arXiv subjects

Roberto Furfaro

Publications and source records attributed to Roberto Furfaro.

33 records · Page 2Linked to original sources

arXiv2020

Six Degree-of-Freedom Body-Fixed Hovering over Unmapped Asteroids via LIDAR Altimetry and Reinforcement Meta-Learning

We optimize a six degrees of freedom hovering policy using reinforcement meta-learning. The policy maps flash LIDAR measurements directly to on/off spacecraft body-frame thrust commands, allowing hovering at a fixed position and attitude in the asteroid body-fixed reference frame. Importantly, the policy does not require position and velocity estimates, and can operate in environments with unknown dynamics, and without an asteroid shape model or navigation aids. Indeed, during optimization the agent is confronted with a new randomly generated asteroid for each episode, insuring that it does not learn an asteroid's shape, texture, or environmental dynamics. This allows the deployed policy to generalize well to novel asteroid characteristics, which we demonstrate in our experiments. Moreover, our experiments show that the optimized policy adapts to actuator failure and sensor noise. Although the policy is optimized using randomly generated synthetic asteroids, it is tested on two shape models from actual asteroids: Bennu and Itokawa. We find that the policy generalizes well to these shape models. The hovering controller has the potential to simplify mission planning by allowing asteroid body-fixed hovering immediately upon the spacecraft's arrival to an asteroid. This in turn simplifies shape model generation and allows resource mapping via remote sensing immediately upon arrival at the target asteroid.

eess.SY↗

arXiv2020

Fuel-Efficient Powered Descent Guidance on Large Planetary Bodies via Theory of Functional Connections

In this paper we present a new approach to solve the fuel-efficient powered descent guidance problem on large planetary bodies with no atmosphere (e.g. the Moon or Mars) using the recently developed Theory of Functional Connections. The problem is formulated using the indirect method which casts the optimal guidance problem as a system of nonlinear two-point boundary value problems. Using the Theory of Functional Connections, the problem constraints are analytically embedded into a "constrained expression," which maintains a free-function that is expanded using orthogonal polynomials with unknown coefficients. The constraints are satisfied regardless of the values of the unknown coefficients which convert the two-point boundary value problem into an unconstrained optimization problem. This process casts the solution into the admissible subspace of the problem and therefore simple numerical techniques can be used (i.e. in this paper a nonlinear least-squares method is used). In addition to the derivation of this technique, the method is validated in two scenarios and the results are compared to those obtained by the general purpose optimal control software, GPOPS-II. In general, the proposed technique produces solutions of $\mathcal{O}(10^{-10})$. Additionally, for the proposed test cases, it is reported that each individual TFC-based inner-loop iteration converges within 6 iterations, each iteration exhibiting a computational time between 72 and 81 milliseconds within the MATLAB legacy implementation. Consequently, the proposed methodology is potentially suitable for on-board generation of optimal trajectories in real-time.

math.OC↗

arXiv2020

Realistic On-the-fly Outcomes of Planetary Collisions II: Bringing Machine Learning to N-body Simulations

Terrestrial planet formation theory is at a bottleneck, with the growing realization that pairwise collisions are treated far too simply. Here, and in our companion paper (Cambioni et al. 2019) that introduces the training methodology, we demonstrate the first application of machine learning to more realistically model the late stage of planet formation by giant impacts. We present surrogate models that give fast, reliable answers for the masses and velocities of the two largest remnants of a giant impact, as a function of the colliding masses and their impact velocity and angle, with the caveat that our training data do not yet include pre-impact rotation or variable thermal conditions. We compare canonical N-body scenarios of terrestrial planet formation assuming perfect merger (Chambers 2001) with our more realistic treatment that includes inefficient accretions and hit-and-run collisions. The result is a protracted tail of final events lasting ~200 Myr, and the conversion of about half the mass of the initial population to debris. We obtain profoundly different solar system architectures, featuring a much wider range of terrestrial planet masses and enhanced compositional diversity.

astro-ph.EP↗

arXiv2019

Space Objects Maneuvering Prediction via Maximum Causal Entropy Inverse Reinforcement Learning

Inverse Reinforcement Learning (RL) can be used to determine the behavior of Space Objects (SOs) by estimating the reward function that an SO is using for control. The approach discussed in this work can be used to analyze maneuvering of SOs from observational data. The inverse RL problem is solved using maximum causal entropy. This approach determines the optimal reward function that a SO is using while maneuvering with random disturbances by assuming that the observed trajectories are optimal with respect to the SO's own reward function. Lastly, this paper develops results for scenarios involving Low Earth Orbit (LEO) station-keeping and Geostationary Orbit (GEO) station-keeping.

eess.SY↗

arXiv2019

Reinforcement Learning for Angle-Only Intercept Guidance of Maneuvering Targets

We present a novel guidance law that uses observations consisting solely of seeker line of sight angle measurements and their rate of change. The policy is optimized using reinforcement meta-learning and demonstrated in a simulated terminal phase of a mid-course exo-atmospheric interception. Importantly, the guidance law does not require range estimation, making it particularly suitable for passive seekers. The optimized policy maps stabilized seeker line of sight angles and their rate of change directly to commanded thrust for the missile's divert thrusters. The use of reinforcement meta-learning allows the optimized policy to adapt to target acceleration, and we demonstrate that the policy performs as well as augmented zero-effort miss guidance with perfect target acceleration knowledge. The optimized policy is computationally efficient and requires minimal memory, and should be compatible with today's flight processors.

eess.SY↗

arXiv2019

Seeker based Adaptive Guidance via Reinforcement Meta-Learning Applied to Asteroid Close Proximity Operations

Current practice for asteroid close proximity maneuvers requires extremely accurate characterization of the environmental dynamics and precise spacecraft positioning prior to the maneuver. This creates a delay of several months between the spacecraft's arrival and the ability to safely complete close proximity maneuvers. In this work we develop an adaptive integrated guidance, navigation, and control system that can complete these maneuvers in environments with unknown dynamics, with initial conditions spanning a large deployment region, and without a shape model of the asteroid. The system is implemented as a policy optimized using reinforcement meta-learning. The spacecraft is equipped with an optical seeker that locks to either a terrain feature, back-scattered light from a targeting laser, or an active beacon, and the policy maps observations consisting of seeker angles and LIDAR range readings directly to engine thrust commands. The policy implements a recurrent network layer that allows the deployed policy to adapt real time to both environmental forces acting on the agent and internal disturbances such as actuator failure and center of mass variation. We validate the guidance system through simulated landing maneuvers in a six degrees-of-freedom simulator. The simulator randomizes the asteroid's characteristics such as solar radiation pressure, density, spin rate, and nutation angle, requiring the guidance and control system to adapt to the environment. We also demonstrate robustness to actuator failure, sensor bias, and changes in the spacecraft's center of mass and inertia tensor. Finally, we suggest a concept of operations for asteroid close proximity maneuvers that is compatible with the guidance system.

eess.SY↗

arXiv2019

Adaptive Guidance and Integrated Navigation with Reinforcement Meta-Learning

This paper proposes a novel adaptive guidance system developed using reinforcement meta-learning with a recurrent policy and value function approximator. The use of recurrent network layers allows the deployed policy to adapt real time to environmental forces acting on the agent. We compare the performance of the DR/DV guidance law, an RL agent with a non-recurrent policy, and an RL agent with a recurrent policy in four challenging environments with unknown but highly variable dynamics. These tasks include a safe Mars landing with random engine failure and a landing on an asteroid with unknown environmental dynamics. We also demonstrate the ability of a RL meta-learning optimized policy to implement a guidance law using observations consisting of only Doppler radar altimeter readings in a Mars landing environment, and LIDAR altimeter readings in an asteroid landing environment, thus integrating guidance and navigation.

eess.SY↗

arXiv2019

Realistic On-The-Fly Outcomes of Planetary Collisions: Machine Learning Applied to Simulations of Giant Impacts

Planet formation simulations are capable of directly integrating the evolution of hundreds to thousands of planetary embryos and planetesimals, as they accrete pairwise to become planets. In principle such investigations allow us to better understand the final configuration and geochemistry of the terrestrial planets, as well as to place our solar system in the context of other exosolar systems. These simulations, however, classically prescribe collisions to result in perfect mergers, but computational advances have begun to allow for more complex outcomes to be implemented. Here we apply machine learning to a large but sparse database of giant impact studies, streamlining simulations into a classifier of collision outcomes and a regressor of accretion efficiency. The classifier maps a 4-Dimensional parameter space (target mass, projectile-to-target mass ratio, impact velocity, impact angle) into the four major collision types: merger, "graze-and-merge", "hit-and-run", and disruption. The definition of the four regimes and their boundary is fully data-driven; the results do not suffer from any model assumption in the fitting. The classifier maps the structure of the parameter space and provides insights about the outcome regimes. The regressor is a neural network which is trained to closely mimic the functional relationship between the 4-D space of collision parameters, and a real-variable outcome, the mass of the largest remnant. This work is a prototype of a more complete surrogate model, based on extended sets of simulations ("big data"), that will quickly and reliably predict specific collision outcomes for use in realistic N-body dynamical studies of planetary formation.

astro-ph.EP↗

arXiv2019

Constraining the Thermal Properties of Planetary Surfaces using Machine Learning: Application to Airless Bodies

We present a new method for the determination of the surface properties of airless bodies from measurements of the emitted infrared flux. Our approach uses machine learning techniques to train, validate, and test a neural network representation of the thermophysical behavior of the atmosphereless body given shape model, illumination and observational geometry of the remote sensors. The networks are trained on a dataset of thermal simulations of the emitted infrared flux for different values of surface rock abundance, roughness, and values of the thermal inertia of the regolith and of the rock components. These surrogate models are then employed to retrieve the surface thermal properties by Markov Chain Monte Carlo Bayesian inversion of observed infrared fluxes. We apply the method to the inversion of simulated infrared fluxes of asteroid (101195) Bennu -- according to a geometry of observations similar to those planned for NASA's OSIRIS-REx mission -- and infrared observations of asteroid (25143) Itokawa. In both cases, the surface properties of the asteroid -- such as surface roughness, thermal inertia of the regolith and rock component, and relative rock abundance -- are retrieved; the contribution from the regolith and rock components are well separated. For the case of Itokawa, we retrieve a rock abundance of about 85% for pebbles larger than the diurnal skin depth, which is about 2 cm. The thermal inertia of the rock is found to be lower than the expected value for LL chondrites, indicating that the rocks on Itokawa could be fractured. The average thermal inertia of the surface is around 750 $J s^{-1/2} K^{-1} m^{-2}$ and the measurement of thermal inertia of the regolith corresponds to an average regolith particle diameter of about 10 mm, consistently with in situ measurements as well as results from previous studies.

astro-ph.EP↗

arXiv2019

End to End Satellite Servicing and Space Debris Management

There is growing demand for satellite swarms and constellations for global positioning, remote sensing and relay communication in higher LEO orbits. This will result in many obsolete, damaged and abandoned satellites that will remain on-orbit beyond 25 years. These abandoned satellites and space debris maybe economically valuable orbital real-estate and resources that can be reused, repaired or upgraded for future use. Space traffic management is critical to repair damaged satellites, divert satellites into warehouse orbits and effectively de-orbit satellites and space debris that are beyond repair and salvage. Current methods for on-orbit capture, servicing and repair require a large service satellite. However, by accessing abandoned satellites and space debris, there is an inherent heightened risk of damage to a servicing spacecraft. Sending multiple small-robots with each robot specialized in a specific task is a credible alternative, as the system is simple and cost-effective and where loss of one or more robots does not end the mission. In this work, we outline an end to end multirobot system to capture damaged and abandoned spacecraft for salvaging, repair and for de-orbiting. We analyze the feasibility of sending multiple, decentralized robots that can work cooperatively to perform capture of the target satellite as a first step, followed by crawling onto damage satellites to perform detailed mapping. After obtaining a detailed map of the satellite, the robots will proceed to either repair and replace or dismantle components for salvage operations. Finally, the remaining components will be packaged with a de-orbit device for accelerated de-orbit.

physics.space-ph↗

arXiv2019

Learning Accurate Extended-Horizon Predictions of High Dimensional Trajectories

We present a novel predictive model architecture based on the principles of predictive coding that enables open loop prediction of future observations over extended horizons. There are two key innovations. First, whereas current methods typically learn to make long-horizon open-loop predictions using a multi-step cost function, we instead run the model open loop in the forward pass during training. Second, current predictive coding models initialize the representation layer's hidden state to a constant value at the start of an episode, and consequently typically require multiple steps of interaction with the environment before the model begins to produce accurate predictions. Instead, we learn a mapping from the first observation in an episode to the hidden state, allowing the trained model to immediately produce accurate predictions. We compare the performance of our architecture to a standard predictive coding model and demonstrate the ability of the model to make accurate long horizon open-loop predictions of simulated Doppler radar altimeter readings during a six degree of freedom Mars landing. Finally, we demonstrate a 2X reduction in sample complexity by using the model to implement a Dyna style algorithm to accelerate policy learning with proximal policy optimization.

cs.LG↗

arXiv2018

Deep Reinforcement Learning for Six Degree-of-Freedom Planetary Powered Descent and Landing

Future Mars missions will require advanced guidance, navigation, and control algorithms for the powered descent phase to target specific surface locations and achieve pinpoint accuracy (landing error ellipse $<$ 5 m radius). The latter requires both a navigation system capable of estimating the lander's state in real-time and a guidance and control system that can map the estimated lander state to a commanded thrust for each lander engine. In this paper, we present a novel integrated guidance and control algorithm designed by applying the principles of reinforcement learning theory. The latter is used to learn a policy mapping the lander's estimated state directly to a commanded thrust for each engine, with the policy resulting in accurate and fuel-efficient trajectories. Specifically, we use proximal policy optimization, a policy gradient method, to learn the policy. Another contribution of this paper is the use of different discount rates for terminal and shaping rewards, which significantly enhances optimization performance. We present simulation results demonstrating the guidance and control system's performance in a 6-DOF simulation environment and demonstrate robustness to noise and system parameter uncertainty.

eess.SY↗

arXiv2018

Satellite Capture and Servicing Using Networks of Tethered Robots Supported by Ground Surveillance

There is ever growing demand for satellite constellations that perform global positioning, remote sensing, earth-imaging and relay communication. In these highly prized orbits, there are many obsolete and abandoned satellites and components strewn posing ever-growing logistical challenges. This increased demand for satellite constellations pose challenges for space traffic management, where there is growing need to identify the risks probabilities and if possible mitigate them. These abandoned satellites and space debris maybe economically valuable orbital real-estate and resources that can be reused, repaired or upgraded for future use. On-orbit capture and servicing of a satellite requires satellite rendezvous, docking and repair, removal and replacement of components. Launching a big spacecraft that perform satellites servicing is one credible approach for servicing and maintaining next-generation constellations. By accessing abandoned satellites and space debris, there is an inherent heightened risk of damage to a servicing spacecraft. Under these scenarios, sending multiple, small-robots with each robot specialized in a specific task is a credible alternative, as the system is simple and cost-effective and where loss of one or more of robot does not end the mission. Eliminating the need for a large spacecraft or positioning the large spacecraft at safe distance to provide position, navigation and tracking support simplifies the system and enable the approach to be extensible with the latest ground-based sensing technology. In this work, we analyze the feasibility of sending multiple, decentralized robots that can work cooperatively to perform capture of the target satellite as first steps to on-orbit satellite servicing.

cs.RO↗

arXiv2018

On-Orbit Smart Camera System to Observe Illuminated and Unilluminated Space Objects

The wide availability of Commercial Off-The-Shelf (COTS) electronics that can withstand Low Earth Orbit conditions has opened avenue for wide deployment of CubeSats and small-satellites. CubeSats thanks to their low developmental and launch costs offer new opportunities for rapidly demonstrating on-orbit surveillance capabilities. In our earlier work, we proposed development of SWIMSat (Space based Wide-angle Imaging of Meteors) a 3U CubeSat demonstrator that is designed to observe illuminated objects entering the Earth's atmosphere. The spacecraft would operate autonomously using a smart camera with vision algorithms to detect, track and report of objects. Several CubeSats can track an object in a coordinated fashion to pinpoint an object's trajectory. An extension of this smart camera capability is to track unilluminated objects utilizing capabilities we have been developing to track and navigate to Near Earth Objects (NEOs). This extension enables detecting and tracking objects that can't readily be detected by humans. The system maintains a dense star map of the night sky and performs round the clock observations. Standard optical flow algorithms are used to obtain trajectories of all moving objects in the camera field of view. Through a process of elimination, certain stars maybe occluded by a transiting unilluminated object which is then used to first detect and obtain a trajectory of the object. Using multiple cameras observing the event from different points of view, it may be possible then to triangulate the position of the object in space and obtain its orbital trajectory. In this work, the performance of our space object detection algorithm coupled with a spacecraft guidance, navigation, and control system is demonstrated.

cs.CV↗

arXiv2018

Surface Composition of (99942) Apophis

On April 13, 2029, near-Earth asteroid (NEA) (99942) Apophis will pass at a distance of 6 Earth radii from Earth. This event will provide researchers with a unique opportunity to study the effects of tidal forces experienced by an asteroid during a close encounter with a terrestrial planet. Binzel et al. (2010) predicted that close flybys of terrestrial planets by NEAs would cause resurfacing of their regolith due to seismic shaking. In this work we present the best pre-encounter near-infrared spectra of Apophis obtained so far. These new data were obtained during the 2013 apparition using the NASA Infrared Telescope Facility (IRTF). We found that our spectral data is consistent with previous observations by Binzel et al. (2009) but with a much higher signal-to-noise ratio. Spectral band parameters were extracted from the spectra and were used to determine the composition of the asteroid. Using a naive Bayes classifier, we computed the likelihood of Apophis being an LL chondrite to be >99% based on mol% of Fa vs. Fs. Using the same method, we estimated a probability of 89% for Apophis being an LL chondrite based on ol/(ol+px) and Fs. The results from the dynamical model indicate that the most likely source region for Apophis is the nu6 resonance in the inner main belt. Data presented in this study (especially Band I depth) could serve as a baseline to verify seismic shaking during the 2029 encounter.

astro-ph.EP↗