Risk Estimation in Robotics and the Impact of Human Behaviour

Abstract

Within this chapter the emerging topic of automated risk assessment in a domestic scene is discussed, state of the art techniques are reviewed followed by developed methodologies which focus on safer human and robotic interactions with an environment. By using the risk estimation framework, the notion of a quantitative risk score is presented. Hazards within a scene are evaluated and measured using risk elements which provide a numeric representation of specific types of risk. Emphasis is given to the concept of risk as a result of interaction with an environment, specifically whether human or robotic actions in a scene can effect overall risk. To this end, techniques which simulate human or robotic behaviour with regard to risk in an environment are reviewed. Specifically the ideas of interaction and visibility are addressed defining risk in terms of areas within a scene that are visited most often and which are least visible. As with any behaviour simulation techniques, validation of their accuracy is required and a number of simulation evaluation techniques are reviewed. Finally a conclusion as to the current state of automated risk assessment is given, with a brief look at the future of the research area.

Integration of a Human-aware Risk-based Braking System into an Open-Field Mobile Robot

“…Our data's covariance (M7) is negative in all experiments as expected, and a lower risk level means that the person is further. The risk score method defined in [5] with balanced weights is selected to estimate the risk per scenario, and its scores are in the Table IV, as well as the number of samples per test case. Estimated risks test case four, random motion, is the one that presents the maximum difference between environments, likely as a result of the motions' randomness.…”

“…Another approach bases on risk assessment, a risk-scoring method defined as a weighting sum of risk elements, gives a quantitative measurement of any potential risk [5]. Additionally, a static environmental risk map encloses a risk index based on the cell's probability of occupancy over time, applying a set of weighted risk elements according to the application.…”

“…Each experiment calculates risk elements as statistical features of each test case in simulation and realworld performance. Our risk elements are inspired by the ones on [12,13]: For the evaluation, we recall the risk estimation formula from [5] which uses all elements to calculate the robotic application risk. For this purpose, we consider each element as equally important.…”

Towards Safe Robotic Agricultural Applications: Safe Navigation System Design for a Robotic Grass-Mowing Application through the Risk Management Method

“…The use of different metrics in human-robot collaboration stages should be a system priority that relies on robot perception. These metrics can be based on social cues, visiting points to define the riskier spots in a map, or in the form of a multi-variable cost function [30]. Further, an analysis of a robotic navigation system concludes that in applications where safety is a concern, additional considerations must be monitored as the CPU load or the performance, and detected anomalies should be input into the safety system [31].…”