Search

For humans and robots to form an effective human-robot team (HRT) there must be sufficient trust between team members throughout a mission. We analyze data from an HRT experiment focused on trust dynamics in teams of one human and two robots, where trust was manipulated by robots becoming temporarily unresponsive. Whole-body movement tracking was achieved using ultrasound beacons, alongside communications and performance logs from a human-robot interface. We find evidence that synchronization between time series of human-robot movement, within a certain spatial proximity, is correlated with changes in self-reported trust. This suggests that the interplay of proxemics and kinesics, i.e. moving together through space, where implicit communication via coordination can occur, could play a role in building and maintaining trust in human-robot teams. Thus, quantitative indicators of coordination dynamics between team members could be used to predict trust over time and also provide early warning signals of the need for timely trust repair if trust is damaged. Hence, we aim to develop the metrology of trust in mobile human-robot teams.

Metric magnitude is a measure of the "size" of point clouds with many desirable geometric properties. It has been adapted to various mathematical contexts and recent work suggests that it can enhance machine learning and optimization algorithms. But its usability is limited due to the computational cost when the dataset is large or when the computation must be carried out repeatedly (e.g. in model training). In this paper, we study the magnitude computation problem, and show efficient ways of approximating it. We show that it can be cast as a convex optimization problem, but not as a submodular optimization. The paper describes two new algorithms - an iterative approximation algorithm that converges fast and is accurate, and a subset selection method that makes the computation even faster. It has been previously proposed that magnitude of model sequences generated during stochastic gradient descent is correlated to generalization gap. Extension of this result using our more scalable algorithms shows that longer sequences in fact bear higher correlations. We also describe new applications of magnitude in machine learning - as an effective regularizer for neural network training, and as a novel clustering criterion.

Integrating robots into teams of humans is anticipated to bring significant capability improvements for tasks such as searching potentially hazardous buildings. Trust between humans and robots is recognized as a key enabler for human-robot teaming (HRT) activity: if trust during a mission falls below sufficient levels for cooperative tasks to be completed, it could critically affect success. Changes in trust could be particularly problematic in teams that have formed on an ad hoc basis (as might be expected in emergency situations) where team members may not have previously worked together. In such ad hoc teams, a foundational level of 'swift trust' may be fragile and challenging to sustain in the face of inevitable setbacks. We present results of an experiment focused on understanding trust building, violation and repair processes in ad hoc teams (one human and two robots). Trust violation occurred through robots becoming unresponsive, with limited communication and feedback. We perform exploratory analysis of a variety of data, including communications and performance logs, trust surveys and post-experiment interviews, toward understanding how autonomous systems can be designed into interdependent ad hoc human-robot teams where swift trust can be sustained.

As of 2023, 43.6 million borrowers owe more than $1.7 trillion in student loan debt. However, there is another, often overlooked, institutional debt that students may owe their former institutions after stopping out. It is estimated that 6.6 million students owe $15 billion in unpaid balances to their institutions. This institutional debt stems from various parts of campus including tuition balances, library fees, or parking fines, among others. Typically resulting in registration and transcript holds, institutional debt limits students' ability to access their transcripts, causing "stranded credits." These institutional debts can hamstring students' ability to complete their credential, transfer to a new program, apply for scholarships, or show proof of their education to potential employers. This report introduces students with stranded credits who were eligible to return to college through the Ohio Compact and provides a glimpse into their circumstances outside of the classroom. The authors share the findings of their survey and describe the hurdles these learners face when once again pursuing their postsecondary degree. They then discuss the types of support vital to the persistence and retention of these students. Finally, the authors conclude by examining the importance of academic and non-academic supports for individuals with stranded credits in their educational journey.

Is it possible to restructure the non-linear activation functions in a deep network to create hardware-efficient models? To address this question, we propose a new paradigm called Restructurable Activation Networks (RANs) that manipulate the amount of non-linearity in models to improve their hardware-awareness and efficiency. First, we propose RAN-explicit (RAN-e) -- a new hardware-aware search space and a semi-automatic search algorithm -- to replace inefficient blocks with hardware-aware blocks. Next, we propose a training-free model scaling method called RAN-implicit (RAN-i) where we theoretically prove the link between network topology and its expressivity in terms of number of non-linear units. We demonstrate that our networks achieve state-of-the-art results on ImageNet at different scales and for several types of hardware. For example, compared to EfficientNet-Lite-B0, RAN-e achieves a similar accuracy while improving Frames-Per-Second (FPS) by 1.5x on Arm micro-NPUs. On the other hand, RAN-i demonstrates up to 2x reduction in #MACs over ConvNexts with a similar or better accuracy. We also show that RAN-i achieves nearly 40% higher FPS than ConvNext on Arm-based datacenter CPUs. Finally, RAN-i based object detection networks achieve a similar or higher mAP and up to 33% higher FPS on datacenter CPUs compared to ConvNext based models. The code to train and evaluate RANs and the pretrained networks are available at https://github.com/ARM-software/ML-restructurable-activation-networks., Comment: This work was presented at an Arm AI virtual tech talk. Video is available at https://www.youtube.com/watch?v=EUqFNE28Kq4

The Texas Student Success Program Inventory (SSPI), available at https://www.highered.texas.gov/sspi, is an online database of information related to student success programs at public colleges and universities, commissioned by the Texas Higher Education Coordinating Board (THECB). Consistent with nearly every other state, prior to the creation of the SSPI, there was no organized source of information about student success programming in Texas. By creating a user-friendly tool for publicly sharing information, the SSPI is intended to push forward collaboration and innovation in student success programming and help the state accomplish the goals laid out in its 2022-2030 strategic plan, Building a Talent Strong Texas. Public undergraduate-serving institutions were invited to nominate their most impactful and innovative student success programs for inclusion within the inventory. Following this nomination process, Ithaka S+R asked program staff to provide detailed information about each program, including eligibility criteria, funding sources, and program outcomes. The SSPI currently houses information from 244 programs across 74 institutions in Texas. The review of the student success program data resulted in the following observations: (1) More programs concentrate on retention and persistence, academic performance, and student belonging and well-being than on objectives such as credential attainment, affordability, and post-completion goals; (2) The majority of programs in the inventory target low-income students, first-generation students, and students of color; (3) Programming centered on mentorship and academic goal setting and planning is the most prevalent in the inventory; (4) Programs in the inventory often depend on one funder, typically a funder within the institution; and (5) Roughly two-thirds of respondents indicated that data on student outcomes had already been collected or were being collected pertaining to their program.

As radio-frequency (RF) antenna, component and processing capabilities increase, the ability to perform multiple RF system functions from a common aperture is being realized. Conducting both radar and communications from the same system is potentially useful in vehicular, health monitoring, and surveillance settings. This paper considers multiple-input-multiple-output (MIMO) dual-function radar-communication (DFRC) systems in which the radar and communication modes use distinct baseband waveforms. A transmit precoder provides spatial multiplexing and power allocation among the radar and communication modes. Multiple precoder design approaches are introduced for a radar detection mode in which a total search volume is divided into dwells to be searched sequentially. The approaches are designed to enforce a reliance on radar waveforms for sensing purposes, yielding improved approximation of desired ambiguity functions over prior methods found in the literature. The methods are also shown via simulation to enable design flexibility, allowing for prioritization of either subsystem and specification of a desired level of radar or communication performance., Comment: 15 pages, 15 figures. This work has been submitted to the IEEE Transactions on Signal Processing for possible publication

Autonomous systems are highly vulnerable to a variety of adversarial attacks on Deep Neural Networks (DNNs). Training-free model-agnostic defenses have recently gained popularity due to their speed, ease of deployment, and ability to work across many DNNs. To this end, a new technique has emerged for mitigating attacks on image classification DNNs, namely, preprocessing adversarial images using super resolution -- upscaling low-quality inputs into high-resolution images. This defense requires running both image classifiers and super resolution models on constrained autonomous systems. However, super resolution incurs a heavy computational cost. Therefore, in this paper, we investigate the following question: Does the robustness of image classifiers suffer if we use tiny super resolution models? To answer this, we first review a recent work called Super-Efficient Super Resolution (SESR) that achieves similar or better image quality than prior art while requiring 2x to 330x fewer Multiply-Accumulate (MAC) operations. We demonstrate that despite being orders of magnitude smaller than existing models, SESR achieves the same level of robustness as significantly larger networks. Finally, we estimate end-to-end performance of super resolution-based defenses on a commercial Arm Ethos-U55 micro-NPU. Our findings show that SESR achieves nearly 3x higher FPS than a baseline while achieving similar robustness., Comment: This preprint is for personal use only. The official article will appear in proceedings of Design, Automation & Test in Europe (DATE), 2022, as part of the Special Initiative on Autonomous Systems Design (ASD)

As Mississippi prepares to support the statewide postsecondary attainment goal, understanding the returns to higher education is crucial to determining where to invest resources. Ithaka S+R has partnered with the Woodward Hines Education Foundation to provide Mississippi policymakers, advocates, and legislators with information they need to make strategic investments in postsecondary education that can increase attainment of high-value postsecondary credentials, especially amongst lower-income Mississippians, people of color, and residents in rural communities, ultimately strengthening the labor market by supplying an educated, trained workforce to meet current and future demands. To understand how postsecondary investments can best serve the needs of individuals and the state, this analysis seeks to answer three central questions: (1) what are the individual returns to higher education in the state; (2) what are the statewide economic returns to higher education; and (3) how can we plan for future investments in high-opportunity credentials? Based on the analysis, the report concludes with three key recommendations: (1) invest to provide earnings and employment opportunities to Mississippians; (2) invest in programs that meet social and labor needs; and (3) invest to close equity gaps in attainment and earnings.