On-board planning for New Millennium Deep Space One autonomy

Abstract

The Deep Space One (DS1) mission, scheduled to fly in 1998, will be the first NASA spacecraft to feature an on-board planner. The planner is part of an artificial intelligence based control architecture that comprises the planner/scheduler, a plan execution engine, and a model-based fault diagnosis and reconfiguration engine. This autonomy architecture reduces mission costs and increases mission quality by enabling high-level commanding, robust fault responses, and opportunistic responses to serendipitous events. This paper describes the on-board planning and scheduling component of the DS1 autonomy architecture.

The SOPHY framework: simulation, observation and planning in hybrid systems

“…The "Hybrid Mode Reconfiguration" engine is responsible for goal oriented coordination and control of the HEs. A system similar to the Planner/Scheduler (PS) of the Deep Space 1 project (DS1) [6] is envisioned to fulfill this role. Finally the "Hyper-Mode Identification" and "Hyper-Hybrid Abstraction Layer" are included in the framework as a mean to facilitate yet another level of Composers if the grouping of Composers is desirable in very complex systems.…”

Robotics in the service of astronomy

“…This type of problem is recurrent in robotic planning which involves the scheduling of robotic actions, resolution of conflicts and re‐planning on the fly when planning goals are not met. Indeed, the automated navigation software Remote Agent onboard Deep Space 1 has successfully demonstrated this type of automated scheduling and rescheduling process on a space exploration mission (Muscettola et al 1997). APA uses “just‐in‐case” scheduling to minimize the advent of errors and conflicts by generating robust, contingent schedules similar in spirit to the “just‐in‐time” scheduling in modern manufacturing plants.…”

Onboard autonomous mission re-planning for multi-satellite system

“…In the mission Deep Space 1 (DS-1) [1], the Remote Agent (RA), a remote intelligent self-repair software had been developed by Jet Propulsion Laboratory (JPL). The RA consists of three components: the Planner/Scheduler (PS), the Executive (EXEC), and a model-based Mode Identification and Recover engine (MIR) [2]. The Earth Observation One (EO-1) mission experimentally applied an autonomous system to data recognition of observed images.…”