Abstract

In an ecosystem comprising coexisting species, mutations frequently occur. These mutations can be induced by various factors such as errors in DNA replication and exposure to chemicals. They constitute an intrinsic element of species evolution. This study investigates the impact of mutations on ecosystems, employing Gillespie simulations and the formulation of the First-passage extinction problem to assess their effects and examine extinction events. Our findings suggest first-extinction time and state distribution in a system with mutation follows intriguing behavior which promotes co-existence. There also exists a depression in the state space post which mutation extends the first-extinction time. Moreover, a system devoid of mutation exhibits a discernible inclination towards probabilities that lean in the direction of an endangered state space.

Abstract

With the rise in consumer depth cameras, a wealth of unlabeled RGB-D data has become available. This prompts the question of how to utilize this data for geometric reasoning of scenes. While many RGB-D registration methods rely on geometric and feature-based similarity, we take a different approach. We use cycle-consistent keypoints as salient points to enforce spatial coherence constraints during matching, improving correspondence accuracy. Additionally, we introduce a novel pose block that combines a GRU recurrent unit with transformation synchronization, blending historical and multi-view data. Our approach surpasses previous selfsupervised registration methods on ScanNet and 3DMatch, even outperforming some older supervised methods. We also integrate our components into existing methods, showing their effectiveness.

Abstract

Assistive agents performing household tasks such as making the bed or cooking breakfast often compute and execute actions that accomplish one task at a time. However, efficiency can be improved by anticipating upcoming tasks and computing an action sequence that jointly achieves these tasks. State-of-the-art methods for task anticipation use data-driven deep networks and Large Language Models (LLMs), but they do so at the level of high-level tasks and/or require many training examples. Our framework leverages the generic knowledge of LLMs through a small number of prompts to perform high-level task anticipation, using the anticipated tasks as goals in a classical planning system to compute a sequence of finer-granularity actions that jointly achieve these goals. We ground and evaluate our framework's abilities in realistic scenarios in the VirtualHome environment and demonstrate a 31% reduction in execution time compared with a system that does not consider upcoming tasks.

Abstract

Classical motion planning for robotic manipulation includes a set of general algorithms that aim to minimize a scene-specific cost of executing a given plan. This approach offers remarkable adaptability, as they can be directly used off-the-shelf for any new scene without needing specific training datasets. However, without a prior understanding of what diverse valid trajectories are and without specially designed cost functions for a given scene, the overall solutions tend to have low success rates. While deep-learning-based algorithms tremendously improve success rates, they are much harder to adopt without specialized training datasets. We propose EDMP, an Ensemble-of-costs-guided Diffusion for Motion Planning that aims to combine the strengths of classical and deep-learning-based motion planning. Our diffusion-based network is trained on a set of diverse kinematically valid trajectories. Like classical planning, for any new scene at the time of inference, we compute scene-specific costs such as "collision cost" and guide the diffusion to generate valid trajectories that satisfy the scene-specific constraints. Further, instead of a single cost function that may be insufficient in capturing diversity across scenes, we use an ensemble of costs to guide the diffusion process, significantly improving the success rate compared to classical planners. EDMP performs comparably with SOTA deep-learning-based methods while retaining the generalization capabilities primarily associated with classical planners.

Abstract

In this letter, we propose a PIPE-CovNet+ model that is ba-sed on convolutional neural networks (CNNs) with multiple kernel sizes, gradient boosting techniques, and hyper-densely connected layers for abnormality detection in wastewater pipe infrastructure. The PIPE-CovNet+ model achieved 85% accuracy and 84% F1-score following assessment utilizing an open-source dataset, overcoming the constraints of imbalanced data and over-fitting issues. Furthermore, it showed greater efficacy when compared against other relevant models, displaying 3% higher accuracy and F1-score than our prior work under ideal test settings. Installing PIPE-CovNet+ into a robot system can alleviate the limitations of being tedious, laborious, and prone to human error in closed-circuit television (CCTV) inspections.

Abstract

Given the current emphasis on maintaining and inspecting high-rise buildings, conventional inspection approaches are costly, slow, error-prone, and labor-intensive due to manual processes and lack of automation. In this paper, we provide an automated, periodic, accurate and economical solution for the inspection of such buildings on real-world images. We propose a novel end-to-end integrated autonomous pipeline for building inspection which consists of three modules: i) Autonomous Drone Navigation, ii) Façade Detection, and iii) Model Construction. Our first module computes a collision-free trajectory for the UAV around the building for surveillance. The images captured in this step are used for façade detection and 3D building model construction. The façade detection module is a deep learning-based object detection method which detects cracks. Finally, the model construction module focuses on reconstructing a 3D model of a building from captured images to mark the corresponding cracks on the 3D model for efficient and accurate inferences from the inspection. We conduct experiments for each module, including collision avoidance for drone navigation, façade detection, model construction and mapping. Our experimental analysis shows the promising performance of i) our crack detection model with a precision and recall of 0.95 and mAP score of 0.96; ii) our 3D reconstruction method includes finer details of the building without having additional information on the sequence of images; and iii) our 2D-3D mapping to compute the original location/world coordinates of cracks for a building.

Abstract

Addressing runtime uncertainties in Machine Learning-Enabled Systems (MLS) is crucial for maintaining Quality of Service (QoS). The Machine Learning Model Balancer is a concept that addresses these uncertainties by facilitating dynamic ML model switching, showing promise in improving QoS in MLS. Leveraging this concept, this paper introduces SWITCH, an exemplar developed to enhance self-adaptive capabilities in such systems through dynamic model switching in runtime. SWITCH is designed as a comprehensive web service catering to a broad range of ML scenarios, with its implementation demonstrated through an object detection use case. SWITCH provides researchers with a flexible platform to apply and evaluate their ML model switching strategies, aiming to enhance QoS in MLS. SWITCH features advanced input handling, real-time data processing, and logging for adaptation metrics supplemented with an interactive real-time dashboard for enhancing system observability. This paper details SWITCH's architecture, self-adaptation strategies through ML model switching, and its empirical validation through a case study, illustrating its potential to improve QoS in MLS. By enabling a hands-on approach to explore adaptive behaviors in ML systems, SWITCH contributes a valuable tool to the SEAMS community for research into self-adaptive mechanisms for MLS and their practical applications.

Abstract

The sustainability of Machine Learning-Enabled Systems (MLS), particularly with regard to energy efficiency, is an important challenge in their development and deployment. Self-adaptation techniques, recognized for their potential in energy savings within software systems, have yet to be extensively explored in Machine Learning-Enabled Systems (MLS), where runtime uncertainties can significantly impact model performance and energy consumption. This variability, alongside the fluctuating energy demands of ML models during operation, necessitates a dynamic approach. Addressing these challenges, we introduce EcoMLS approach, which leverages the Machine Learning Model Balancer concept to enhance the sustainability of MLS through runtime ML model switching. By adapting to monitored runtime conditions, EcoMLS optimally balances energy consumption with model confidence, demonstrating a significant advancement towards sustainable, energy-efficient machine learning solutions. Through an object detection exemplar, we illustrate the application of EcoMLS, showcasing its ability to reduce energy consumption while maintaining high model accuracy throughout its use. This research underscores the feasibility of enhancing MLS sustainability through intelligent runtime adaptations, contributing a valuable perspective to the ongoing discourse on energy-efficient machine learning.

Abstract

We present a new additive image factorization technique that treats images to be composed of multiple latent specular components which can be simply estimated recursively by modulating the sparsity during decomposition. Our model-driven {\em RSFNet} estimates these factors by unrolling the optimization into network layers requiring only a few scalars to be learned. The resultant factors are interpretable by design and can be fused for different image enhancement tasks via a network or combined directly by the user in a controllable fashion. Based on RSFNet, we detail a zero-reference Low Light Enhancement (LLE) application trained without paired or unpaired supervision. Our system improves the state-of-the-art performance on standard benchmarks and achieves better generalization on multiple other datasets. We also integrate our factors with other task specific fusion networks for applications like deraining, deblurring and dehazing with negligible overhead thereby highlighting the multi-domain and multi-task generalizability of our proposed RSFNet. The code and data is released for reproducibility on the project homepage.

Abstract

This edited volume presents perspectives from computer science, information theory, neuroscience and brain imaging, aesthetics, social sciences, psychiatry, and philosophy to answer frontier questions related to artificial intelligence and human experience. Can a machine think, believe, aspire and be purposeful as a human? What is the place in the machine world for hope, meaning and transformative enlightenment that inspires human existence? How, or are, the minds of machines different from that of humans and other species? These questions are responded to along with questions in the intersection of health, intelligence and the brain. It highlights the place of consciousness by attempting to respond to questions with the help of fundamental reflections on human existence, its life-purposes and machine intelligence.