Mobile robots operating indoors must be prepared to navigate challenging scenes that contain transparent surfaces. This paper proposes a novel method for the fusion of acoustic and visual sensing modalities through implicit neural representations to enable dense reconstruction of transparent surfaces in indoor scenes. We propose a novel model that leverages generative latent optimization to learn an implicit representation of indoor scenes consisting of transparent surfaces. We demonstrate that we can query the implicit representation to enable volumetric rendering in image space or 3D geometry reconstruction (point clouds or mesh) with transparent surface prediction. We evaluate our method's effectiveness qualitatively and quantitatively on a new dataset collected using a custom, low-cost sensing platform featuring RGB-D cameras and ultrasonic sensors. Our method exhibits significant improvement over state-of-theart for transparent surface reconstruction. Website and Dataset: https://umfieldrobotics.github.io/VAIR_site/

Generative Artificial Intelligence (GenAI) is rapidly changing the manner in which organizations manage and govern technology. As a growing percentage of code is AI generated, and a growing number of no-code tools increase user access to development opportunities the governing and oversight role of Architecture teams will change. The enhanced productivity possible through GenAI may be a means to boost sustainable innovation, particular in resource constrained non-profit and public sector organizations. In this paper we present Integrated Action Research as a methodology that can support scholars in actively engaging with practitioners in developing new theories and practices associated with the effective engagement of GenAI in architecture practice. We propose that academic researchers can provide a unique perspective from that of consultants or industry practitioners, and therefore have a valuable role to play in the integration of GenAI into technology management practices. We further present a future research agenda for building AI enabled foundations for architecture programs.

We propose CACE (Constraints And Correlations mining Engine) which investigates the challenges of improving the recognition of complex daily activities in multi-inhabitant smart homes, by better exploiting the spatiotemporal relationships across the activities of different individuals. We first propose and develop a loosely-coupled Hierarchical Dynamic Bayesian Network (HDBN), which both (a) captures the hierarchical inference of complex (macro-activity) contexts from lower-layer microactivity context (postural and improved oral gestural context), and (b) embeds the various types of behavioral correlations and constraints (at both micro-and macro-activity contexts) across the individuals. While this model is rich in terms of accuracy, it is computationally prohibitive, due to the explosive increase in the number of jointly-defined states. To tackle this challenge, we employ data mining to learn behaviorally-driven context correlations in the form of association rules, we then use such rules to prune the state space dramatically. To evaluate our framework, we build a customized smart home system and collected naturalistic multi-inhabitant smart home activities data. The system performance is illustrated with results from real-time system deployment experiences in a smart home environment reveals a radical (max 16 fold) reduction in the computational overhead compared to traditional hybrid classification approaches, as well as an improved activity recognition accuracy of max 95%.