Skip to main content

PLEASE NOTE: We are currently experiencing issues with articles from the AIAA Journal not adding to our shopping cart (for transactional sales of individual articles only). This ONLY affects the AIAA Journal. All other journal titles should work as expected. We apologize for this inconvenience. Please contact [email protected] for help with any urgent article requests. Thank you.

No Access

Multi-Agent Motion Planning using Deep Learning for Space Applications

AIAA 2020-4233
Session: Mission Planning and Autonomy for Distributed Space Systems and Swarms
Published Online:

State-of-the-art motion planners cannot scale to a large number of systems. Motion planning for multiple agents is an NP (non-deterministic polynomial-time) hard problem, so the computation time increases exponentially with each addition of agents. This computational demand is a major stumbling block to the motion planner's application to future NASA missions involving the swarm of space vehicles. We applied a deep neural network to transform computationally demanding mathematical motion planning problems into deep learning-based numerical problems. We showed optimal motion trajectories can be accurately replicated using deep learning-based numerical models in several 2D and 3D systems with multiple agents. The deep learning-based numerical model demonstrates superior computational efficiency with plans generated 1000 times faster than the mathematical model counterpart.