"Multi-armed bandits" offer a new paradigm for the AI-assisted design of user interfaces. To help designers understand the potential, we present the results of two experimental comparisons between bandit algorithms and random assignment. Our studies are intended to show designers how bandits algorithms are able to rapidly explore an experimental design space and automatically select the optimal design configuration. Our present focus is on the optimization of a game design space. The results of our experiments show that bandits can make data-driven design more efficient and accessible to interface designers, but that human participation is essential to ensure that AI systems optimize for the right metric. Based on our results, we introduce several design lessons that help keep human design judgment in the loop. We also consider the future of human-technology teamwork in AI-assisted design and scientific inquiry. Finally, as bandits deploy fewer low-performing conditions than typical experiments, we discuss ethical implications for bandits in large-scale experiments in education.

This paper examines a mission planning problem for a solar-powered unmanned ground vehicle (UGV) which requires the vehicle to visit a series of objective points in minimal time subject to a strict net-energy change constraint. Though related to the Traveling Salesperson Problem, the mission planning problem discussed herein imposes further complexity through additional coupled mixed-variable sets and the strict energy constraint. A scalar field representing the solar radiation of the mission environment is first characterized from a visual-spectrum image. A cascaded particle swarm optimization algorithm, coupled with the integer linear programming technique, is used to generate a time-optimized motion plan and power schedules for the UGV, which guides it to visit the assigned objective points with optimized sequence and paths, and then return to its starting location and orientation while guaranteeing compliance with the net energy gain constraint.

One consequence of rapid advances in computer technology is the obsolescence of hundreds of millions of computers each year. This paper explores strategies for increasing the reuse of outdated computers through an investigation of an 8-bit home computer that is still popular in developing countries. We observed the use of the computers in 16 households in Ahmedabad and Bangalore, India in order to gain insight into the contextual factors that support the continued popularity of the device. While most computers become obsolete in less than a decade, this 30-year-old computer technology remains useful because it provides exciting, multi-user family entertainment. While having minimal processing power and virtually no connectivity, the 8-bit computer supports input and output channels that are especially suited for co-located social game play. In contrast, PCs are primarily designed for individual use. Therefore, we offer low-cost design recommendations that would enable outdated PCs to support greater shared use and increased utility within the constrained material context of low-income households. These simple interventions, if adopted by computer refurbishment industries, have the potential to significantly extend the useful lifespan of PCs.

Online games can serve as research instruments to explore the effects of game design elements on motivation and learning. In our research, we manipulated the design of an online math game to investigate the effect of challenge on player motivation and learning. To test the \'1cInverted-U Hypothesis\'1d, which predicts that maximum game engagement will occur with moderate challenge, we produced two large-scale (10K and 70K subjects), multi-factor (2x3 and 2x9x8x4x25) online experiments. We found that, in almost all cases, subjects were more engaged and played longer when the game was easier, which seems to contradict the generality of the Inverted-U Hypothesis. Troublingly, we also found that the most engaging design conditions produced the slowest rates of learning. Based on our findings, we describe several design implications that may increase challenge-seeking in games, such as providing feedforward about the anticipated degree of challenge.