Autonomy and machine intelligence in complex systems: A tutorial

Abstract

This tutorial paper will discuss the development of novel state-of-the-art control approaches and theory for complex systems based on machine intelligence in order to enable full autonomy. Given the presence of modeling uncertainties, the unavailability of the model, the possibility of cooperative/noncooperative goals and malicious attacks compromising the security of teams of complex systems, there is a need for approaches that respond to situations not programmed or anticipated in design. Unfortunately, existing schemes for complex systems do not take into account recent advances of machine intelligence. We shall discuss on how to be inspired by the human brain and combine interdisciplinary ideas from different fields, i.e. computational intelligence, game theory, control theory, and information theory to develop new self-configuring algorithms for decision and control given the unavailability of model, the presence of enemy components and the possibility of network attacks. Due to the adaptive nature of the algorithms, the complex systems will be capable of breaking or splitting into parts that are themselves autonomous and resilient. The algorithms discussed will be characterized by strong abilities of learning and adaptivity. As a result, the complex systems will be fully autonomous, and tolerant to communication failures.

Event-triggered optimal tracking control of nonlinear systems

“…One can also conclude that the tracking error e track is bounded for ¤ 0, which is the case when the desired trajectory does not go to zero because (16) with (17) becomes…”

Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation

“…where G : exists by Assumption 1. Note that we also need to estimate the matrix C q (see (1)) so that q j can be calculated from x j . While estimating the exact elements of these matrices is quite challenging, we can estimate the non-zero elements in the matrices, which is enough to design safe initial control policies, because the exact elements of C q will be subsumed within the Lipschitz constant.…”

Applying autonomy to distributed satellite systems: Trends, challenges, and future prospects

“…Vamvoudakis et al . also stated that full autonomy enables mission tailoring, control reconfigurability to allow for safe recovery, improved responsiveness and agility, and a general adaptability to changing environmental conditions . Nevertheless, autonomy in DSS goes beyond local management of failures and generation of plans of action and needs be rather seen as an enabler for the system qualities and function discussed in Section .…”

“…31, 33 autonomy is key to operate spacecraft under uncertainty and to cope with unexpected situations. Vamvoudakis et al 34 also stated that full autonomy enables mission tailoring, control reconfigurability to allow for safe recovery, improved responsiveness and agility, and a general adaptability to changing environmental conditions. 34 36 Furthermore, interactions between two nodes in a distributed satellite mission heavily depend upon their orbital parameters.…”

“…Vamvoudakis et al 34 also stated that full autonomy enables mission tailoring, control reconfigurability to allow for safe recovery, improved responsiveness and agility, and a general adaptability to changing environmental conditions. 34 36 Furthermore, interactions between two nodes in a distributed satellite mission heavily depend upon their orbital parameters. So much so that some task allocation approaches are even taking advantage of their intermittent and predictable communication processes.…”