An official website of the United States government
The earth’s orbit is becoming increasingly crowded with debris that poses significant safety risks to the operation of existing and new spacecraft and satellites. The active tether-net system, which consists of a flexible net with maneuverable corner nodes, launched from a small autonomous spacecraft, is a promising solution to capturing and disposing of such space debris. The requirement of autonomous operation and the need to generalize over debris scenarios in terms of different rotational rates makes the capture process significantly challenging. The space debris could rotate about multiple axes, which along with sensing/estimation and actuation uncertainties, call for a robust, generalizable approach to guiding the net launch and flight – one that can guarantee robust capture. This paper proposes a decentralized actuation system combined with reinforcement learning based on prior work in designing and controlling this tether-net system. In this new system, four microsatellites with thrusters act as the corner nodes of the net, and can thus help control the flight of the net after launch. The microsatellites pull the net to complete the task of approaching and capturing the space debris. The proposed method uses a reinforcement learning framework that integrates a proximal policy optimization to find the optimal solution based on the dynamics simulation of the net and the MUs in Vortex Studio. The reinforcement learning framework finds the optimal trajectory that is both energy-efficient and ensures a desired level of capture quality
more »
« less
Concurrent Design Optimization of Tether-Net System and Actions for Reliable Space-Debris Capture
Tether-nets deployed from a chaser spacecraft are a promising solution to capturing space debris. The success of the one-shot capture process depends on the net’s structural dynamic properties, attributed to its physical design, and on the ability to perform an optimal launch and closure subject to sensing and actuation uncertainties. Hence, this paper presents a reliability-based optimization framework to simultaneously optimize the net design and its launch and closing actions to minimize the system mass (case 1) or closing time (case 2) while preserving a specified probability of capture success. Success is assessed in terms of a capture quality index and the number of locked node pairs. Gaussian noise is used to model the uncertainties in the dynamics, state estimation, and actuation of the tether-net, which is propagated via Monte Carlo sampling. To account for uncertainties and ensure computational efficiency, given the cost of simulating the tether-net dynamics, Bayesian optimization is used to solve this problem. Optimization results show that the mission success rate in the presence of uncertainties has increased from 75% to over 98%, while the capture completion time has almost halved.
more »
« less
- Award ID(s):
- 2128578
- PAR ID:
- 10538895
- Publisher / Repository:
- AIAA
- Date Published:
- Journal Name:
- Journal of Spacecraft and Rockets
- Volume:
- 61
- Issue:
- 3
- ISSN:
- 0022-4650
- Page Range / eLocation ID:
- 773 to 783
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Tethered net systems are considered one of the most effective solutions for addressing the problem of space debris. However, it is crucial to study the robustness of net-based debris capture in the presence of a wide range of possible activation and environmental uncertainties. The aim of this study was to analyze the limitations and operational envelope of tethered net systems in capturing space debris, with a particular focus on robustness and safety. The success of capture in nonnominal conditions was investigated, with errors considered in the target position, angular velocity, and parameters concerning the ejection of the net. In the sensitivity study, a capture quality index and mission safety factor were used to evaluate the success or failure of capture in an automated way. The quantitative relationships between relative parameter errors and capture evaluation metrics are also presented. The results of the sensitivity studies are promising and suggest that the target capture is robust to inaccuracies in the mission parameters beyond what is expected in reality.more » « less
-
Abstract Fish fin rays constitute a sophisticated control system for ray-finned fish, facilitating versatile locomotion within complex fluid environments. Despite extensive research on the kinematics and hydrodynamics of fish locomotion, the intricate control strategies in fin-ray actuation remain largely unexplored. While deep reinforcement learning (DRL) has demonstrated potential in managing complex nonlinear dynamics; its trial-and-error nature limits its application to problems involving computationally demanding environmental interactions. This study introduces a cutting-edge off-policy DRL algorithm, interacting with a fluid–structure interaction (FSI) environment to acquire intricate fin-ray control strategies tailored for various propulsive performance objectives. To enhance training efficiency and enable scalable parallelism, an innovative asynchronous parallel training (APT) strategy is proposed, which fully decouples FSI environment interactions and policy/value network optimization. The results demonstrated the success of the proposed method in discovering optimal complex policies for fin-ray actuation control, resulting in a superior propulsive performance compared to the optimal sinusoidal actuation function identified through a parametric grid search. The merit and effectiveness of the APT approach are also showcased through comprehensive comparison with conventional DRL training strategies in numerical experiments of controlling nonlinear dynamics.more » « less
-
Abstract Silicon anodes have been demonstrated to provide significant actuation in addition to energy storage in lithium-ion batteries (LIBs). This work studies the optimization of 1D unimorph and bimorph actuators to achieve a target shape upon actuation. A 1D shape matching with design optimization is used to estimate the varied charge distribution along the length for a LIB actuator and thereby the effect of distance between electrodes in charging. A genetic algorithm (GA) is used with actuation strain distribution as the design variable. The objective of the optimization is to shape-match by minimizing the shape error between a target shape and actuated shape, both defined by several points along the length. The approach is experimentally validated by shape matching a notched unimorph target shape. A shape error of 1.5% is obtained. An optimized unimorph converges to an objective function of less than 0.029% of the length at full state of charge (SOC) for a 5-segment beam. A second shape matching case study using a bimorph is investigated to showcase the tailorability of LIB actuators. The optimal bimorph achieves an objective function of less than 0.23% of the length for a design variable set of top and bottom actuation strain of an 8-segment beam. The actuated shape nearly matches the target shape by simultaneously activating top and bottom active layers to achieve the same differential actuation strain (the difference between top and bottom active layer actuation strain). The results show that a bimorph actuator can achieve a given shape while also storing significantly more charge than is necessary to maintain a given complex shape. This demonstrates a strength of energy storage based actuators: excess energy can be stored within the actuator and can be expended without affecting the work done or the shape maintained by the actuator.more » « less
-
null (Ed.)Dielectric elastomer (DE) materials, a category of electroactive polymers, can be used to design actuators that are flexible, resilient, lightweight, and durable. However, due to the uncertainties in its actuation dynamics, DE actuators always rely on feedback control to perform accurate and safe operations. In this paper, a tubular dielectric elastomer actuator (DEA) with self-sensing capability is developed. It does not require external devices to measure displacement for feedback control. The displacement of the actuator is controlled using a proportional-integral controller with the capacitance measured at high probing frequency as the self-sensing mechanism component of the actuator. By superimposing actuation and probing voltage and applying them to the DE tube, the actuation voltage activates the movement of the DE tube and the probing voltage is used for self-sensing. Fast Fourier Transform (FFT) is then used to filter a given frequency of the probing current and voltage and then calculate the capacitance from the probing current and voltage during each time window. With the relationship between capacitance and displacement of the DE tube, the displacement output is estimated online and self-sensing without an external sensor is achieved. The self-sensing signal is then used as a feedback signal in a closed-loop design to follow a reference signal for tracking. The experimental results validate the self-sensing of the DE actuator in feedback control.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.2514/1.A35812
