Vsevolod V. Koryanov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Vsevolod V. Koryanov has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
Victor P. Kazakovtsev
Bauman Moscow State Technical University, 105005, 2-nd Baumanskaya, 5, b1, Moscow, Russian Federation
10 shared publicationsAlexey G. Toporkov
Dynamics and flight control of motion of rockets and spacecraft, Bauman Moscow State Technical University (BMSTU), Moscow, Russia
6 shared publications- Anton A. Nedogarok
Bauman Moscow State Technical University
3 shared publications - Danhe Chen
Nanjing University of Science and Technology
3 shared publications - Konstantin S. Fedyaev
Space Research Institute of the Russian Academy of Sciences
3 shared publications - Vladislav A. Zubko
Space Research Institute of the Russian Academy of Sciences
3 shared publications
Latest Publications
- 10 September 2026
- Published by Pleiades Publishing Ltd in Solar System Research
- Vol. 60 (5) , 54
Statistical Analysis and Neural Network Approximation of Mass-Optimal, Free-Final-Time Trajectories Using Kolmogorov–Arnold Networks for Multi-Target Rendezvous Planning
This paper addresses the statistical analysis and prediction of characteristics for mass-optimal, free-final-time (MOFFT) transfer trajectories of spacecraft equipped with electric propulsion systems. Transitioning from single-target flybys to multi-target asteroid missions requires evaluating numerous orbital transfer options. Classical indirect methods for solving MOFFT trajectory problems suffer from severe sensitivity of the boundary value problem to the initial guess of costate variables. To overcome this, a two-level parameter homotopy continuation scheme is proposed. This approach enabled the generation of a large-scale dataset and, through subsequent statistical analysis, the determination of an optimal empirical coefficient k to achieve an efficient balance between propellant consumption and flight time. To resolve the absence of an a priori initial guess when solving boundary value problems, a proxy model based on Fast Kolmogorov–Arnold Networks (FastKAN) was developed. It is demonstrated that incorporating FastKAN significantly enhances the convergence probability of the numerical shooting method without requiring a priori approximations. The trained FastKAN model is integrated into a beam search algorithm to plan multi-target rendezvous sequences. This approach is shown to nearly double the number of visited asteroids, given identical resource constraints, compared to planning based on time-optimal trajectories, thereby ensuring high ballistic efficiency and increasing the potential scientific value of the designed missions.
- 10 September 2026
- Published by Pleiades Publishing Ltd in Solar System Research
- Vol. 60 (5) , 54
Statistical Analysis and Neural Network Approximation of Mass-Optimal, Free-Final-Time Trajectories Using Kolmogorov–Arnold Networks for Multi-Target Rendezvous Planning
This paper addresses the statistical analysis and prediction of characteristics for mass-optimal, free-final-time (MOFFT) transfer trajectories of spacecraft equipped with electric propulsion systems. Transitioning from single-target flybys to multi-target asteroid missions requires evaluating numerous orbital transfer options. Classical indirect methods for solving MOFFT trajectory problems suffer from severe sensitivity of the boundary value problem to the initial guess of costate variables. To overcome this, a two-level parameter homotopy continuation scheme is proposed. This approach enabled the generation of a large-scale dataset and, through subsequent statistical analysis, the determination of an optimal empirical coefficient k to achieve an efficient balance between propellant consumption and flight time. To resolve the absence of an a priori initial guess when solving boundary value problems, a proxy model based on Fast Kolmogorov–Arnold Networks (FastKAN) was developed. It is demonstrated that incorporating FastKAN significantly enhances the convergence probability of the numerical shooting method without requiring a priori approximations. The trained FastKAN model is integrated into a beam search algorithm to plan multi-target rendezvous sequences. This approach is shown to nearly double the number of visited asteroids, given identical resource constraints, compared to planning based on time-optimal trajectories, thereby ensuring high ballistic efficiency and increasing the potential scientific value of the designed missions.
- 30 July 2026
- Published by Springer Nature
- p. 365-372
Concept of a LEO Augmentation Constellation for GLONASS
- 30 July 2026
- Published by Springer Nature
- p. 365-372
Concept of a LEO Augmentation Constellation for GLONASS
- 11 March 2026
- Published by Springer Nature in Astrodynamics
- Vol. 10 (2) , 239-259
Trajectory design for comet 67P/Churyumov–Gerasimenko mission: Multiple gravity assist analysis using Tisserand Graph
- 11 March 2026
- Published by Springer Nature in Astrodynamics
- Vol. 10 (2) , 239-259
Trajectory design for comet 67P/Churyumov–Gerasimenko mission: Multiple gravity assist analysis using Tisserand Graph
- Open Access
- 6 March 2026
- Published by IOS Press
- p. 406-413
Application of the Ensemble Model TabM to Predict Fuel-Optimal Low-Thrust Transfers
In multi-target interplanetary mission design, fuel consumption is a critical performance metric. Accurate and rapid estimation of fuel-optimal low-thrust transfers is therefore critically important for practical mission design. From a deep learning perspective, this prediction task can be formulated as a regression problem. While multilayer perceptrons (MLPs) are widely used as baseline regressors due to their strong universal approximation capabilities, single MLP models often suffer from overfitting or underfitting. In contrast, ensemble networks leverage structured feature interaction mechanisms to capture complex physical relationships among inputs more effectively, thereby enhancing model robustness and generalization. In this work, we first generate a dataset encompassing a broad range of orbital elements using the Homotopy Ray Method, which enables rapid computation of low-thrust trajectories. We then train and evaluate different models, comparing the performance of the ensemble networks TabM and TabMmini against a baseline MLP. Comparative evaluation demonstrates the superior predictive performance of TabMmini.
- 6 March 2026
- Published by IOS Press
- p. 406-413
Open AccessApplication of the Ensemble Model TabM to Predict Fuel-Optimal Low-Thrust Transfers
In multi-target interplanetary mission design, fuel consumption is a critical performance metric. Accurate and rapid estimation of fuel-optimal low-thrust transfers is therefore critically important for practical mission design. From a deep learning perspective, this prediction task can be formulated as a regression problem. While multilayer perceptrons (MLPs) are widely used as baseline regressors due to their strong universal approximation capabilities, single MLP models often suffer from overfitting or underfitting. In contrast, ensemble networks leverage structured feature interaction mechanisms to capture complex physical relationships among inputs more effectively, thereby enhancing model robustness and generalization. In this work, we first generate a dataset encompassing a broad range of orbital elements using the Homotopy Ray Method, which enables rapid computation of low-thrust trajectories. We then train and evaluate different models, comparing the performance of the ensemble networks TabM and TabMmini against a baseline MLP. Comparative evaluation demonstrates the superior predictive performance of TabMmini.
- Open Access
- 6 March 2026
- Published by IOS Press
- p. 574-578
Research on Robustness of Lightweight SLAM Framework in Unknown Environment
In this paper, a lightweight event-triggered back-end optimization algorithm of distributed attitude relaxation architecture is proposed to solve the failure problem of cooperative SLAM in multi-robot systems due to lack of computing resources and extreme communication conditions. This paper simulates extreme network scenarios in space environment, uses a decentralized algorithm with low computing requirements in high packet loss rate, optimizes and verifies that map drawing can be corrected by using a single loop data packet in the environment, which reduces the error caused by sensor drift, and determines the robustness and accuracy of the algorithm in extreme environments.
- 6 March 2026
- Published by IOS Press
- p. 574-578
Open AccessResearch on Robustness of Lightweight SLAM Framework in Unknown Environment
In this paper, a lightweight event-triggered back-end optimization algorithm of distributed attitude relaxation architecture is proposed to solve the failure problem of cooperative SLAM in multi-robot systems due to lack of computing resources and extreme communication conditions. This paper simulates extreme network scenarios in space environment, uses a decentralized algorithm with low computing requirements in high packet loss rate, optimizes and verifies that map drawing can be corrected by using a single loop data packet in the environment, which reduces the error caused by sensor drift, and determines the robustness and accuracy of the algorithm in extreme environments.
- 18 January 2026
- Published by Springer Nature
- p. 67-79
Determination and Analysis of Possible Flight Schemes to Sedna in 2029–2037
- 18 January 2026
- Published by Springer Nature
- p. 67-79
Determination and Analysis of Possible Flight Schemes to Sedna in 2029–2037
- 1 October 2025
- Published by Pleiades Publishing Ltd in Cosmic Research
- Vol. 63 (5) , 448-459
Time-of-Flight Estimation in Low-Thrust Transfers between Asteroids Using Deep Neural Networks
This paper focuses on optimizing the transfer time for multiple asteroid rendezvous missions utilizing low-thrust propulsion. An indirect method based on Pontryagin’s maximum principle is employed to generate training data by optimizing low-thrust trajectories for minimal time of flight. A deep neural network (DNN) is subsequently trained to estimate the minimum time of flight (TOF) between each pair of asteroids. To enhance the accuracy of predictions for rapid transfers (less than 150 days), the dataset is augmented with additional trajectory simulations. Leveraging the trained neural network, a Beam Search (BS) algorithm is implemented to efficiently determine the fastest sequence of rendezvous with multiple asteroids, starting from an arbitrary initial asteroid. The results demonstrate that an optimal rendezvous sequence involving 15 asteroids is achieved, with an average time of flight of 107.5 days per segment.
- 1 October 2025
- Published by Pleiades Publishing Ltd in Cosmic Research
- Vol. 63 (5) , 448-459
Time-of-Flight Estimation in Low-Thrust Transfers between Asteroids Using Deep Neural Networks
This paper focuses on optimizing the transfer time for multiple asteroid rendezvous missions utilizing low-thrust propulsion. An indirect method based on Pontryagin’s maximum principle is employed to generate training data by optimizing low-thrust trajectories for minimal time of flight. A deep neural network (DNN) is subsequently trained to estimate the minimum time of flight (TOF) between each pair of asteroids. To enhance the accuracy of predictions for rapid transfers (less than 150 days), the dataset is augmented with additional trajectory simulations. Leveraging the trained neural network, a Beam Search (BS) algorithm is implemented to efficiently determine the fastest sequence of rendezvous with multiple asteroids, starting from an arbitrary initial asteroid. The results demonstrate that an optimal rendezvous sequence involving 15 asteroids is achieved, with an average time of flight of 107.5 days per segment.
- Open Access
- 17 March 2025
- Published by IOS Press
A Two-Step Trajectory Design Exploration Method Based on Tisserand Graph and Genetic Algorithm
Multiple gravity assists allow spacecraft to reach gas giants or even the outer regions of the solar system. The Tisserand graph method is an ingenious approach that simplifies the complex problem of interplanetary transfers—characterized by multiple gravity assist maneuvers (a mixed-integer nonlinear programming problem)—into a more straightforward combinatorial problem. The Tisserand Graph method allows for quick and intuitive generation of preliminary feasible transfer solutions. Genetic algorithms have long been an effective means of solving multiple gravity assist problems, but they often require an initial transfer solution. Therefore, this paper combines these two optimization methods to propose an interplanetary two-step trajectory design exploration method.
- 17 March 2025
- Published by IOS Press
Open AccessA Two-Step Trajectory Design Exploration Method Based on Tisserand Graph and Genetic Algorithm
Multiple gravity assists allow spacecraft to reach gas giants or even the outer regions of the solar system. The Tisserand graph method is an ingenious approach that simplifies the complex problem of interplanetary transfers—characterized by multiple gravity assist maneuvers (a mixed-integer nonlinear programming problem)—into a more straightforward combinatorial problem. The Tisserand Graph method allows for quick and intuitive generation of preliminary feasible transfer solutions. Genetic algorithms have long been an effective means of solving multiple gravity assist problems, but they often require an initial transfer solution. Therefore, this paper combines these two optimization methods to propose an interplanetary two-step trajectory design exploration method.
- Open Access
- 17 March 2025
- Published by IOS Press
Using Elite Ant Mechanism to Optimize Ant Colony Genetic Algorithm to Improve the Working Efficiency of Multi-Robot
Ant colony-genetic algorithm is a more mature multi-robot path planning algorithm, and this algorithm can be used to solve the optimal solution problem of path planning for multi-robot systems executing exploration on the surface of a planet. In this paper, we design a multi-robot system path planning scheme that introduces an elite ant mechanism to further optimize the optimal solution of multi-robot system path planning and improve the efficiency of the overall multi-robot system through the introduction of a mechanism that dynamically adjusts the path weights of the elite individuals. In this paper, the reliability and efficiency optimization of the multi-robot path planning using the elite ant mechanism to improve the ant colony-genetic algorithm is verified by simulating the handling task of a multi-robot system in a simulated Martian surface environment.
- 17 March 2025
- Published by IOS Press
Open AccessUsing Elite Ant Mechanism to Optimize Ant Colony Genetic Algorithm to Improve the Working Efficiency of Multi-Robot
Ant colony-genetic algorithm is a more mature multi-robot path planning algorithm, and this algorithm can be used to solve the optimal solution problem of path planning for multi-robot systems executing exploration on the surface of a planet. In this paper, we design a multi-robot system path planning scheme that introduces an elite ant mechanism to further optimize the optimal solution of multi-robot system path planning and improve the efficiency of the overall multi-robot system through the introduction of a mechanism that dynamically adjusts the path weights of the elite individuals. In this paper, the reliability and efficiency optimization of the multi-robot path planning using the elite ant mechanism to improve the ant colony-genetic algorithm is verified by simulating the handling task of a multi-robot system in a simulated Martian surface environment.