On-board autonomy, EURECA experience and requirements for future space missions

The paper describes, after a basic definition of on-board autonomy, the on-board autonomous mission control capabilities used during the EURECA mission for nominal operations and fault management and related experiences. It also covers autonomy enhancements required for future highly productive missions. These are functionalities in relation to on-board mission planning, use of intelligent sub-system elements, “off-line” test capabilities and adaptive fault management.

EURECA, an unmanned retrievable multi-disciplinary science laboratory has successfully flown an 11-month mission in a 500 km, 28 deg. inclination orbit in the period August 1992 to June 1993. It was launched and brought back to earth by Space Shuttle flights STS46 and STS57 respectively. The complex spacecraft was operated by ESOC, in continuous productive mode, with less than 6% ground on-line contact, in a highly on-board autonomous mode. Its mission products encompassed all types of continuously produced scientific data, processed materials and biological samples, and a significant number of technological demonstrations.     

Increasing autonomy of UAVs

Unmanned aerial vehicles (UAVs) are acquiring an increased level of autonomy as more complexmission scenarios are envisioned [1]. For example, UAVs are being used for intelligence, surveillance, and reconnaissance missions as well as to assist humans in the detection and localization of wildfires [2], tracking of moving vehicles along roads [3], [4], and performing border patrol missions [5]. A critical component for networks of autonomous vehicles is the ability to detect and localize targets of interest in a dynamic and unknown environment. The success of these missions hinges on the ability of the algorithms to appropriately handle the uncertainty in the information of the dynamic environment and the ability to cope with the potentially large amounts of communicated data that will need to be broadcast to synchronize information across networks of vehicles. Because of their relative simplicity, centralized mission management algorithms have previously been developed to create a conflict-free task assignment (TA) across all vehicles. However, these algorithms are often slow to react to changes in the fleet and environment and require high bandwidth communication to ensure a consistent situational awareness (SA) from distributed sensors and also to transmit detailed plans back to those sensors.     

Computer Vision on Mars

Increasing the level of spacecraft autonomy is essential for broadening the reach of solar system exploration. Computer vision has and will continue to play an important role in increasing autonomy of both spacecraft and Earth-based robotic vehicles. This article addresses progress on computer vision for planetary rovers and landers and has four main parts. First, we review major milestones in the development of computer vision for robotic vehicles over the last four decades. Since research on applications for Earth and space has often been closely intertwined, the review includes elements of both. Second, we summarize the design and performance of computer vision algorithms used on Mars in the NASA/JPL Mars Exploration Rover (MER) mission, which was a major step forward in the use of computer vision in space. These algorithms did stereo vision and visual odometry for rover navigation and feature tracking for horizontal velocity estimation for the landers. Third, we summarize ongoing research to improve vision systems for planetary rovers, which includes various aspects of noise reduction, FPGA implementation, and vision-based slip perception. Finally, we briefly survey other opportunities for computer vision to impact rovers, landers, and orbiters in future solar system exploration missions.     

ATOS — An AI-based space mission operations system

Artificial Intelligence is generally recognised as one of the key technologies for future spaceflight, and a number of ambitious applications for on-board use have been proposed already. Such applications still require a good deal of basic research and development, but on-ground applications could make an impact already in the medium term, and will for some time represent the major part of AI use for space missions.

ESA has started the development of a future integrated and mission-independent spacecraft control data processing system called the Advanced Technology Operations System (ATOS) at the European Space Operations Centre, which will employ artificial intelligence techniques in supporting the operations staff during all mission preparation and implementation phases, in order to cope reliably with complex mission operations and to achieve optimal efficiency in the use of human resources.

ATOS will consist of a number of knowledge based software modules, such as

• Automated mission planning

• Automated operations preparation

• Computer assisted operations

• Advanced operator training,

centred around a Mission Information Base configured for the particular satellite mission, the common data repository for all information required to conduct the mission and operate the spacecraft.

The Mission Information Base will, in addition to numerical data presently found in conventional spacecraft control systems, contain a large amount of ‘knowledge’ about the spacecraft and its mission, which is currently available only in paper documents or embedded in software. It will be implemented as a physically and logically distributed set of databases each representing a particular field of mission information, such that the knowledge can be dynamically shared between different intelligent spacecraft control applications.     

Experiences applying formal approaches in the development of swarm-based space exploration systems

NASA is researching advanced technologies for future exploration missions using intelligent swarms of robotic vehicles. One of these missions is the Autonomous Nano-Technology Swarm (ANTS) mission that will explore the asteroid belt using 1,000 cooperative autonomous spacecraft. The emergent properties of intelligent swarms make it a potentially powerful concept, but at the same time more difficult to design and ensure that the proper behaviors will emerge. NASA is investigating formal methods and techniques for verification of such missions. The advantage of using formal methods is the ability to mathematically verify the behavior of a swarm, emergent or otherwise. Using the ANTS mission as a case study, we have evaluated multiple formal methods to determine their effectiveness in modeling and ensuring desired swarm behavior. This paper discusses the results of this evaluation and proposes an integrated formal method for ensuring correct behavior of future NASA intelligent swarms.     

Multiagent robotics: toward energy autonomy

In this paper, we propose a novel trend in multiagent robotics: energy autonomy. A definition of energy autonomy is developed from an original concept, “potential energy,” that is under the constraints of remaining energy capacity and the relative distance among robotic agents. Toward energy autonomy, we initially present a simulation of a multiagent robotic system in which each robot is capable of exchanging energy cells with other robots. Our simulation points out that: (1) each robot is able not only to act as an autonomous agent, but also to interact with others to be beyond the individual capabilities; (2) in order to adapt to changes in the environment, each robot is situated as an adaptive agent in a network of neighboring robots, which leads to a state of energy autonomy. Finally, based on the results of the simulation, we adjust the rules for our real multirobot system. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007     

Estimation of model quality

This paper provides an introduction to recent work on the problem of quantifying errors in the estimation of models for dynamic systems. This is a very large field. We therefore concentrate on approaches that have been motivated by the need for reliable models for control system design. This will involve a discussion of efforts that go under the titles of ‘estimation in ’, ‘worst-case estimation’, ‘estimation in ℓ₁’ and ‘stochastic embedding of undermodelling’. A central theme of this survey is to examine these new methods with reference to the classic bias/variance tradeoff in model structure selection.     

Toward combining autonomy and interactivity for social robots

The success of social robots in achieving natural coexistence with humans depends on both their level of autonomy and their interactive abilities. Although a lot of robotic architectures have been suggested and many researchers have focused on human–robot interaction, a robotic architecture that can effectively combine interactivity and autonomy is still unavailable. This paper contributes to the research efforts toward this architecture in the following ways. First a theoretical analysis is provided that leads to the notion of co-evolution between the agent and its environment and with other agents as the condition needed to combine both autonomy and interactivity. The analysis also shows that the basic competencies needed to achieve the required level of autonomy and the envisioned level of interactivity are similar but not the same. Secondly nine specific requirements are then formalized that should be achieved by the architecture. Thirdly a robotic architecture that tries to achieve those requirements by utilizing two main theoretical hypothesis and several insights from social science, developmental psychology and neuroscience is detailed. Lastly two experiments with a humanoid robot and a simulated agent are reported to show the potential of the proposed architecture.     

On-board preventive maintenance: a design-oriented analytic study for long-life applications

With respect to the long-life missions associated with NASA’s X2000 Advanced Deep-Space System Development Program, reliability implies a system’s continuous operation for many years in an unsurveyed radiation-intense environment. Further, the stringent constraints on the mass of a spacecraft and the power on-board create unprecedented challenges on the means for achieving the ultra-high mission reliability. In this paper, we present an approach to on-board preventive maintenance which rejuvenates a system by letting system components rotate between on-duty and off-duty shifts, slowing down a system’s aging process and thus enhancing mission reliability. By exploiting nondedicated system redundancy, hardware and software rejuvenation are realized simultaneously without significant performance penalty. Our design-oriented analysis confirms a potential for significant gains in mission reliability from on-board preventive maintenance and provides to us useful insights about the collective effect of age-dependent failure behavior, residual mission life, risk of unsuccessful maintenance and maintenance frequency on mission reliability.     

Efference copies in neural control of dynamic biped walking

In the early 1950s, von Holst and Mittelstaedt proposed that motor commands copied within the central nervous system (efference copy) help to distinguish ‘reafference’ activity (afference activity due to self-generated motion) from ‘exafference’ activity (afference activity due to external stimulus). In addition, an efference copy can be also used to compare it with the actual sensory feedback in order to suppress self-generated sensations. Based on these biological findings, we conduct here two experimental studies on our biped “RunBot” where such principles together with neural forward models are applied to RunBot’s dynamic locomotion control. The main purpose of this article is to present the modular design of RunBot’s control architecture and discuss how the inherent dynamic properties of the different modules lead to the required signal processing. We believe that the experimental studies pursued here will sharpen our understanding of how the efference copies influence dynamic locomotion control to the benefit of modern neural control strategies in robots.     

Real-time supply chain control via multi-agent adjustable autonomy

Real-time supply chain management in a rapidly changing environment requires reactive and dynamic collaboration among participating entities. In this work, we model supply chain as a multi-agent system where agents are subject to an adjustable autonomy. The autonomy of an agent refers to its capability to make and influence decisions within a multi-agent system. Adjustable autonomy means changing the autonomy of the agents during runtime as a response to changes in the environment. In the context of a supply chain, different entities will have different autonomy levels and objective functions as the environment changes, and the goal is to design a real-time control technique to maintain global consistency and optimality. We propose a centralized fuzzy framework for sensing and translating environmental changes to the changes in autonomy levels and objectives of the agents. In response to the changes, a coalition-formation algorithm will be executed to allow agents to negotiate and re-establish global consistency and optimality. We apply our proposed framework to two supply chain control problems with drastic changes in the environment: one in controlling a military hazardous material storage facility under peace-to-war transition, and the other in supply management during a crisis (such as bird-flu or terrorist attacks). Experimental results show that by adjusting autonomy in response to environmental changes, the behavior of the supply chain system can be controlled accordingly.     

A System for Building Intelligent Agents that Learn to Retrieve and Extract Information

We present a system for rapidly and easily building instructable and self-adaptive software agents that retrieve and extract information. Our Wisconsin Adaptive Web Assistant (WAWA) constructs intelligent agents by accepting user preferences in the form of instructions. These user-provided instructions are compiled into neural networks that are responsible for the adaptive capabilities of an intelligent agent. The agent’s neural networks are modified via user-provided and system-constructed training examples. Users can create training examples by rating Web pages (or documents), but more importantly WAWA’s agents uses techniques from reinforcement learning to internally create their own examples. Users can also provide additional instruction throughout the life of an agent. Our experimental evaluations on a ‘home-page finder’ agent and a ‘seminar-announcement extractor’ agent illustrate the value of using instructable and adaptive agents for retrieving and extracting information.     

Consumer decision support systems: Internet versus in-store application

This paper reports a study of consumer decision support in the context of Internet and in-store applications. A sample (n = 30) of experienced runners made running shoe selections in either ‘product only’, ‘decision support system only’, or ‘decision support system and product’ conditions. Participants’ decisions tended to be more uniform and of better quality when the DSS was available. Decision making was clearly influenced by DSS recommendations, but these were not always accepted. In this latter circumstance participants reported themselves to be relatively less happy with and less confident in their decision. Consistent with previous literature, abstract attributes were considered more frequently and given higher weightings when using the decision support system. However, predicted differences between conditions with respect to the types of attributes considered and the importance ascribed to different types of attributes were not found.     

Integrated Premission Planning and Execution for Unmanned Ground Vehicles

Fielding robots in complex applications can stress the human operators responsible for supervising them, particularly because the operators might understand the applications but not the details of the robots. Our answer to this problem has been to insert agent technology between the operator and the robotic platforms. In this paper, we motivate the challenges in defining, developing, and deploying the agent technology that provides the glue in the application of tasking unmanned ground vehicles in a military setting. We describe how a particular suite of architectural components serves equally well to support the interactions between the operator, planning agents, and robotic agents, and how our approach allows autonomy during planning and execution of a mission to be allocated among the human and artificial agents. Our implementation and demonstrations (in real robots and simulations) of our multi-agent system shows significant promise for the integration of unmanned vehicles in military applications.     

Model-based autonomy in deep space missions

The article discusses trade-offs involved in current-generation autonomy systems for deep-space applications and describes emerging research that will let future spacecraft operate unattended for significant periods of time, synthesizing control decisions in response to both planned and unplanned events.     

Fault‐tolerant on‐board computing for robotic space missions

This paper describes an approach to providing software fault tolerance for future deep‐space robotic National Aeronautics and Space Administration missions, which will require a high degree of autonomy supported by an enhanced on‐board computational capability. We focus on introspection‐based adaptive fault tolerance guided by the specific requirements of applications. Introspection supports monitoring of the program execution with the goal of identifying, locating, and analyzing errors. Fault tolerance assertions for the introspection system can be provided by the user, domain‐specific knowledge, or via the results of static or dynamic program analysis. This work is part of an on‐going project at the Jet Propulsion Laboratory in Pasadena, California. Copyright © 2011 John Wiley & Sons, Ltd.     

An Autonomous Spacecraft Agent Prototype

This paper describes the New Millennium Remote Agent (NMRA) architecture for autonomous spacecraft control systems. The architecture supports challenging requirements of the autonomous spacecraft domain not usually addressed in mobile robot architectures, including highly reliable autonomous operations over extended time periods in the presence of tight resource constraints, hard deadlines, limited observability, and concurrent activity. A hybrid architecture, NMRA integrates traditional real-time monitoring and control with heterogeneous components for constraint-based planning and scheduling, robust multi-threaded execution, and model-based diagnosis and reconfiguration. Novel features of this integrated architecture include support for robust closed-loop generation and execution of concurrent temporal plans and a hybrid procedural/deductive executive.We implemented a prototype autonomous spacecraft agent within the architecture and successfully demonstrated the prototype in the context of a challenging autonomous mission scenario on a simulated spacecraft. As a result of this success, the integrated architecture has been selected to fly as an autonomy experiment on Deep Space One (DS-1), the first flight of NASA';s New Millennium Program (NMP), which will launch in 1998. It will be the first AI system to autonomously control an actual spacecraft.     

Capturing autonomy features for unmanned spacecraft with ARE,the autonomy requirements engineering approach

Along with the traditional requirements, requirements engineering for autonomous and self-adaptive systems needs to address requirements related to adaptation issues, in particular: (1) what adaptations are possible; (2) under what constrains; and (3) how those adaptations are realized. Note that adaptations arise when a system needs to cope with changes to ensure realization of the system’s objectives. The autonomy requirements engineering approach converts adaptation issues into autonomy features where goal-oriented requirements engineering is used along with a model for generic autonomy requirements. The approach is intended to help engineers develop missions for unmanned exploration, often with limited or no human control.     

A New Concept for the On-line Storage of Sample Plates, Integrated with Plate Preparation for High-Throughput Screening and ‘Cherry-Picking’

Recently Organon installed automated screening and plate preparation systems for its research facilities in Oss (The Netherlands) and Newhouse (UK). These robotic systems have been developed in close collaboration between Organon and Scitec Laboratory Automation (Lausanne, Switzerland), now part of the Zymark corporation.Each of the systems consists of three linear track robots, one of which performs the screening process using standard peripherals. The other two robots take care of the plate preparation and ‘cherry-picking’ procedures. To this end, copies of our total mother plate collection are stored under controlled conditions in Scitec plate stackers (AutoStack) that can be addressed by one of the two robots. The system is designed in such a way that the loading and refreshment of the on-line storage, screening-plate preparation, and ‘cherry-picking’ can be executed automatically in 24 hours operation.     

Model-driven design space exploration for multi-robot systems in simulation

Multi-robot systems are increasingly deployed to provide services and accomplish missions whose complexity or cost is too high for a single robot to achieve on its own. Although multi-robot systems offer increased reliability via redundancy and enable the execution of more challenging missions, engineering these systems is very complex. This complexity affects not only the architecture modelling of the robotic team but also the modelling and analysis of the collaborative intelligence enabling the team to complete its mission. Existing approaches for the development of multi-robot applications do not provide a systematic mechanism for capturing these aspects and assessing the robustness of multi-robot systems. We address this gap by introducing ATLAS, a novel model-driven approach supporting the systematic design space exploration and robustness analysis of multi-robot systems in simulation. The ATLAS domain-specific language enables modelling the architecture of the robotic team and its mission and facilitates the specification of the team’s intelligence. We evaluate ATLAS and demonstrate its effectiveness in three simulated case studies: a healthcare Turtlebot-based mission and two unmanned underwater vehicle missions developed using the Gazebo/ROS and MOOS-IvP robotic platforms, respectively.