Search algorithms such as Rapidly-exploring Random Trees (RRTs) are common in robot programming. Including graphical representations of the output of these algorithms in a robotics framework can make the algorithms more accessible to students, and can also help programmers analyze and account for unexpected results. For this project, we used the Tekkotsu open source robot programming framework, available at Tekkotsu.org. We extended Tekkotsu’s graphical user interface for displaying vision data and maps to also display the output of an RRT search. We created several demos using two types of searches: one from a navigation path planner, and one from an arm path planner. In some cases the search had no solution, and the graphical output helped to illustrate why. This confirms the utility of the RRT visualization for explaining unexpected search results. We expect that this tool will also contribute to improved student understanding of the search algorithm.

The praying mantis uses its front legs for locomotion, prey capture and feeding. Inspired by this dexterity, we began designing a hexapod robot that could use its front legs for both locomotion and manipulation. Our current work focuses on the middle and back legs of the robot. We designed a five degree of freedom leg, using a gimbal to form three intersecting axes of rotation at the hip to imitate a ball-and-socket joint. There is also a one degree of freedom knee, and an unpowered ankle joint. A key requirement for the design is to provide for standing postures in which the robot can support itself without putting any load on the leg servos. This will increase servo life span. We simulated the leg by constructing a 3D model in SolidWorks, then importing that model into the Mirage simulator, part of the Tekkotsu robotics framework. A functioning prototype was then built using Robotis Dynamixel RX-64 servos. This was a geometrically simplified version of the original model, but it retained every motor capability of the original design. We tested the prototype using two types of pre-specified motion sequences, with good results.

This paper suggests and supports a design idea for improving dynamical navigation: adding an intermediary, adaptive obstacle representation level between perception and repeller representations. We illustrate our idea with our specific example of an adaptive obstacle representation level, which cleanly integrates into multiple existing navigation systems, treating each perceived obstacle entity as a locally sensitive, obstacle-valued function that returns an obstacle representation upon which steering and obstacle avoidance are based. Moreover, other elements of the navigation systems remain unaltered, thus preserving and extending original design virtues such as behavioral flexibility, computational efficiency, and dynamic responsiveness. Extensive simulations, validated with tests of real robots, demonstrate that our new representations compare favorably to previously employed representations on measures of effectiveness within a tested scenario, robustness over varying scenarios and ranges of parameter values, and computational efficiency.

The accuracy of an automated reading tutor in tracking the reader’s position is affected by phenomena at the frontier of the speech recognizer’s output as it evolves in real time. We define metrics of real-time tracking accuracy computed from the recognizer’s successive partial hypotheses, in contrast to previous metrics computed from the final hypothesis. We analyze the resulting considerable loss in real-time accuracy, and propose and evaluate a method to address it. Our method raises real-time accuracy from 58% to 70%, which should improve the quality of the tutor’s feedback.

Psychosocial assessments and treatments are effective for a range of psychological problems.One particular area of concern is youth suicide. This paper reports on the SAMHT intelligent tutoring system, which provides youth suicide risk assessment training.SAMHT's interactive avatar interface is based on an intelligent backend, and provides a believable interaction that is effective for training mental health professionals.

Reading tutors can provide an unprecedented opportunity to collect and analyze large amounts of data for understanding how students learn. We trained models of oral reading prosody (pitch, intensity, and duration) on a corpus of narrations of 4558 sentences by 11 fluent adults. We used these models to evaluate the oral reading prosody of 85,209 sentences read by 55 children (mostly) 7-10 years old who used Project LISTEN's Reading Tutor during the 2005-2006 school year. We mined the resulting data to pinpoint the specific common syntactic and lexical features of text that children scored best and worst on. These features predict their fluency and comprehension test scores and gains better than previous models. Focusing on these features may help human or automated tutors improve children’s fluency and comprehension more effectively.

Modeling skills are essential during the process of learning programming. ITS systems for modeling are typically hard to build due to the ill-definedness of most modeling tasks. This paper presents a system that can teach UML skills to novice programmers. The system is “simple and cheap” in the sense that it only requires an expert solution against which the student solutions are compared, but still flexible enough to accommodate certain degrees of solution flexibility and variability that are characteristic of modeling tasks. An empirical evaluation via a controlled lab study showed that the system worked fine and, while not leading to significant learning gains as compared to a control condition, still revealed some promising results.

Grimes and Warschauer (2010) describe two accuracy (Warschauer & Ware, 2006), there have been kinds of systems: automated essay scoring (AES) and relatively few evaluations of student improvement (e.g., automated writing evaluation (AWE). AES systems strive Kellogg, Whiteford, & Quinlan, 2010) or the role of to assign accurate and reliable scores to essays or specific feedback (e.g., Roscoe, Varner, Cai, Weston, Crossley, & writing features (e.g., mechanics). Scores are generated McNamara, 2011). Hence, in this paper, we explore and using various artificial intelligence (AI) methods, including describe a method for developing pedagogically-guided statistical modeling, natural language processing (NLP), algorithms that guide formative feedback in an intelligent and Latent Semantic Analysis (LSA) (Shermis & Burstein, tutor system (ITS) for writing.

In the area of student knowledge assessment, knowledge tracing is a model that has been used for over a decade to predict student knowledge and performance. Many modifications to this model have been proposed and evaluated, however, the modifications are often based on a combination of intuition and experience in the domain. This method of model improvement can be difficult for researchers without high level of domain experience and furthermore, the best improvements to the model could be unintuitive ones. Therefore, we propose a completely data driven approach to model improvement. This alternative allows for researchers to evaluate which aspects of a model are most likely to result in model performance improvement. Our results suggest a variety of different improvements to knowledge tracing many of which have not been explored.

Concept maps are frequently used in K-12 educational settings. The purpose of this study is to determine whether students’ performance on interactive concept map tasks in Guru, an intelligent tutoring system, is related to immediate and delayed learning outcomes. Guru is a dialogue-based system for high-school biology that intersperses concept map tasks within the tutorial dialogue. Results indicated that when students first attempt to complete concept maps, time spent on the maps may be a good indicator of their understanding, whereas the errors they make on their second attempts with the maps may be an indicator of the knowledge they are lacking.  This pattern of results was observed for one cycle of testing, but not replicated in a second cycle. Differences in the findings for the two testing cycles are most likely due to topic variations.