| 1. |
- Bellini, Emanuele, et al.
(författare)
-
Resilience learning through self adaptation in digital twins of human-cyber-physical systems
- 2021
-
Ingår i: Proceedings of the 2021 IEEE International Conference on Cyber Security and Resilience (CSR). - : IEEE. - 9781665402859 - 9781665402866 ; , s. 168-173
-
Konferensbidrag (refereegranskat)abstract
- Human-Cyber-Physical-Systems (HPCS), such as critical infrastructures in modern society, are subject to several systemic threats due to their complex interconnections and interdependencies. Management of systemic threats requires a paradigm shift from static risk assessment to holistic resilience modeling and evaluation using intelligent, data-driven and run-time approaches. In fact, the complexity and criticality of HCPS requires timely decisions considering many parameters and implications, which in turn require the adoption of advanced monitoring frameworks and evaluation tools. In order to tackle such challenge, we introduce those new paradigms in a framework named RESILTRON, envisioning Digital Twins (DT) to support decision making and improve resilience in HCPS under systemic stress. In order to represent possibly complex and heterogeneous HCPS, together with their environment and stressors, we leverage on multi-simulation approaches, combining multiple formalisms, data-driven approaches and Artificial Intelligence (AI) modelling paradigms, through a structured, modular and compositional framework. DT are used to provide an adaptive abstract representation of the system in terms of multi-layered spatially-embedded dynamic networks, and to apply self-adaptation to time-warped What-If analyses, in order to find the best sequence of decisions to ensure resilience under uncertainty and continuous HPCS evolution.
|
|
| 2. |
- Da Lio, Mauro, et al.
(författare)
-
A Mental Simulation Approach for Learning Neural-Network Predictive Control (in Self-Driving Cars)
- 2020
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 8, s. 192041-192064
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a novel approach to learning predictive motor control via mental simulations. The method, inspired by learning via mental imagery in natural Cognition, develops in two phases: first, the learning of predictive models based on data recorded in the interaction with the environment; then, at a deferred time, the synthesis of inverse models via offline episodic simulations. Parallelism with human-engineered control-theoretic workflow (mathematical modeling the direct dynamics followed by optimal control inversion) is established. Compared to the latter human-directed synthesis, the mental simulation approach increases autonomy: a robotic agent can learn predictive models and synthesize inverse ones with a large degree of independence. Human modeling is still needed but limited to providing efficient templates for the forward and inverse neural networks and a few other directives. One could consider these templates as the efficient brain network typologies that evolution produced to permit live beings quickly and efficiently learning. The structure of the neural networks both forward and inverse ones; is made of interpretable local models which follows the cerebellar organization (and are also similar to local model approaches known in the literature). We demonstrate the learning of a first-round model (contrasted to Model Predictive Control) for lateral vehicle dynamics. Then, we demonstrate a second learning iteration, where the forward/inverse neural models are significantly improved.
|
|
