KnowGo: An Adaptive Learning-Based Multi-model Framework for Dynamic Automotive Risk Assessment

Abstract

In autonomous driving systems, the level of monitoring and control expected from the vehicle and the driver change in accordance with the level of automation, creating a dynamic risk environment where risks change according to the level of automation. Moreover, the input data and their essential features for a given risk model can also be inconsistent, heterogeneous, and volatile. Therefore, risk assessment systems must adapt to changes in the automation level and input data content to ensure that both the risk criteria and weighting reflect the actual system state, which can change at any time. This paper introduces KnowGo, a learning-based dynamic risk assessment framework that provides a risk prediction architecture that can be dynamically reconfigured in terms of risk criterion, risk model selection, and weighting in response to dynamic changes in the operational environment. We validated the KnowGo framework with five types of risk scoring models implemented using data-driven and rule-based methods.

Evaluation Framework for Autonomous Systems: The Case of Programmable Electronic Medical Systems

“…Eventually, only a few papers (i.e., [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43]) fulfilled the criteria and were evaluated. Hartsell et al [34] present ReSonAte, a dynamic risk estimation and assessment framework for autonomous systems.…”

“…The proposed framework exploits multiple risk profiles to support users in better understanding risks and appropriately adapting to various situations. Mundt et al [42] also refer to autonomous driving systems. The authors present KnowGo, a dynamic risk assessment framework.…”

“…It makes use of a risk prediction architecture enabling dynamic reconfiguration in terms of risk criterion, risk model selection, and level of automation, to manage dynamic changes in the operational environment. The frameworks proposed in [34], [35], [42] clearly show that, due to its criticality, risk estimation and assessment require dynamic runtime techniques, thus capturing the failures that systems face at runtime. To this aim, they are specifically intended for evaluating systems during their operation and under the lens of one or a few critical properties, such as the risk of failures.…”