A Goal-oriented Autonomous Controller for Space Exploration

Advances in Control System Technology for Aerospace Applications, 2015

In early 2011, NASA's Office of the Chief Technologist released a set of technology roadmaps with the aim of fostering the development of concepts and cross-cutting technologies addressing NASA's needs for the 2011-2021 decade and beyond. NASA reached out to the National Research Council (NRC) to review the program objectives and prioritize their list of technologies. In January 2012, the NRC released its report entitled "Restoring NASA's Technological Edge and Paving the Way for a New Era in Space." While the NRC report provides a systematic and thorough ranking of the future technology needs for NASA, it does not discuss in detail the technical aspects of the prioritized technologies (that is clearly beyond the scope of the report). This chapter, building upon the NRC report, aims at providing technical details for a selected number of high-priority technologies in the autonomous systems area. Specifically, this chapter focuses on technology area TA04 "Robotics, Tele-Robotics, and Autonomous Systems" and discusses in some detail the technical aspects and challenges associated with three high-priority TA04 technologies: "Relative Guidance Algorithms", "Extreme Terrain Mobility", and "Small Body/Microgravity Mobility." Each of these technologies is discussed along four main dimensions: scope, need, state of the art, and challenges and future directions. The result is a unified explanation of key autonomy challenges for next generation space missions.

This paper focuses on the ESA APSI software platform for developing planning and scheduling applications for space missions. In particular, it describes work performed by CNR-ISTC developing new APSI-compliant features that address aspects considered as "improvable" in the current APSI distribution. The APSI version used within the GOAC project has been considered as the starting state for the new work. In particular, two aspects are described: (a) two new planning systems able to integrate causal and resource reasoning (called EPSL and J-TRE); (b) the KEEN knowledge engineering environment that allows an integrated use of various research facilities we have developed over time. Some examples are shown taken from the GOAC space robotics domain.

2014

During the most recent period of performance, the team has refined the major implemented functions of our MIDCA architecture at the cognitive level (Cox, 2013; Paisner, Cox, Maynord, & Perlis, 2014) and has started work on an analogous metacognitive cycle at the meta-level (Dannenhauer, Cox, Gupta, Paisner & Perlis, 2014; Perlis & Cox, 2014). We produced substantial progress on the knowledge-rich track of the Note-Assess-Guide interpretation procedure. Additionally we started an integration of MIDCA and the T-REX planning and scheduling system. This work explores the use of meta-level control for vehicle planning and behavior execution in dynamic environments. The initial data are encouraging and the path forward is favorable.

Upcoming missions will require a higher degree of remote operations to increase quality and quantity of science return. Remote operations are certainly a challenging scenario, mainly because communication delays and errors lead to objective difficulties for the operator to promptly enable opportunistic science, activate contingency recovery procedures or to anticipate and react to tracked events. AI planning-based control layers have demonstrated to be able to entail autonomy, but modeling still constitute a bottleneck for the use of these technologies. In this paper we discuss how to design a controller based on the ESA GOAC platform to robustify the line operator -communication layer -remote system in the context of remote operations, with particular attention on discussing a general methodology to design efficient models for the AI planning engine. The approach presented has been tested on a real system made of a communication network, to simulate the communication issues, and a rover, as controlled device. The communication system and rover used are part of the ESA METERON infrastructure (Multi-Purpose End-To-End Robotic Operations Network).

2002

A novel approach to the design of reactive embedded software systems, called model-based autonomy, is generating significant interest in the space systems community. The goal of the model-based approach is to automate onboard sequence execution by tightly integrating goal-driven commanding with fault detection, diagnosis, and recovery capabilities. This paper describes Titan, a system-level autonomy framework that expands upon previous model-based approaches to configuration management, such as the Livingstone mode identification and reconfiguration system, which was demonstrated on the Deep Space One spacecraft. Titan is a model-based executive that estimates current spacecraft modes, detects and repairs failures, and executes commands, all within a fast sense-decide-act loop. This paper discusses the model-based software technologies implemented within the Titan executive. It describes a case study of the deployment of Titan to a representative space mission, including an overview...

Current Robotics Reports, 2021

Purpose of Review The purpose of this review is to highlight space autonomy advances across mission phases, capture the anticipated need for autonomy and associated rationale, assess state of the practice, and share thoughts for future advancements that could lead to a new frontier in space exploration. Recent Findings Over the past two decades, several autonomous functions and system-level capabilities have been demonstrated and used in spacecraft operations. In spite of that, spacecraft today remain largely reliant on ground in the loop to assess situations and plan next actions, using pre-scripted command sequences. Advances have been made across mission phases including spacecraft navigation; proximity operations; entry, descent, and landing; surface mobility and manipulation; and data handling. But past successful practices may not be sustainable for future exploration. The ability of ground operators to predict the outcome of their plans seriously diminishes when platforms phy...

1997 IEEE Aerospace Conference, 1997

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 highlevel 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.

2002

The New Millennium Remote Agent (NMRA) vSll be the first AI system to control an actual spacecraft. The spacecraft domain raises a number of challenges for planning and execution, ranging from extended agency and long-term planning to dynamic recoveries and robust concurrent execution, all in the presence of tight real-time deadlines, changing goals, scarce resource constraints, and a v-ide variety of possible failures. We believe NMRA is the first system to integrate closed-loop planning and e.xecution of concurrent temporal plans, and the first autonomous system that v-ill be able to achieve a sustained multi-stage multiyear mission v-ithout communication or guidance from earth.

1999

On May 17th 1999, NASA activated for the first time an AI-based planner/scheduler running on the flight processor of a spacecraft. This was part of the Remote Agent Experiment (RAX), a demonstration of closedloop planning and execution, and model-based state inference and failure recovery. This paper describes the RAX Planner/Scheduler (RAX-PS), both in terms of the underlying planning framework and in terms of the fielded planner. RAX-PS plans are networks of constraints, built incrementally by consulting a model of the dynamics of the spacecraft. The RAX-PS planning procedure is formally well defined and can be proved to be complete. RAX-PS generates plans that are temporally flexible, allowing the execution system to adjust to actual plan execution conditions without breaking the plan. The practical aspect, developing a mission critical application, required paying attention to important engineering issues such as the design of methods for programmable search control, knowledge acquisition and planner validation. The result was a system capable of building concurrent plans with over a hundred tasks within the performance requirements of operational, mission-critical software.