Natural language allows robot programming to be accessible to everyone. However, the inherent fuzziness in natural language poses challenges for inflexible, traditional robot systems. We focus on instructions with fuzzy time requirements (e.g., "start in a few minutes"). Building on previous robotics research, we introduce fuzzy skills. These define an execution by the robot with so-called satisfaction functions representing vague execution time requirements. Such functions express a user's satisfaction over potential starting times for skill execution. When the robot handles multiple fuzzy skills, the satisfaction function provides a temporal tolerance window for execution, thus, enabling optimal scheduling based on satisfaction. We generalized such functions based on individual user expectations with a user study. The participants rated their satisfaction with an instruction's execution at various times. Our investigations reveal that trapezoidal functions best approximate the users' satisfaction. Additionally, the results suggest that users are more lenient if the execution is specified further into the future.

In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions. We have trained this architecture on a video game environment used as a standard test-bed for intelligent systems applications, testing it on different levels of the same game to evaluate its generalization abilities. We have measured the performance of our approach as more training data is made available, as well as compared it with both a state-of-the-art, classical planner and the standard Deep Q-Learning algorithm. The results obtained show our model performs better than the alternative methods considered, when both plan quality (plan length) and time requirements are taken into account. On the one hand, it is more sample-efficient than standard Deep Q-Learning, and it is able to generalize better across levels. On the other hand, it reduces problem-solving time when compared with a state-of-the-art automated planner, at the expense of obtaining plans with only 9% more actions.

If you had to make a list of the major things that business leaders in nearly every industry are concerned about on a daily basis, tax preparation would undoubtedly be right at the top. It's a major source of concern – whether they're worried about the effects of tax reform, the consequences of making a mistake or the sheer volume of time and effort involved in preparation to begin with, it's something that many cite as one of the biggest challenges of running a business, year after year. But what if there was a way to streamline the tax preparation process? If there was a solution that not only allowed you to automate a lot of the administrative side of tax preparation, but also reduce the possibility of human error and extract relevant information from W2s and other documents in real-time, that would be a solution worth investigating, right? The good news is that this solution already exists: it's called OCR and if your business isn't already using it to help manage your tax documents, there are a number of compelling reasons as to why now would be an excellent time to start.

Our previous discussion on augmented reality revealed a new trend in supply chain management, the use of computer-simulated imagery to enhance production and efficiency. However, the supply chain tends to forget how augmented reality will naturally transform the entire supply chain, and supply chain artificial intelligence is one of the key driving forces behind supply chain augmented reality. However, artificial intelligence is poised to radically change the supply chain in profound ways. Let's take a closer look at what artificial intelligence is and what it can offer the exciting world of supply chain management. "Alexa....please tell Baxter the Robot to machine this part."

The fastest known exact algorithms for scorebased structure discovery in Bayesian networks on n nodes run in time and space 2nnO(1). The usage of these algorithms is limited to networks on at most around 25 nodes mainly due to the space requirement. Here, we study space-time tradeoffs for finding an optimal network structure. When little space is available, we apply the Gurevich-Shelah recurrence-originally proposed for the Hamiltonian path problem-and obtain time 22n-snO(1) in space 2snO(1) for any s = n/2, n/4, n/8, . . .; we assume the indegree of each node is bounded by a constant. For the more practical setting with moderate amounts of space, we present a novel scheme. It yields running time 2n(3/2)pnO(1) in space 2n(3/4)pnO(1) for any p = 0, 1, . . ., n/2; these bounds hold as long as the indegrees are at most 0.238n. Furthermore, the latter scheme allows easy and efficient parallelization beyond previous algorithms. We also explore empirically the potential of the presented techniques.

We present current work on the NextSlidePlease slide- ware presentation tool and discuss how mixed-initiative principles may support the complex tasks of combin- ing multiple linear presentations into a network of re- lated content. We discuss future directions in two areas: supporting the layout of complex sets of interconnected slides, and refining the time requirements and content importance in these networks.

Unmanned aircraft systems use a variety of techniques to plan collision-free flight paths given a map of obstacles and no-fly zones. However, maps are not perfect and obstacles may change over time or be detected during flight, which may invalidate paths that the aircraft is already following. Thus, dynamic in-flight replanning is required. Numerous strategies can be used for replanning, where the time requirements and the plan quality associated with each strategy depend on the environment around the original flight path. In this paper, we investigate the use of machine learning techniques, in particular support vector machines, to choose the best possible replanning strategy depending on the amount of time available. The system has been implemented, integrated and tested in hardware-in-the-loop simulation with a Yamaha RMAX helicopter platform.

Insufficient knowledge and resources is not only a biological constraint on human and animal intelligence, but also has important functional implications for artificial intelligence (AI) systems. Traditional theories dominating AI research typically assume some kind of sufficiency of knowledge and resources, so cannot solve many problems in the field. AI needs new theories obeying this constraint, which cannot be obtained by minor revisions or extensions of the traditional theories. The practice of NARS, an AI project, shows that such new theories are feasible and promising in providing a new theoretical foundation for AI.