A metareasoning problem involves three parts: 1) a set of concrete problem domains; 2) reasoners to reason about the problems; and, 3) metareasoners to reason about the reasoners. We believe that the metareasoning community would benefit from agreeing on the first two problems. To support this kind of collaboration, we offer an open source 3D simulator containing everyday, commonsense problems that take place in kitchens. This paper presents several arguments for using a simulator to solve commonsense problems. The paper concludes by describing future work in simulator-based unified generative benchmarks for AI.

The success of autonomous vehicles has made path planning in real, physically grounded environments an increasingly important problem. In environments where speed matters and vehicles must maneuver around obstructions, such as autonomous car navigation in hostile environments, the speed with which real vehicles can traverse a path is often dependent on the sharpness of the corners on the path as well as the length of path edges. We present an algorithm that incorporates the use of the turn angle through path nodes as a limiting factor for vehicle speed. Vehicle speed is then used in a time-weighting calculation for each edge. This allows the path planning algorithm to choose potentially longer paths, with less turns in order to minimize path traversal time. Results simulated in the Breve environment show that travel time can be reduced over the solution obtained using the Anytime D* Algorithm by approximately 10% for a vehicle that is speed limited based on turn rate.

Most of the existing weight-learning algorithms for Markov Logic Networks (MLNs) use batch training which becomes computationally expensive and even infeasible for very large datasets since the training examples may not fit in main memory. To overcome this problem, previous work has used online learning algorithms to learn weights for MLNs. However, this prior work has only applied existing online algorithms, and there is no comprehensive study of online weight learning for MLNs. In this paper, we derive new online algorithms for structured prediction using the primal-dual framework, apply them to learn weights for MLNs, and compare against existing online algorithms on two large, real-world datasets. The experimental results show that the new algorithms achieve better accuracy than existing methods.

Past educational robotics research has indicated that the use of simulators can increase students’ performance in introductory robotics programming courses. In this paper, we introduce a simulator for the iRobot Create that works on Windows PCs. It was developed to work with a Python robotics library and includes an Eclipse plugin, but can simulate any library that uses the serial Open Interface on the Create. The platform, library, and simulator are all easy to use and have been well-received initially by students.

We present a new robot platform, the Finch, that was designed to align with the learning goals and concepts taught in introductory computer science courses. The Finch was developed in the context of the CSbots program, the goal of which is to improve retention and learning in computer science courses through the use of robots and other physically embodied hardware. This paper concentrates on design constraints that were determined in earlier CSbots studies and how those constraints were instantiated by the Finch. We also present some preliminary results from pilot studies in which Finch robots were used in CS1 and CS2 classes.

In Australia, the Scientists-in-Schools program partners professional scientists with teachers from K-12 schools to improve early engagement and educational outcomes in the sciences and mathematics.  An overview of the developing syllabus of a K-6 course resulting from the pairing of a senior AI researcher with teachers from a K-6 (primary) school is presented. Now entering its third year, the course introduces the basic concepts, vocabulary and history of science generally and AI specifically in a manner that emphasises student engagement and provides a challenging but age appropriate syllabus. Reflecting on the course at this time provides an action research basis for ongoing maturation of the syllabus, and the paper is presented in that light.

In this paper, we describe the outline for a course-long information retrieval (IR) project. The project guides the students in constructing a working IR system from the ground up. The first half of the project is structured and closely follows common foundational IR concepts. During this portion of the project, a bare-bones IR system is constructed. For the last half of the project, students (in groups) implement research-driven extensions to the basic system with the additional constraint that their project must integrate with the base system. By the end, the students have worked on a large software project (~40 classes with thousands of lines of code) in a group setting as well as been introduced to the research process. This project plan has been successfully used in an undergraduate course; resources including starter code, solutions, and an example IR system with project write-ups are available.

The projects that we have developed for UC Berkeley’s introductory artificial intelligence (AI) course teach foundational concepts using the classic video game Pac-Man. There are four project topics: state-space search, multi-agent search, probabilistic inference, and reinforcement learning. Each project requires students to implement general-purpose AI algorithms and then to inject domain knowledge about the Pac- Man environment using search heuristics, evaluation functions, and feature functions. We have found that the Pac-Man theme adds consistency to the course, as well as tapping in to students’ excitement about video games.

Reasoning by the usage of mental images has been the subject of much debate in Cognitive Science, especially among the schools of depictive and descriptive imagistic representations. Whether or not reasoning with mental images involves a mechanism or a process different from language based reasoning is an important question. This paper proposes that any theory which aims for a cohesive whole needs to be constrained by neurophysiological data and such data can be obtained by the Clock Drawing Test. The Clock Drawing Test (CDT) is a screening tool for cognitive impairment and can be used as a tool to test resilience of certain factors of visual spatial representations. Thus, it can help to form an empirical case for which factors are prone to debility and which factors are not during the onset and progress of cognitive impairment from a mental representation point of view. This paper presents 50 CDT tests done on patients with cognitive impairment and analyses the results which support the case for a depictive rather than a descriptive theory for imagistic representations. Lastly, this paper proposes that there is some evidence for a more dynamic and distributed nature of representation in the observations which question the above dichotomy and can be partly explained by certain aspects of the connectionist school of thought.

The architectural approach to AI focuses on the fixed structure underlying intelligence. Applying it to statistical relational AI should further stimulate the application of statistical relational techniques across AI, while focusing research on their commonalities, (in)compatibilities and integration. It could also yield new architectures that are simpler yet more comprehensive than today’s best.