability to reason and learn from data. Perhaps the most successful paradigm in the field is probabilistic logic programming: the enabling of stochastic primitives in logic programming, which is now increasingly seen to provide a declarative background to complex machine learning applications. While many systems offer inference capabilities, the more significant challenge is that of learning meaningful and interpretable symbolic representations from data. In that regard, inductive logic programming and related techniques have paved much of the way for the last few decades. Unfortunately, a major limitation of this exciting landscape is that much of the work is limited to finite-domain discrete probability distributions. Recently, a handful of systems have been extended to represent and perform inference with continuous distributions. The problem, of course, is that classical solutions for inference are either restricted to well-known parametric families (e.g., Gaussians) or resort to sampling strategies that provide correct answers only in the limit. When it comes to learning, moreover, inducing representations remains entirely open, other than "data-fitting" solutions that force-fit points to aforementioned parametric families. In this paper, we take the first steps towards inducing probabilistic logic programs for continuous and mixed discrete-continuous data, without being pigeon-holed to a fixed set of distribution families. Our key insight is to leverage techniques from piecewise polynomial function approximation theory, yielding a principled way to learn and compositionally construct density functions. We test the framework and discuss the learned representations.

Abstract-- Our recent work suggests that, thanks to nowadays powerful CNNs, image-based 2D pose estimation is a promising cue for determining pedestrian intentions such as crossing the road in the path of the ego-vehicle, stopping before entering the road, and starting to walk or bending towards the road. This statement is based on the results obtained on non-naturalistic sequences (Daimler dataset), i.e. in sequences choreographed specifically for performing the study. Fortunately, a new publicly available dataset (JAAD) has appeared recently to allow developing methods for detecting pedestrian intentions in naturalistic driving conditions; more specifically, for addressing the relevant question is the pedestrian going to cross? Accordingly, in this paper we use JAAD to assess the usefulness of 2D pose estimation for answering such a question. We combine CNN-based pedestrian detection, tracking and pose estimation to predict the crossing action from monocular images. Overall, the proposed pipeline provides new state-ofthe-art results. I. INTRODUCTION Even there is still room to improve pedestrian detection and tracking, the state-of-the-art is sufficiently mature [1], [2], [3] as to allow for increasingly focusing more on higher level tasks which are crucial in terms of (assisted or automated) driving safety and comfort. In particular, knowing the intention of a pedestrian to cross the road in front of the ego-vehicle, i.e. before the pedestrian has actually entered the road, would allow the vehicle to warn the driver or automatically perform maneuvers which are smoother and more respectful with pedestrians; it even significantly reduces the chance of injury requiring hospitalization when a vehicleto-pedestrian crash is not fully avoidable [4]. The idea can be illustrated with the support of Figure 1.

Kingdomino is introduced as an interesting game for studying game playing: the game is multiplayer (4 independent players per game); it has a limited game depth (13 moves per player); and it has limited but not insignificant interaction among players. Several strategies based on locally greedy players, Monte Carlo Evaluation (MCE), and Monte Carlo Tree Search (MCTS) are presented with variants. We examine a variation of UCT called progressive win bias and a playout policy (Player-greedy) focused on selecting good moves for the player. A thorough evaluation is done showing how the strategies perform and how to choose parameters given specific time constraints. The evaluation shows that surprisingly MCE is stronger than MCTS for a game like Kingdomino. All experiments use a cloud-native design, with a game server in a Docker container, and agents communicating using a REST-style JSON protocol. This enables a multi-language approach to separating the game state, the strategy implementations, and the coordination layer.

Technology might produce a spike in slavery, and it's not related to your smartphone addiction. The Human Rights Outlook 2018 report released on Thursday by risk consultancy Verisk Maplecroft highlights how the rise in automation and robot manufacturing could force out of their jobs millions of people in Southeast Asia, with women disproportionately affected in the garment, textile and footwear industry. In both Vietnam and Cambodia, for example, over 85% of jobs in those sectors are at high risk of automation, and over 76% of these jobs are held by women, the study says. Automation might lead to a downward spiral, making exploited workers even more vulnerable to labor abuses and an easy prey to human traffickers and slaveholders as they compete for a diminishing supply of low-skilled and low-paid jobs. "Without concrete measures from governments to adapt and educate future generations to function alongside machines, it could be a race to the bottom for many workers," Alexandra Channer, the consultancy's head of human rights, said in a statement.

The current world speed record for riding a bike down a straight, flat road was set in 2012 by a Dutch team, but the Swiss have a plan to topple their rivals -- with a little help from machine learning. An algorithm trained on aerodynamics could streamline their bike, perhaps cutting air resistance by enough to set a new record. Currently the record is held by Sebastiaan Bowier, who in 2012 set a record of 133.78 km/h, or just over 83 mph. It's hard to imagine how his bike, which looked more like a tiny landbound rocket than any kind of bicycle, could be significantly improved on. But every little bit counts when records are measured down a hundredth of a unit, and anyway, who knows but that some strange new shape might totally change the game?

Arriving at Creator, a new restaurant located on the ground floor of an office building on downtown San Francisco's Folsom Street, feels like walking into a catalog. Sleek, wooden communal tables with high white stools line one end of the room, with a bookshelf full of hand-picked culinary books against the wall and modern light fixtures overhead. It's what you would have imagined a restaurant eventually looking like if you watched a lot of The Jetsons. Those machines, with large transparent glass casings and ingredients in cylindrical tubes, are Creator's burger-making robots. Each 14-foot device contains around 350 sensors and 20 microcomputers to produce the best, freshest, locally sourced cheeseburger that $6 can get you in America's most expensive city.