Age-related loss of mobility and increased risk of falling remain important obstacles toward facilitating aging-in-place. Many elderly people lack the coordination and strength necessary to perform common movements around their home, such as getting out of bed or stepping into a bathtub. The traditional solution has been to install grab bars on various surfaces; however, these are often not placed in optimal locations due to feasibility constraints in room layout. In this paper, we present a mobile robot that provides an older adult with a handle anywhere in space - "handle anywhere". The robot consists of an omnidirectional mobile base attached to a repositionable handle. We analyze the postural changes in four activities of daily living and determine, in each, the body pose that requires the maximal muscle effort. Using a simple model of the human body, we develop a methodology to optimally place the handle to provide the maximum support for the elderly person at the point of most effort. Our model is validated with experimental trials. We discuss how the robotic device could be used to enhance patient mobility and reduce the incidence of falls.

Existing defenses against adversarial examples such as adversarial training typically assume that the adversary will conform to a specific or known threat model, such as $\ell_p$ perturbations within a fixed budget. In this paper, we focus on the scenario where there is a mismatch in the threat model assumed by the defense during training, and the actual capabilities of the adversary at test time. We ask the question: if the learner trains against a specific "source" threat model, when can we expect robustness to generalize to a stronger unknown "target" threat model during test-time? Our key contribution is to formally define the problem of learning and generalization with an unforeseen adversary, which helps us reason about the increase in adversarial risk from the conventional perspective of a known adversary. Applying our framework, we derive a generalization bound which relates the generalization gap between source and target threat models to variation of the feature extractor, which measures the expected maximum difference between extracted features across a given threat model. Based on our generalization bound, we propose variation regularization (VR) which reduces variation of the feature extractor across the source threat model during training. We empirically demonstrate that using VR can lead to improved generalization to unforeseen attacks during test-time, and combining VR with perceptual adversarial training (Laidlaw et al., 2021) achieves state-of-the-art robustness on unforeseen attacks. Our code is publicly available at https://github.com/inspire-group/variation-regularization.

Newly developed graph neural networks (GNNs) [1-3], in particular convolutional graph neural networks, have been shown to be effective in a variety of classification and regression tasks. Recently they have been applied to physical problems [4, 5] where they can accommodate unstructured and hierarchical data naturally. Analogous to pixel-based convolutional neural networks (CNNs), "message passing" [6] graph convolutional neural networks (GCNNs) [7, 8] employ convolutional operations to achieve a compact parameter space by exploiting correlations in the data through connectivity defined by adjacency on the source discretization. Frankel et al. [9] and others [10-13] derive the information transmission graph directly from the connectivity of the discretization, computational grid or mesh based on the assumption the physical interactions are local. Some obvious advantages of applying convolutions to the discretization graph are that: general mesh data can be handled without interpolation to a structured grid, the discretization can be conformal to the microstructure, periodic boundary conditions can be handled without padding, and topological irregularities can be accommodated without approximations. In this approach the kernels and number of parameters are similar for a pre-selected reduction of the representation, e.g. based on the grains in a polycrystal [5], but the size of the adjacency can be prohibitive.

Argument Unit Recognition and Classification aims at identifying argument units from text and classifying them as pro or against. One of the design choices that need to be made when developing systems for this task is what the unit of classification should be: segments of tokens or full sentences. Previous research suggests that fine-tuning language models on the token-level yields more robust results for classifying sentences compared to training on sentences directly. We reproduce the study that originally made this claim and further investigate what exactly token-based systems learned better compared to sentence-based ones. We develop systematic tests for analysing the behavioural differences between the token-based and the sentence-based system. Our results show that token-based models are generally more robust than sentence-based models both on manually perturbed examples and on specific subpopulations of the data.

Artificial Intelligence on the Battlefield By Shephard Media Download from Itunes

This public webinar, hosted by the National Academy of Medicine (NAM) and the U.S. Government Accountability Office (GAO), will explore the promise and issues associated with using artificial intelligence (AI) in medical diagnosis. This webinar builds off a recent GAO technology assessment titled Artificial Intelligence in Health Care: Benefits and Challenges of Machine Learning Technologies for Medical Diagnostics and NAM Perspectives Discussion Paper titled Meeting the Moment: Addressing Barriers and Facilitating Clinical Adoption of Artificial Intelligence in Medical Diagnosis. Participants will hear an overview of and reactions from field experts to the GAO report and the NAM Discussion Paper. The GAO report discusses current and emerging machine learning (ML) medical diagnostic technologies for select diseases and provides a broad overview of the challenges that affect their development and adoption. The NAM Discussion Paper focuses primarily on deployment and presents a framework for evaluating and promoting provider and health system adoption of AI-diagnostic decision support (AI-DDS) tools while exploring intersection equity issues.

CORVALLIS, Ore. – Cassie the robot, invented at the Oregon State University College of Engineering and produced by OSU spinout company Agility Robotics, has established a Guinness World Record for the fastest 100 meters by a bipedal robot. Cassie clocked the historic time of 24.73 seconds at OSU's Whyte Track and Field Center, starting from a standing position and returning to that position after the sprint, with no falls. The run can also be seen on YouTube.) The 100-meter record builds on earlier achievements by the robot, including traversing 5 kilometers in 2021 in just over 53 minutes. Cassie, the first bipedal robot to use machine learning to control a running gait on outdoor terrain, completed the 5K on Oregon State's campus untethered and on a single battery charge.

Iran launched cross-border missile and drone strikes that killed nine people in Iraq's Kurdistan region Wednesday after accusing Kurdish armed groups based there of stoking a wave of unrest that has rocked the Islamic republic. The September 16 death of Kurdish Iranian woman Mahsa Amini, 22, while in the custody of Iran's morality police has sparked a major wave of protests and a crackdown that has left scores of demonstrators dead over the past 12 nights. Iran's Islamic Revolutionary Guard Corps has in recent days accused the Iraq-based Kurdish groups of "attacking and infiltrating Iran from the northwest of the country to sow insecurity and riots and spread unrest". After several earlier Iranian cross-border attacks that caused no casualties, a barrage of missiles and drones on Wednesday claimed nine lives and wounded 32, said the regional health minister in Arbil, Saman al-Barazanji, while visiting some off the wounded in a hospital in the capital of Iraq's autonomous Kurdistan region. "There are civilians among the victims", including one of those killed, a senior official of the Kurdistan region earlier told AFP.

Iran has attacked an Iranian-Kurdish opposition group in the Kurdish region of northern Iraq, killing nine people and injuring several others, Kurdish officials said. The missile and drone attacks on Wednesday focused on bases in Koya, some 60km (35 miles) east of Erbil, said Soran Nuri – a member of the Democratic Party of Iranian Kurdistan. The group, known by the acronym KDPI, is a left-wing armed opposition force that is banned in Iran. Iran's state-run IRNA news agency and broadcaster said Iran's Revolutionary Guard Corps ground forces targeted some bases of a separatist group in the north of Iraq with "precision missiles" and a "suicide drone". "This operation will continue with our full determination until the threat is effectively repelled, terrorist groups' bases are dismantled, and the authorities of the Kurdish region assume their obligations and responsibilities," the IRGC said in a statement read on state television. Nine people were killed and 24 wounded, according to Kurdistan Regional Government's health minister, Saman Barazanchi.

Since April, DALL-E has triggered an explosion of images generated using artificial intelligence. But the technology is spreading faster than creators can shape norms around its use.