Evolvable Hardware (EHW) refers to HW design and self reconfiguration using evolutionary/genetic mechanisms. The paper presents an overview of some key concepts EHW, describing also a set selected applications. A fine-grained Field Programmable Transistor Array (FPTA) architecture for reconfigurable hardware is presented as example initial effort toward evolution-oriented devices. Evolutionary experiments in simulations with FPTA chip in-the-loop demonstrate automatic synthesis electronic...

Current techniques in evolutionary synthesis of analogue and digital circuits designed at transistor level have focused on achieving the desired functional response, without paying sufficient attention to issues needed for a practical implementation resulting solution. No silicon fabrication with topologies by evolution has been done before, leaving open questions feasibility circuit design approach, as well how high-performance, robust, or portable such designs could be when implemented...

The increasing demand in air transportation is pushing the current traffic management system to its limits airspace capacity and workload of controllers (ATCOs). ATCOs are an urgent need assistant tools aid them dealing with increased traffic, specifically resolving potential conflict. Because automated conflict resolutions not conformance thinking or preferences individual ATCOs, consequently, they unlikely accepted by ATCOs. In this work, artificial intelligence (AI) built as a digital...

Intractable delays occur in air traffic due to the imbalance between ever-increasing demand and limited airspace capacity. As is associated with complex transport systems, can be magnified propagated throughout these resulting emergent behavior known as delay propagation. An understanding of propagation dynamics pertinent modern management. In this work, we present a network perspective dynamics. Specifically, model scenarios using spatial–temporal networks airports nodes. To establish...

Enabling effective learning using only a few presented examples is crucial but difficult computer vision objective. Few-shot have been proposed to address the challenges, and more recently variational inference-based approaches are incorporated enhance few-shot classification performances. However, current dominant strategy utilized Kullback-Leibler (KL) divergences find log marginal likelihood of target class distribution, while neglecting possibility other probabilistic comparative...

Remote digital towers using high-resolution cameras that cover a 360-degree view of airports have recently been solution to some in replacing physical and introducing technologies as tools assist tower controllers. We propose the use machine learning techniques automatically detect track small moving objects airfield from their motion patterns, i.e. ways an object moves. A video dataset comprising aircraft drones captured fixed angle is constructed. To dataset, we apply Harris Detection...

Classical approaches for modelling aircraft taxi-speed assume constant speed or use a turning rate function to approximate taxi-timings taxiing aircraft. However, those cannot predict spatio-temporal component of aircraft-taxi trajectory due lack consideration the complexity and stochasticity airport-airside movements interactions. This research adopts Generative Adversarial Imitation Learning (GAIL) algorithm modelling, while considering multiple operational factors including surrounding...

Abstract Departure delays are a major cause of economic loss and inefficiency in the growing industry passenger flights. A departure delay current flight is inevitably affected by late arrival immediately preceding it with same aircraft. We seek to understand mechanisms such propagated delays, obtain universal metrics which evaluate an airline’s operational effectiveness alleviation. Here we use big data collected American Bureau Transportation Statistics design models delays. Offering two...

Incorporating deep learning (DL) classification models into unmanned aerial vehicles (UAVs) can significantly augment search-and-rescue operations and disaster management efforts. In such critical situations, the UAV's ability to promptly comprehend crisis optimally utilize its limited power processing resources narrow down search areas is crucial. Therefore, developing an efficient lightweight method for scene of utmost importance. However, current approaches tend prioritize accuracy on...

Recently, the advances in reinforcement learning have enabled an artificial intelligent agent to solve many challenging problems (e.g. AlphaGo) at unprecedented levels. However, robustness of safety critical operation remains unclear. In this work, applicability Air Traffic Control was explored. We focus on building algorithm automate flight conflict resolution which is ultimate goal air traffic control. For that purpose, a simulator, provides environment for learning, developed simulate...

In air traffic control, the airspace is divided into several smaller sectors for better management of and controller workload. Such are usually managed by a team two controllers: planning (D-side) executive (R-side). D-side responsible processing flight-plan information to plan organize flow entering sector. R-side deals with ensuring safety flights in their A understanding predictability actions, given scenario, may help automating some its tasks hence reduce this paper, we propose learning...

We consider the Airspace Sectorization Problem (ASP) in which airspace has to be partitioned into a given number of sectors, each being assigned team air traffic controllers. The objective is minimize coordination workload between adjacent sectors while balancing total Many specific constraints, including both geometrical and aircraft related constraints are taken account. problem solved constraint programming framework. Experimental results show that our approach can used on real life problems.

Temperature and radiation tolerant electronics, as well long life survivability are key capabilities required for future NASA missions. Current approaches to electronics extreme environments focus on component level robustness hardening. However, current technology can only ensure very limited lifetime in environments. This paper describes novel experiments that allow adaptive in-situ circuit redesign/reconfiguration temperature would complement material/device/layout advancements increase...

Air traffic is operated in an air network (ATN) environment. It pertinent to improve the robustness of ATNs as they are frequently exposed manifold uncertainties which can break down their functioning components. Existing studies ATN by either rewiring its links or adding more ones. In this paper we discover paradox phenomenon ATNs. Specifically, claim removing links. order determine whose removal ATN's robustness, develop a bi-objective optimization model with one objective maximizing...

Much of the delay in US National Airspace System (NAS) arises from convective weather. One major objective our research is to take a less conservative route, where we risk higher attain better expected delay, instead avoiding bad weather zone completely. We address single aircraft problem using Markov decision process model and stochastic dynamic programming algorithm, evolution modeled as stationary chain. Our solution provides routing strategy for an that minimizes delay. A significant...

This paper presents experimental results of fast intrinsic evolutionary design and fault recovery a 4-bit digital to analog converter (DAC) using the JPL stand-alone board-level evolvable system (SABLES). SABLES is part an effort achieve integrated systems provides autonomous, (tens hundreds seconds), on-chip evolution involving about 100,000 circuit evaluations. Its main components are field programmable transistor array (FPTA) chip used as transistor-level reconfigurable hardware, TI DSP...