Rapid trajectory design in complex environments enabled by reinforcement learning and graph search strategies
A Das-Stuart, KC Howell, DC Folta - Acta Astronautica, 2020 - Elsevier
Designing trajectories in dynamically complex environments is challenging and easily
becomes intractable. Recasting the problem may reduce the design time and offer global …
becomes intractable. Recasting the problem may reduce the design time and offer global …
[PDF][PDF] A rapid trajectory design strategy for complex environments leveraging attainable regions and low-thrust capabilities
A Das-Stuart, KC Howell… - 68th International …, 2017 - engineering.purdue.edu
Designing trajectories in dynamically complex environments is challenging and easily
becomes intractable. Recasting the problem may reduce the design time and offer global …
becomes intractable. Recasting the problem may reduce the design time and offer global …
[PDF][PDF] Rapid trajectory design in complex environments enabled via supervised and reinforcement learning strategies
A Das-Stuart, KC Howell… - 69th International …, 2018 - engineering.purdue.edu
The investigation focuses on blending machine learning strategies with traditional trajectory
design techniques to uncover solutions and enhance human intuition. A free-form search …
design techniques to uncover solutions and enhance human intuition. A free-form search …
[PDF][PDF] Contingency planning in complex dynamical environments via heuristically accelerated reinforcement learning
A Das-Stuart, K Howell - AAS/AIAA Astrodynamics …, 2019 - engineering.purdue.edu
Unexpected events can cause a spacecraft to significantly deviate from its nominal path,
leading to undesirable impacts on the mission. In such scenarios, the capability for rapid …
leading to undesirable impacts on the mission. In such scenarios, the capability for rapid …
Artificial intelligence aided rapid trajectory design in complex dynamical environments
A Das - 2019 - search.proquest.com
Designing trajectories in dynamically complex environments is challenging and can easily
become intractable via solely manual design efforts. Thus, the problem is recast to blend …
become intractable via solely manual design efforts. Thus, the problem is recast to blend …