MAPF is an NP-hard problem. We are given a large pre-calculated set of paths. The aim is to select paths from this set such that they do not collide with static obstacles nor with each other. This selection should be calculated in near real-time, i.e., extremely faster than classic MAPF algorithms.
We investigate how Deep-Learning methods may speed up the search process. We train the NN to recognize patterns in the training examples and apply them to previously unseen settings of the problem.
The challenge of mapping indoor environments is addressed. Frontier-based methods calculation time may increase substantially as more areas are exposed. To overcome this limitation, we apply deep reinforcement learning to train the motion planner, and pre-trained generative deep neural network, acting as a map predictor. Hence, we improve the decision making through use of the learned structural statistics of the environment and ensure a constant calculation time. We show that combining the two methods can shorten the duration of the mapping process substantially.
This report, written under the supervision of Professor Alfred M. Bruckstein as part of a doctoral dissertation, surveys results on distributed systems comprising mobile agents that are identical and anonymous, oblivious and interact solely by adjusting their motion according to the relative location of their neighbours. The agents are assumed capable of sensing the presence of other agents within a given sensing range and able to implement rules of motion based on partial information on the geometric constellation of their neighbours.
This project aims to advance the existing scientific knowledge on solar design by harnessing novel computational optimization methods. We explore a generative approach in which a combination of solar-driven metrics drives the form-finding process based on a multi-objective optimization process. The workflow is applied to a real district case study in Tel Aviv and yields a large set of spatial solar-driven building masses, rather than one solar envelope volume, which corresponds to the different trade-offs between the environmental performance metrics applied.
.
This project offers new insights into the nexus between urban form and environmental performance both at the local and global contexts. We develop and explore a new set of harmonized workflows, which by capitalizing on the benefits of advanced computational intelligence, open new possibilities in the pursuit of a sustainable urban form – going beyond energy considerations towards environmental quality and urban livability. As part of the project new simplified evaluation metrics are developed to be employed in multi-objective optimization studies of environmental performance at the urban scale.
The focus is on recognizing and analyzing the challenges that arise when autonomous agents with different capabilities need to interact and collaborate on unknown tasks, on providing methods for the automated design of these environments to promote collaboration, and on specifying guarantees regarding the quality of the design solutions produced by our suggested methods. This research combines data-driven approaches with symbolic AI techniques and involves both theoretical work and evaluations on multi-agent reinforcement learning settings and on multi robot systems.
Promoting multi-agent collaboration via dynamic markets of information and skills in which AI agents and robots trade their physical capabilities and their ability to acquire new information. The value of these traded commodities is dynamically computed based on the agents’ objectives, sensors and actuation capabilities as well as their ability to communicate with each other and ask for assistance. This framework maximizes performance and team resilience, without relying on a centralized controller.
Most current approaches to robotic planning separate the low-level planning of basic behaviors and the high-level search for a sequence of behaviors that will accomplish a task. However, in complex settings such as packing, personal assistance, and cooking, this dichotomous view becomes inefficient, especially in environments shared by multiple autonomous agents. We therefore offer new ways for integrating task-level considerations when planning the robot’s movement, and for propagating motion-planning considerations into task planning.
We study basic human decision making and learning processes when making repeated and/or sequential choice. Understanding the basic processes in these very common settings (e.g. driving, behavior in pandemics, using smartphone apps, health decisions) both improves our ability to predict behavior and to design mechanisms and policies that are robust to the likely behaviors of systems’ users.
We integrate psychological theories and models of human decision making into machine learning systems to predict human decision making in state-of-the-art levels. Focusing on the most fundamental choice task from behavioral economics and using the largest datasets currently available, we study which theories and models, which types of machine learning algorithms and tools, and which methods of integration lead to the best out-of-sample predictions.
Mobile Ad-hoc NETworks (MANET) is a communication platform for wireless first response units that creates a temporary network without any help of any centralized support. MANET is characterized by its rapidly changing connectivity and bandwidth over the communication links. Mobile Ad Hoc Network is a collection of wireless hosts that creates a temporary network without any help of any centralized support. At the same time, the application runs on the units often requires strict availability of end to end bandwidth and delay. It is essential to be build an optimization tool that will be able to predict the traffic bandwidth or the delay performance once the network topology changes or a new application starts running. Developing such tool requires network modeling. Nowadays, network models are either based on packet-level simulators or analytical models (e.g., queuing theory). Packet–level simulators are very costly computationally, while the analytical models are fast but not accurate. Hence, Machine Learning (ML) arises as a promising solution to build accurate network models able to operate in real time and to predict the resulting network performance according to the target policy, i.e maximum bandwidth or minimum end-to-end delay. Recently, Graph Neural Networks (GNN) have shown a strong potential to be integrated into commercial products for network control and management. Early works using GNN have demonstrated capability to learn from different network characteristics that are fundamentally represented as graphs, such as the topology, the routing configuration, or the traffic that flows along a series of nodes in the network. In contrast to previous ML-based solutions, GNN enables to produce accurate predictions even in networks unseen during the training phase. The main project target is to adjust GNN to MANET and test its prediction accuracy for such network.
Understanding how to deal with model uncertainty is key for building resilient agents that can overcome environments that are unforeseen. My research group has studied for years different approaches that build robust agents that can cope with different types of uncertainties. Robustness means that policies are immune to changes in the environment leading to better real time performance. In a sequence of papers we developed robust reinforcement learning and planning algorithms including scaling up such algorithms, learning the uncertainty set online, adapting quickly to unknown uncertainties, and online adaptation. The main application areas here are energy and transport services.
Modern recommendation platforms have become complex, dynamic eco-systems. Platforms often rely on machine learning models to successfully match users to content, but most methods neglect to account for how they affect user behavior, satisfaction, and well-being of over time. Here we propose a novel dynamical-systems perspective to recommendation that allows to reason about, and control, macro-temporal aspects of recommendation policies as they relate to user behavior.
Machine learning has become imperative for informing decisions that affect the lives of humans across a multitude of domains. But when people benefit from certain predictive outcomes, they are prone to act strategically to improve those outcomes. Our goal in this project is to develop a practical learning framework that accounts for how humans behaviourally respond to classification rules. Our framework provides robustness while also providing means to promote favourable social outcomes.
This project will enable unreliable edge computing nodes to jointly provide a reliable storage service for unpredictable user workloads. Edge systems consists small-scale servers (nodes) at the edge of the network whose root is in the cloud-based datacenter. Their premise is to bring data and computing closer to time-critical applications running on e.g., cellphones and autonomous vehicles. We combine storage redundancy schemes with scalable algorithms for object mapping and request scheduling.
Non-invasive brain computer interfaces (BCIs) provide direct communication link from the brain to external devices. We develop non-invasive BCIs that are based on interpreting EEG measurements to identify user’s desired selection, action or movement. We focus on developing self- correction capabilities, based on error-related potentials (ErrPs), which are evoked in the brain when errors are detected. We investigate ErrPs, develop classifiers for detecting them and methods to integrate them to improve BCIs. This project is funded by Dr. Maria Ascoli Rossi Research Grant.
Big data sources have been used extensively to analyze people’s travel patterns. This project breaks new ground by using big data on travel patterns to identify the incidence and severity of travel problems – defined here as any difficulty a person may experience in reaching desired destinations. Relying on a large-scale app-based mobility survey, data will be extracted on individual’s trip rates, travel horizons, trip speeds, and more, with the aim to detect individuals particularly likely to experience severe travel problems.
This project focuses on the design, analysis, development, and practical implementation of simple algorithms for solving the Wireless Sensor Network (WSN) Localization problems. In a recent paper, we solve the original non-convex and non-smooth formulation using first-order methods. We proposed a parameter-free algorithmic framework that includes the whole spectrum ranging from a fully centralized to a fully distributed implementation, and that it can also achieve partial parallelization.
In domains where planning is slow compared to the evolution of the environment, it can be important to take into account the time taken by the planning process itself. For one example, plans involving taking a certain bus are of no use if planning finishes after the bus departs. We call this setting situated temporal planning and we define it as a variant of temporal planning with timed initial literals.
As LiDAR sensors for depth acquisition advance to solid-state technologies, new capabilities raise new theoretical and technological challenges. In particular, we investigate benefits afforded by controlling and changing in real time the sampling scheme (adaptive sampling). We use neural-network to predict the optimal sampling scheme per scene, given a fixed sampling budget. We found that for a given RMSE, the sampling budget can be reduced by a factor of about 4 on average. Various strategies and algorithms are examined.
We investigate analytic and numerical solutions of nonlinear gradient flows. We examine the flows as nonlinear PDE’s and use tools from nonlinear spectral theory. We have recently revealed relations between Dynamic mode decomposition (DMD), a common tool for fluid dynamics, and nonlinear eigenfunctions related to homogeneous flows. We are investigating through this lens gradient descent algorithms of complex systems.
Database schema matching is a challenging task that call for improvement for several decades. Automatic algorithms fail to provide reliable enough results. We use human matching to overcome algorithm failures and vice versa. We refer to human and algorithmic matchers as imperfect matchers with different strengths and weaknesses. We use insights from cognitive research to predict human matchers behavior and identify those who can do better than others. We then merge their responses with algorithmic outcomes and get better results.
Image denoising is a well-known and well studied problem, commonly targeting a minimization of the mean squared error (MSE) between the outcome and the original image. Unfortunately, especially for severe noise levels, such Minimum MSE (MMSE) solutions may lead to blurry output images. In this work we propose a novel stochastic denoising approach that produces viable and high perceptual quality results, while maintaining a small MSE. Our method employs Langevin dynamics that relies on a repeated application of any given MMSE denoiser, obtaining the reconstructed image by effectively sampling from the posterior distribution. Due to its stochasticity, the proposed algorithm can produce a variety of high-quality outputs for a given noisy input, all shown to be legitimate denoising results. In addition, we present an extension of our algorithm for handling the inpainting problem, recovering missing pixels while removing noise from partially given data.
The vast work in Deep Learning (DL) has led to a leap in image denoising research. Most DL solutions for this task have chosen to put their efforts on the denoiser’s architecture while maximizing distortion performance. However, distortion driven solutions lead to blurry results with sub-optimal perceptual quality, especially in immoderate noise levels. In this paper we propose a different perspective, aiming to produce sharp and visually pleasing denoised images that are still faithful to their clean sources. Formally, our goal is to achieve high perceptual quality with acceptable distortion. This is attained by a stochastic denoiser that samples from the posterior distribution, trained as a generator in the framework of conditional generative adversarial networks (CGAN). Contrary to distortion-based regularization terms that conflict with perceptual quality, we introduce to the CGAN objective a theoretically founded penalty term that does not force a distortion requirement on individual samples, but rather on their mean. We showcase our proposed method with a novel denoiser architecture that achieves the reformed denoising goal and produces vivid and diverse outcomes in immoderate noise levels.
The non-local self-similarity property of natural images has been exploited extensively for solving various image processing problems. When it comes to video sequences, harnessing this force is even more beneficial due to the temporal redundancy. In the context of image and video denoising, many classically-oriented algorithms employ self-similarity, splitting the data into overlapping patches, gathering groups of similar ones and processing these together somehow. With the emergence of convolutional neural networks (CNN), the patch-based framework has been abandoned. Most CNN denoisers operate on the whole image, leveraging non-local relations only implicitly by using a large receptive field. This work proposes a novel approach for leveraging self-similarity in the context of video denoising, while still relying on a regular convolutional architecture. We introduce a concept of patch-craft frames – artificial frames that are similar to the real ones, built by tiling matched patches. Our algorithm augments video sequences with patch-craft frames and feeds them to a CNN. We demonstrate the substantial boost in denoising performance obtained with the proposed approach.
Cellular channels are increasingly used for sensitive real-time applications. For example, real time video can now be broadcast over parallel cellular channel, possibly from a moving vehicle. Such channels are characterized by high variability, and require improved flow control algorithms to maintain stable flow. This work addresses the application of deep learning algorithms to develop suitable flow control and scheduling algorithm under real-time delay constraints.
Generative adversarial networks (GANs) are known to benefit from regularization or normalization of their discriminator network during training. In this work, we introduced sparsity aware normalization (SAN), a new method for stabilizing GAN training. Our method is particularly effective for image restoration and image-to-image translation. There, it significantly improves upon existing methods, like spectral normalization, while allowing using shorter training and smaller capacity networks, at no computational overhead.
Image restoration methods do not allow exploring the infinitely many plausible reconstructions that might have given rise to the measured image. In this work, we introduced the task of explorable image restoration, and illustrated it for the tasks of super resolution and JPEG decompression. We proposed a framework comprising a graphical user interface with a neural network backend, allowing editing the output to explore the abundance of plausible explanations to the input. We illustrated our approach in a variety of use cases, ranging from medical imaging and forensics to graphics (Oral presentations at CVPR`20, CVPR`21).
We introduced an unconditional generative model that can be learned from a single natural image. Our model, coined SinGAN, is trained to capture the internal distribution of patches within the image, and is then able to generate high quality, diverse samples of arbitrary size and aspect ratio, that carry the same visual content as the image. We illustrated the utility of SinGAN in a wide range of image manipulation tasks. This work won the Best Paper Award (Marr Prize) at ICCV`19.
Improvements in training speed are needed to develop the next generation of deep learning models. To perform such a massive amount of computation in a reasonable time, it is parallelized across multiple GPU cores. Perhaps the most popular parallelization method is to use a large batch of data in each iteration of SGD, so the gradient computation can be performed in parallel on multiple workers. We aim to enable massive parallelization without performance degradation, as commonly observed.
We aim to improve the resource efficiency of deep learning (e.g., energy, bandwidth) for training and inference. Our focus is decreasing the numerical precision of the neural network model is a simple and effective way to improve their resource efficiency. Nearly all recent deep learning related hardware relies heavily on lower precision math. The benefits are a reduction in the memory required to store the neural network, a reduction in chip area, and a drastic improvement in energy efficiency.
Significant research efforts are being invested in improving Deep Neural Networks (DNNs) via various modifications. However, such modifications often cause an unexplained degradation in the generalization performance DNNs to unseen data. Recent findings suggest that this degradation is caused by changes to the hidden algorithmic bias of the training algorithm and model. This bias determines which solution is selected from all solutions which fit the data. We aim to understand and control this algorithmic bias.
Our goal is to develop multi-modal neural network architectures for the tasks of guided super-resolution (SR) of dynamic elevation models (DEM). Current DEMs for most of the earth surface is still low resolution (sometimes 2 meters per pixel, but more often 10, 15, or 30 meters per pixel) and thus cannot accurately represent the morphology of the terrain. High resolution DEMs, however, have many uses, including precision agriculture, urban mapping, high-definition maps for autonomous navigation, line-of-sight analysis, and more.
A framework for modelling an optimal dynamic toll pricing strategy for a system of managed lanes is developed. A macroscopic traffic simulation model is used to estimate the traffic states subject to initial and boundary conditions while incorporating the tolling policy. Traffic states and optimal toll actions are derived for a set of scenarios. These are used with an artificial neural network to develop a tolling policy for toll actions at each step.
The aim of this research is to develop a new tool to automatically design complex actuated traffic signal plans. The method uses an automatic programming approach, combined with a mesoscopic traffic simulation model to design and evaluate optimal intersection traffic signal plans. Thus, reducing the need of human intervention in the design process. The tool takes into consideration not only the plan parameters but also the control logic as well.
