22 April 2020 in IEEE Transactions on Aerospace and Electronic Systems
Accurate orbit prediction (OP) of space debris is vital in Space Situation Awareness (SSA) related tasks, like space collision warnings. However, due to the sparse and low precision observations, unknown geometrical and physical features of debris, and effects of incomplete force models, OP based on the orbital mechanics theory or physics-based OP of space debris suffers from rapid error growth over a long duration, limiting the period of validity of debris OP for precise space applications. Considering that the tracking arcs of a debris object over a single station often share a similar temporal and spatial distribution in the inertial space, the resultant OP errors possibly have a coherent relationship with the temporal and spatial distribution of tracking arcs. This paper proposes a machine learning (ML)-based approach to model the underlying pattern of debris OP errors from historical observations and apply it to modify the future physics-based OP results. The approach includes three steps: constructing a historical OP error set, training a ML model to fit the historical OP error set, and correcting the future physics-based OP with ML-predicted orbital errors. The ensemble learning algorithm of boosting tree (BT) is studied as the primary ML method for the error modeling and predicting process. Experiments with three low-Earth-orbit (LEO) objects, tracked by a single radar station, demonstrate that the trained ML models can capture more than 80% of the underlying pattern of the historical OP errors. More importantly, the errors of physics-based OP over the future 7 days reduce from thousands of meters to hundreds or even tens of meters through the error correction with the learned error pattern, achieving at least 50% accuracy improvement. Such dramatic OP improvements show the promising potential of ML for enhanced SSA capability.
1 November 2021 in Acta Astronautica
20 January 2013 in JOURNAL OF RADARS
25 September 2012 in Research in Astronomy and Astrophysics
Object correlation and maneuver detection are persistent problems in space surveillance and maintenance of a space object catalog. We integrate these two problems into one interrelated problem, and consider them simultaneously under a scenario where space objects only perform a single in-track orbital maneuver during the time intervals between observations. We mathematically formulate this integrated scenario as a maximum a posteriori (MAP) estimation. In this work, we propose a novel approach to solve the MAP estimation. More precisely, the corresponding posterior probability of an orbital maneuver and a joint association event can be approximated by the Joint Probabilistic Data Association (JPDA) algorithm. Subsequently, the maneuvering parameters are estimated by optimally solving the constrained non-linear least squares iterative process based on the second-order cone programming (SOCP) algorithm. The desired solution is derived according to the MAP criterions. The per- formance and advantages of the proposed approach have been shown by both theoretical analysis and simulation results. We hope that our work will stimulate future work on space surveillance and maintenance of a space object catalog.
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Text-based knowledge graph completion methods take advantage of pre-trained language models (PLM) to enhance intrinsic semantic connections of raw triplets with detailed text descriptions. Typical methods in this branch map an input query (textual descriptions associated with an entity and a relation) and its candidate entities into feature vectors, respectively, and then maximize the probability of valid triples. These methods are gaining promising performance and increasing attention for the rapid development of large language models. According to the property of the language models, the more related and specific context information the input query provides, the more discriminative the resultant embedding will be. In this paper, through observation and validation, we find a neglected fact that the relation-aware neighbors of the head entities in queries could act as effective contexts for more precise link prediction. Driven by this finding, we propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC). Specifically, in our method, to provide a reference of what might the target entity be like, we first generate anchor entities within the relation-aware neighborhood of the head entity. Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching. The results of our extensive experiments not only validate the efficacy of RAA-KGC but also reveal that by integrating our relation-aware anchor enhancement strategy, the performance of current leading methods can be notably enhanced without substantial modifications.