Multi-agent system for formation flying missions

Abstract

Currently, spacecraft are not operated as autonomous coordinated teams. Generalized reasoning capability offered by advanced distributed s o h a r e technology and AI have the potential to cope with unexpected events and uncertainty and allow to close the loop of perception, decision and eventually deliberation, D n board. The team members play different interchangeable roles and they negotiate the task that they ue achieving together. We present a multi-agent system :o provide a high degree of autonomy and support for :oordination among team members. We use JPL Formation flying mission initial architectures as ienchmark.Our target is to avoid nconsistencies/disagreements between two or more iarticipants in a collaborative context, increase the iystem's fault tolerance in cases such as loss of a member while the system should be able to still reliably operate. We address the cooperation between independent tutonomous agents when they have to collaborate to ichieve a common goal. In a top-down organization, gents are coordinated in a hierarchical fashion, where the gents at the top of the hierarchy make the majority of the ntelligent group decisions. In a more structured, but still iierarchical organization, lower-level agents exercise nore intelligence in making group decisions. A lowereve1 agent can advance a plan for the others to follow, md then a higher rank agent will decide on the best plans iroduced by individual agents. Although more rigid, the entralized intelligence organization allows for less ommunication among agents, so is more straightforward D implement. The decentralized approach requires more ommunication, but the intelligence is truly distributed, which makes for a more flexible, adaptive and efficient organization.

Autonomous navigation of formation flying spacecrafts in deep space exploration and communication by hybrid navigation utilizing neural network filter

“…Large quantity of relative works and projects focus on FFS are under way by various organizations and universities [7][8][9]. For example, earth-centered FFS of Gemini and Techsat21 missions locate on low earth orbit for observing and detecting the earth [10], and projects of space-FFS replacing signal large spacecraft for interferometry and surveillance certain celestial bodies may be positioned on halo orbit or Lagrange points in restricted three bodies systems as XEUS and Darwin missions.…”

Virtual Spring-Based 3D Multi-Agent Group Coordination

“…A multi-agent System for formation flying missions is proposed in [19] and for collaborative sensing, multiple Unmanned Aerial Vehicles (UAVs) are considered in [18].Methods for optimizing the task allocation problem for a fleet of UAVs with tightly coupled tasks and rigid relative timing constraints are described in [2]. Minimization of the mission completion time for the fleet is the overall objective in this work that uses timing constraints and loitering.…”