Robot Programming by Human Demonstration is an intuitive programming method designed to facilitate short term robotic applications. The programmer demonstrates the task using a teaching gripper that measures the human's forces and positions, and a robot program is generated from the demonstration data. A direct approach to generating a robot program would be to simply duplicate the demonstrated trajectory, yet with this approach the robot would not be able to adapt to the environment and would also duplicate unnecessary motion included in the demonstration. This article presents an approach for identifying a range of acceptable robot force and motion trajectories from multiple human demonstrations. The resulting robot program can adapt to part misalignment in simple assembly tasks. In addition, inconsistent human motion is not duplicated by the robot, but rather is used to identify task accuracy requirements. The analysis is applied to simple assembly tasks consisting of 3D translation. For each segment of constrained motion, a range of robot compliance is identified that can adapt to part misalignment, and limit robot errors to the task accuracy requirements.

No abstract

Van Den Einde is a Teaching Professor at UCSD. She teaches core undergraduate courses in Structural Engineering, is the chair of the ABET committee responsible for the continuous curricular improvement process, incorporates education innovations into courses (Peer Instruction, Project-based learning), is responsible for TA training (preparing next generation faculty), serves as faculty advisor to student organizations, hears cases of academic misconduct as a member of the Academic Integrity Review Board, and is committed to fostering a supportive environment for diverse students at UCSD by serving on the faculty advisory board for the IDEA Student Center. Her research is focused on engagement strategies for large classrooms and the development of K-16 curriculum in earthquake engineering.c American Society for Engineering Education, 2015Page 26.1595.1 Tracking Student Engagement with a Touchscreen App for Spatial Visualization Training and Freehand Sketching AbstractThe Spatial Visualization Trainer (SVT) App was developed for an iPad to enable students to freehand sketch isometrics and orthographic projections. The App consists of an algorithm that automatically grades each sketch. When errors are made, students can redraw their sketch or take a peek at the solution, which highlights the lines in their sketch that are correct or incorrect. The objective of the App is to teach spatial visualization and freehand sketching skills, which have been show to increase retention in STEM majors, especially among under-represented and women students. A unique aspect of this App compared to other eLearning tools is that the sketching assignments are not multiple-choice, and thus require students to synthesize their complete solution. As a result, data that tracks how engaged students are at different stages of an assignment can be collected. The App was integrated into a 1-unit Spatial Visualization class consisting of 54 students. To assess learning gains, an assessment test was given at the beginning and end of the course. Overall, students' test performance increased by 7%. The group of students who started the class with low pre-test scores was investigated in more depth, since this group is often at a higher risk of dropping out of STEM majors. There was a marked bimodal distribution in this group, with one subgroup (n=6) having a 43% increase in test scores, and the other subgroup (n=7) having a drop in test scores of -4%. The largest difference between these two sub-groups was that students who did not see an increase in their post-test performance were 74% more likely to peek at a solution than try again without peeking. This peeking metric is an indication of perseverance and how engaged the students were in their learning, and could be used to alert teachers early on to students who need additional assistance in the course. This study illustrates the potential of non multiple-choice questions in an eLearning environment and can provide guidance on how to further improve eLearning tools to teach spatial visualizat...

Programming by Human Demonstration is an intuitive method of robot programming, in which the programmer demonstrates how a task is performed using a humadrobot teaching device that measures human motion, and the data gathered is used to generate the robot program. A direct duplication of the demonstrated trajectory would result in unnecessary robot motion due to human "wiggles" and unintended motion. To identify a more satisfactory robot trajectory, a method is presented that uses multiple demonstrations of the same task. Variation in human trajectories between trials is attributed to human inconsistency and is used to define an obstacle free region, by applying the Jordan curve theorem. The shortest path within the obstacle free region is determined, resulting in a shorter robot path than any of the demonstrations. Thus the presence of human inconsistency is used to improve robot performance. The analysis is restricted to planar translational motion.

No abstract