arXiv subjects

Dario Izzo

Publications and source records attributed to Dario Izzo.

87 records · Page 5Linked to original sources

arXiv2016

Differentiable Genetic Programming

We introduce the use of high order automatic differentiation, implemented via the algebra of truncated Taylor polynomials, in genetic programming. Using the Cartesian Genetic Programming encoding we obtain a high-order Taylor representation of the program output that is then used to back-propagate errors during learning. The resulting machine learning framework is called differentiable Cartesian Genetic Programming (dCGP). In the context of symbolic regression, dCGP offers a new approach to the long unsolved problem of constant representation in GP expressions. On several problems of increasing complexity we find that dCGP is able to find the exact form of the symbolic expression as well as the constants values. We also demonstrate the use of dCGP to solve a large class of differential equations and to find prime integrals of dynamical systems, presenting, in both cases, results that confirm the efficacy of our approach.

cs.NE↗

arXiv2016

Real-time optimal control via Deep Neural Networks: study on landing problems

Recent research on deep learning, a set of machine learning techniques able to learn deep architectures, has shown how robotic perception and action greatly benefits from these techniques. In terms of spacecraft navigation and control system, this suggests that deep architectures may be considered now to drive all or part of the on-board decision making system. In this paper this claim is investigated in more detail training deep artificial neural networks to represent the optimal control action during a pinpoint landing, assuming perfect state information. It is found to be possible to train deep networks for this purpose and that the resulting landings, driven by the trained networks, are close to simulated optimal ones. These results allow for the design of an on-board real time optimal control system able to cope with large sets of possible initial states while still producing an optimal response.

eess.SY↗

arXiv2016

Optimal Orderings of k-subsets for Star Identification

Finding the optimal ordering of k-subsets with respect to an objective function is known to be an extremely challenging problem. In this paper we introduce a new objective for this task, rooted in the problem of star identification on spacecrafts: subsets of detected spikes are to be generated in an ordering that minimizes time to detection of a valid star constellation. We carry out an extensive analysis of the combinatorial optimization problem, and propose multiple algorithmic solutions, offering different quality-complexity trade-offs. Three main approaches are investigated: exhaustive search (branch and prune), goal-driven (greedy scene elimination, minimally intersecting subsets), and stateless algorithms which implicitly seek to satisfy the problem's goals (pattern shifting, base unrank). In practical terms, these last algorithms are found to provide satisfactory approximations to the ideal performance levels, at small computational costs.

math.OC↗

arXiv2016

Persistent self-supervised learning principle: from stereo to monocular vision for obstacle avoidance

Self-Supervised Learning (SSL) is a reliable learning mechanism in which a robot uses an original, trusted sensor cue for training to recognize an additional, complementary sensor cue. We study for the first time in SSL how a robot's learning behavior should be organized, so that the robot can keep performing its task in the case that the original cue becomes unavailable. We study this persistent form of SSL in the context of a flying robot that has to avoid obstacles based on distance estimates from the visual cue of stereo vision. Over time it will learn to also estimate distances based on monocular appearance cues. A strategy is introduced that has the robot switch from stereo vision based flight to monocular flight, with stereo vision purely used as 'training wheels' to avoid imminent collisions. This strategy is shown to be an effective approach to the 'feedback-induced data bias' problem as also experienced in learning from demonstration. Both simulations and real-world experiments with a stereo vision equipped AR drone 2.0 show the feasibility of this approach, with the robot successfully using monocular vision to avoid obstacles in a 5 x 5 room. The experiments show the potential of persistent SSL as a robust learning approach to enhance the capabilities of robots. Moreover, the abundant training data coming from the own sensors allows to gather large data sets necessary for deep learning approaches.

cs.RO↗

arXiv2016

Designing Complex Interplanetary Trajectories for the Global Trajectory Optimization Competitions

The design of interplanetary trajectories often involves a preliminary search for options later refined/assembled into one final trajectory. It is this broad search that, often being intractable, inspires the international event called Global Trajectory Optimization Competition. In the first part of this chapter, we introduce some fundamental problems of space flight mechanics, building blocks of any attempt to participate successfully in these competitions, and we describe the use of the open source software PyKEP to solve them. In the second part, we formulate an instance of a multiple asteroid rendezvous problem, related to the 7th edition of the competition, and we show step by step how to build a possible solution strategy. In doing so, we introduce two new techniques useful in the design of this particular mission type: the use of an asteroid phasing value and its surrogates and the efficient computation of asteroid clusters. We show how the basic building blocks, sided to these innovative ideas, allow designing an effective global search for possible trajectories.

physics.space-ph↗

arXiv2016

GTOC8: Results and Methods of ESA Advanced Concepts Team and JAXA-ISAS

We consider the interplanetary trajectory design problem posed by the 8th edition of the Global Trajectory Optimization Competition and present the end-to-end strategy developed by the team ACT-ISAS (a collaboration between the European Space Agency's Advanced Concepts Team and JAXA's Institute of Space and Astronautical Science). The resulting interplanetary trajectory won 1st place in the competition, achieving a final mission value of $J=146.33$ [Mkm]. Several new algorithms were developed in this context but have an interest that go beyond the particular problem considered, thus, they are discussed in some detail. These include the Moon-targeting technique, allowing one to target a Moon encounter from a low Earth orbit; the 1-$k$ and 2-$k$ fly-by targeting techniques, enabling one to design resonant fly-bys while ensuring a targeted future formation plane% is acquired at some point after the manoeuvre ; the distributed low-thrust targeting technique, admitting one to control the spacecraft formation plane at 1,000,000 [km]; and the low-thrust optimization technique, permitting one to enforce the formation plane's orientations as path constraints.

physics.space-ph↗

arXiv2016

On the astrodynamics applications of Weierstrass elliptic and related functions

Weierstrass elliptic and related functions have been recently shown to enable analytical explicit solutions to classical problems in astrodynamics. These include the constant radial acceleration problem, the Stark problem and the two-fixed center (or Euler's) problem. In this paper we review the basic technique that allows for these results and we discuss the limits and merits of the approach. Applications to interplanetary trajectory design are then discussed including low-thrust planetary fly-bys and the motion of an artificial satellite under the influence of an oblate primary including $J_2$ and $J_3$ harmonics.

astro-ph.EP↗

arXiv2015

A complete and explicit solution to the three-dimensional problem of two fixed centres

We present for the first time an explicit, complete and closed-form solution to the three-dimensional problem of two fixed centres, based on Weierstrass elliptic and related functions. With respect to previous treatments of the problem, our solution is exact, valid for all initial conditions and physical parameters of the system (including unbounded orbits and repulsive forces), and expressed via a unique set of formulae. Various properties of the three-dimensional problem of two fixed centres are investigated and analysed, with a particular emphasis on quasi-periodic and periodic orbits, regions of motion and equilibrium points.

astro-ph.EP↗

arXiv2015

Explicit Solution to the Constant Radial Acceleration Problem

While the constant radial acceleration problem is known to be integrable and has received some recent attention in an orbital mechanics context, a closed form explicit solution, relating the state variables to a time parameter, has eluded all researchers so far. It is here shown how such a solution exists and is elegantly expressed in terms of the Weierstrass elliptic and related functions. Previously known facts can be derived from the new explicit solution and new insights are revealed.

math-ph↗

arXiv2014

Revisiting Lambert's Problem

The orbital boundary value problem, also known as Lambert Problem, is revisited. Building upon Lancaster and Blanchard approach, new relations are revealed and a new variable representing all problem classes, under L-similarity, is used to express the time of flight equation. In the new variable, the time of flight curves have two oblique asymptotes and they mostly appear to be conveniently approximated by piecewise continuous lines. We use and invert such a simple approximation to provide an efficient initial guess to an Householder iterative method that is then able to converge, for the single revoltuion case, in only two iterations. The resulting algorithm is compared to Gooding's procedure revealing to be numerically as accurate, while having a smaller computational complexity.

astro-ph.EP↗

arXiv2014

The Stark problem in the Weierstrassian formalism

We present a new general, complete closed-form solution of the Stark problem in terms of Weierstrass elliptic and related functions. With respect to previous treatments of the problem, our analysis is exact and valid for all values of the external force field, and it is expressed via unique formulæ valid for all initial conditions and parameters of the system. The simple form of the solution allows us to perform a thorough investigation of the properties of the dynamical system, including the identification of quasi-periodic and periodic orbits, the formulation of a simple analytical criterion to determine the boundness of the trajectory, and the characterisation of the equilibrium points.

math-ph↗

arXiv2010

Towards a High Fidelity Direct Transcription Method for Optimisation of Low-Thrust Trajectories

We build upon some new ideas in direct transcription methods developed within the Advanced Concepts Team to introduce two improvements to the Sims-Flanagan transcription for low-thrust trajectories. The obtained new algorithm is able to produce an operational trajectory accounting for the real spacecraft dynamics and adapting the segment duration on-line improving the final trajectory optimality.

math.OC↗

arXiv2010

On the Impact of the Migration Topology on the Island Model

Parallel Global Optimization Algorithms (PGOA) provide an efficient way of dealing with hard optimization problems. One method of parallelization of GOAs that is frequently applied and commonly found in the contemporary literature is the so-called Island Model (IM). In this paper we analyze the impact of the migration topology on the performance of a PGOA which uses the Island Model. In particular we consider parallel Differential Evolution and Simulated Annealing with Adaptive Neighborhood and draw first conclusions that emerge from the conducted experiments.

cs.DC↗

arXiv2010

A Global Optimisation Toolbox for Massively Parallel Engineering Optimisation

A software platform for global optimisation, called PaGMO, has been developed within the Advanced Concepts Team (ACT) at the European Space Agency, and was recently released as an open-source project. PaGMO is built to tackle high-dimensional global optimisation problems, and it has been successfully used to find solutions to real-life engineering problems among which the preliminary design of interplanetary spacecraft trajectories - both chemical (including multiple flybys and deep-space maneuvers) and low-thrust (limited, at the moment, to single phase trajectories), the inverse design of nano-structured radiators and the design of non-reactive controllers for planetary rovers. Featuring an arsenal of global and local optimisation algorithms (including genetic algorithms, differential evolution, simulated annealing, particle swarm optimisation, compass search, improved harmony search, and various interfaces to libraries for local optimisation such as SNOPT, IPOPT, GSL and NLopt), PaGMO is at its core a C++ library which employs an object-oriented architecture providing a clean and easily-extensible optimisation framework. Adoption of multi-threaded programming ensures the efficient exploitation of modern multi-core architectures and allows for a straightforward implementation of the island model paradigm, in which multiple populations of candidate solutions asynchronously exchange information in order to speed-up and improve the optimisation process. In addition to the C++ interface, PaGMO's capabilities are exposed to the high-level language Python, so that it is possible to easily use PaGMO in an interactive session and take advantage of the numerous scientific Python libraries available.

cs.DC↗

arXiv2006

Options for a nondedicated mission to test the Pioneer anomaly

The Doppler-tracking data of the Pioneer 10 and 11 spacecraft show an unmodelled constant acceleration in the direction of the inner Solar System. Serious efforts have been undertaken to find a conventional explanation for this effect, all without success at the time of writing. Hence the effect, commonly dubbed the Pioneer anomaly, is attracting considerable attention. Unfortunately, no other space mission has reached the long-term navigation accuracy to yield an independent test of the effect. To fill this gap we discuss strategies for an experimental verification of the anomaly via an upcoming space mission. Emphasis is put on two plausible scenarios: nondedicated concepts employing either a planetary exploration mission to the outer Solar System or a piggybacked micro-spacecraft to be launched from a mother spacecraft travelling to Saturn or Jupiter. The study analyses the impact of a Pioneer anomaly test on the system and trajectory design for these two paradigms. It is found that both paradigms are capable of verifying the Pioneer anomaly and determine its magnitude at 10% level. Moreover the concepts can discriminate between the most plausible classes of models of the anomaly, a central force, a blueshift of the radio signal and a drag-like force. The necessary adaptions of the system and mission design do not impair the planetary exploration goals of the missions.

astro-ph↗