Naoya Ozaki

Masato Shibukawa, Fumi Yoshida, Toshifumi Yanagisawa et al.

One of the greatest challenges for detecting moving objects in the solar system from wide-field survey data is determining whether a signal indicates a true object or is due to some other source, like noise. Object verification has relied heavily on human eyes, which usually results in significant labor costs. In order to address this limitation and reduce the reliance on manual intervention, we propose a multi-input convolutional neural network integrated with a convolutional block attention module. This method is specifically tailored to enhance the moving object detection system that we have developed and used previously. The current method introduces two innovations. This first one is a multi-input architecture that processes multiple stacked images simultaneously. The second is the incorporation of the convolutional block attention module which enables the model to focus on essential features in both spatial and channel dimensions. These advancements facilitate efficient learning from multiple inputs, leading to more robust detection of moving objects. The performance of the model is evaluated on a dataset consisting of approximately 2,000 observational images. We achieved an accuracy of nearly 99% with AUC (an Area Under the Curve) of >0.99. These metrics indicate that the proposed model achieves excellent classification performance. By adjusting the threshold for object detection, the new model reduces the human workload by more than 99% compared to manual verification.

Takayuki Hosonuma, Takeshi Miyabara, Naoya Ozaki et al.

DESTINY+ is an upcoming JAXA Epsilon medium-class mission to flyby multiple asteroids including Phaethon. As an asteroid flyby observation instrument, a telescope mechanically capable of single-axis rotation, named TCAP, is mounted on the spacecraft to track and observe the target asteroids during flyby. As in past flyby missions utilizing rotating telescopes, TCAP is also used as a navigation camera for autonomous optical navigation during the closest-approach phase. To mitigate the degradation of the navigation accuracy, past missions performed calibration of the navigation camera's alignment before starting optical navigation. However, such calibration requires significant operational time to complete and imposes constraints on the operation sequence. From the above background, the DESTINY+ team has studied the possibility of reducing operational costs by allowing TCAP alignment errors to remain. This paper describes an autonomous optical navigation algorithm robust to the misalignment of rotating telescopes, proposed in this context. In the proposed method, the misalignment of the telescope is estimated simultaneously with the spacecraft's orbit relative to the flyby target. To deal with the nonlinearity between the misalignment and the observation value, the proposed method utilizes the unscented Kalman filter, instead of the extended Kalman filter widely used in past studies. The proposed method was evaluated with numerical simulations on a PC and with hardware-in-the-loop simulation, taking the Phaethon flyby in the DESTINY+ mission as an example. The validation results suggest that the proposed method can mitigate the misalignment-induced degradation of the optical navigation accuracy with reasonable computational costs suited for onboard computers.

Naoya Ozaki, Kanta Yanagida, Takuya Chikazawa et al.

Asteroid exploration has been attracting more attention in recent years. Nevertheless, we have just visited tens of asteroids while we have discovered more than one million bodies. As our current observation and knowledge should be biased, it is essential to explore multiple asteroids directly to better understand the remains of planetary building materials. One of the mission design solutions is utilizing asteroid flyby cycler trajectories with multiple Earth gravity assists. An asteroid flyby cycler trajectory design problem is a subclass of global trajectory optimization problems with multiple flybys, involving a trajectory optimization problem for a given flyby sequence and a combinatorial optimization problem to decide the sequence of the flybys. As the number of flyby bodies grows, the computation time of this optimization problem expands maliciously. This paper presents a new method to design asteroid flyby cycler trajectories utilizing a surrogate model constructed by deep neural networks approximating trajectory optimization results. Since one of the bottlenecks of machine learning approaches is the computation time to generate massive trajectory databases, we propose an efficient database generation strategy by introducing pseudo-asteroids satisfying the Karush-Kuhn-Tucker conditions. The numerical result applied to JAXA's DESTINY+ mission shows that the proposed method is practically applicable to space mission design and can significantly reduce the computational time for searching asteroid flyby sequences.