Smart environments offer valuable technologies for activity monitoring and health assessment. Here, we describe an integration of robots into smart environments to provide more interactive support of individuals with functional limitations. RAS, our Robot Activity Support system, partners smart environment sensing, object detection and mapping, and robot interaction to detect and assist with activity errors that may occur in everyday settings. We describe the components of the RAS system and demonstrate its use in a smart home testbed. To evaluate the usability of RAS, we also collected and analyzed feedback from participants who received assistance from RAS in a smart home setting as they performed routine activities.

No abstract

Background & objectives: Coronavirus disease 2019 (COVID-19) has so far affected over 41 million people globally. The limited supply of real-time reverse transcription-polymerase chain reaction (rRT-PCR) kits and reagents has made meeting the rising demand for increased testing incompetent, worldwide. A highly sensitive and specific antigen-based rapid diagnostic test (RDT) is the need of the hour. The objective of this study was to evaluate the performance of a rapid chromatographic immunoassay-based test (index test) compared with a clinical reference standard (rRT-PCR). Methods: A cross-sectional, single-blinded study was conducted at a tertiary care teaching hospital in north India. Paired samples were taken for RDT and rRT-PCR (reference standard) from consecutive participants screened for COVID-19 to calculate the sensitivity and specificity of the RDT. Further subgroup analysis was done based on the duration of illness and cycle threshold values. Cohen's kappa coefficient was used to measure the level of agreement between the two tests. Results: Of the 330 participants, 77 were rRT-PCR positive for SARS-CoV-2. Sixty four of these patients also tested positive for SARS-CoV-2 by RDT. The overall sensitivity and specificity were 81.8 and 99.6 per cent, respectively. The sensitivity of RDT was higher (85.9%) in participants with a duration of illness ≤5 days. Interpretation & conclusions: With an excellent specificity and moderate sensitivity, this RDT may be used to rule in COVID-19 in patients with a duration of illness ≤5 days. Large-scale testing based on this RDT across the country would result in quick detection, isolation and treatment of COVID-19 patients.

Symbolic planning models allow decision-making agents to sequence actions in arbitrary ways to achieve a variety of goals in dynamic domains. However, they are typically handcrafted and tend to require precise formulations that are not robust to human error. Reinforcement learning (RL) approaches do not require such models, and instead learn domain dynamics by exploring the environment and collecting rewards. However, RL approaches tend to require millions of episodes of experience and often learn policies that are not easily transferable to other tasks. In this paper, we address one aspect of the open problem of integrating these approaches: how can decision-making agents resolve discrepancies in their symbolic planning models while attempting to accomplish goals? We propose an integrated framework named SPOTTER that uses RL to augment and support ("spot") a planning agent by discovering new operators needed by the agent to accomplish goals that are initially unreachable for the agent. SPOTTER outperforms pure-RL approaches while also discovering transferable symbolic knowledge and does not require supervision, successful plan traces or any a priori knowledge about the missing planning operator.

No abstract