Research/ ORBITAL ROBOTICS

CIKAN: Constraint Informed Kolmogorov-Arnold Networks for Autonomous Spacecraft Rendezvous using Time Shift Governor

Taehyeun Kim, Anouck Girard, Ilya Kolmanovsky

Conference on Learning for Dynamics & Control 2024/Dec 4, 2024/ 3 citations

Technique

Guidance, Dynamics & ControlarXiv: eess.SY · Rendezvous, Proximity Ops & DockingOpenAlex keyword: spacecraft rendezvous · Learning-based MethodsarXiv: cs.LG

Indexed as

arXiveess.SY · cs.AI · cs.LG · cs.SYOpenAlexSpacecraft Dynamics and Control · Space Satellite Systems and Control · Guidance and Control Systems

HTML PDF arXiv:2412.03710 Publisher Semantic Scholar OpenAlex

The paper considers a Constrained-Informed Neural Network (CINN) approximation for the Time Shift Governor (TSG), which is an add-on scheme to the nominal closed-loop system used to enforce constraints by time-shifting the reference trajectory in spacecraft rendezvous applications. We incorporate Kolmogorov-Arnold Networks (KANs), an emerging architecture in the AI community, as a fundamental component of CINN and propose a Constrained-Informed Kolmogorov-Arnold Network (CIKAN)-based approximation for TSG. We demonstrate the effectiveness of the CIKAN-based TSG through simulations of constrained spacecraft rendezvous missions on highly elliptic orbits and present comparisons between CIKANs, MLP-based CINNs, and the conventional TSG.

Comments: 10 pages, 4 figures

Latest in ORBITAL ROBOTICS

See all →

Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment

Tristan Leuridan, Yiping Fang, Adam Abdin3rd Conference on AI in and for Space (SPAICE 2026), European Space Agency (ESA), Oct 2026, Noordwijk, NetherlandsNov 2, 2026

Space × AIORBITAL ROBOTICS Guidance, Dynamics & Control Learning-based Methods

PDF HTML arXiv

Nov 2, 2026

An intelligent satellite must do nothing well

Fabrizio Pilone, Giordana BucchioniPreprint 2026Nov 2, 2026

Space × AIORBITAL ROBOTICS

PDF HTML arXiv

Nov 2, 2026

Clockwork: Scheduling Compound AI Systems in Space Data Centers

Milos Gravara, Andrija Stanisic, Stefan NasticPreprint 2026Oct 31, 2026

Space × AIORBITAL ROBOTICS Autonomy, Task Planning & Operations

PDF HTML arXiv

Oct 31, 2026

STLT: A Novel System for Energy-Aware Distributed Inference in the Edge-Cloud-Space Continuum

Andrija Stanisic, Milos Gravara, Juan Luis Herrera, Stefan NasticPublished 2026Oct 31, 2026

Space × AIORBITAL ROBOTICS

PDF HTML arXiv

Oct 31, 2026

CIKAN: Constraint Informed Kolmogorov-Arnold Networks for Autonomous Spacecraft Rendezvous using Time Shift Governor

Related papers

Constrained Control for Autonomous Spacecraft Rendezvous: Learning-Based Time Shift Governor

A nearly optimal control for spacecraft rendezvous with constrained controls

Transformers for Trajectory Optimization with Application to Spacecraft Rendezvous

Model-Based Reinforcement Learning and Neural-Network-Based Policy Compression for Spacecraft Rendezvous on Resource-Constrained Embedded Systems

Spacecraft Autonomous Rendezvous Control With Rotation Target on SE(3): Deep Reinforcement Learning Methods

Machine Learning Techniques for Autonomous Spacecraft Guidance during Proximity Operations

Neural representation of a time optimal, constant acceleration rendezvous

Learning-Based Stable Optimal Guidance for Spacecraft Close-Proximity Operations

Real-Time Guidance for Low-Thrust Transfers Using Deep Neural Networks

Deep Learning Techniques for Autonomous Spacecraft Guidance During Proximity Operations

Latest in ORBITAL ROBOTICS

Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment

An intelligent satellite must do nothing well

Clockwork: Scheduling Compound AI Systems in Space Data Centers

STLT: A Novel System for Energy-Aware Distributed Inference in the Edge-Cloud-Space Continuum

CIKAN: Constraint Informed Kolmogorov-Arnold Networks for Autonomous Spacecraft Rendezvous using Time Shift Governor

Related papers

Constrained Control for Autonomous Spacecraft Rendezvous: Learning-Based Time Shift Governor

A nearly optimal control for spacecraft rendezvous with constrained controls

Transformers for Trajectory Optimization with Application to Spacecraft Rendezvous

Model-Based Reinforcement Learning and Neural-Network-Based Policy Compression for Spacecraft Rendezvous on Resource-Constrained Embedded Systems

Spacecraft Autonomous Rendezvous Control With Rotation Target on SE(3): Deep Reinforcement Learning Methods

Machine Learning Techniques for Autonomous Spacecraft Guidance during Proximity Operations

Neural representation of a time optimal, constant acceleration rendezvous

Learning-Based Stable Optimal Guidance for Spacecraft Close-Proximity Operations

Real-Time Guidance for Low-Thrust Transfers Using Deep Neural Networks

Deep Learning Techniques for Autonomous Spacecraft Guidance During Proximity Operations

Latest in ORBITAL ROBOTICS

Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment

An intelligent satellite must do nothing well

Clockwork: Scheduling Compound AI Systems in Space Data Centers

STLT: A Novel System for Energy-Aware Distributed Inference in the Edge-Cloud-Space Continuum