Traceability and Accountability in Autonomous Agents

Rodríguez-Lera, Francisco J.; González-Santamarta, Miguel Á.; Guerrero, Ángel Manuel; Martı́n, Francisco; Olivera, Vicente Matellán

doi:10.1007/978-3-030-57805-3_28

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accountability system should be faced from a middleware‐free approach, for this reason, this research has been working in a three layer approach described in previous research (Matellán et al, 2021; Rodríguez‐Lera et al, 2019; Rodríguez‐Lera, Santamarta, et al, 2020). However, the authors also believe that the accountability system should be faced from any of the most extended robotic middleware.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, there are solutions to get statistics about message interchange or to provide network introspection services; see (Bihlmaier et al, 2016). In (Rodríguez‐Lera, Santamarta, et al, 2020), authors show some of the most popular tools according to a three‐factor metric: (1) they are available online in ROS repositories or ROS wiki‐forum; (2) they are available online in GitHub, and it has been forked, or (3) the tool has been used in a well‐known conference, such as the ROSPlan dispatcher or the rqt plugin (Lima & Ventura, 2018).…”

Section: Introductionmentioning

confidence: 99%

“…In a prior work (Rodríguez‐Lera, Santamarta, et al, 2020), authors naively proposed a formal view of an audit process in autonomous robots tracing the links between logs and robot behaviours. This study presents an update based on what we call facts, revisiting the three‐layer accountability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards explainability in robotics: A performance analysis of a cloud accountability system

et al. 2022

View full text Add to dashboard Cite

Understanding why a robot's behaviour was triggered is a growing concern to get human‐acceptable social robots. Every action, expected and unexpected, should be able to be explained and audited. The formal model proposed here deals with different information levels, from low‐level data, such as sensors' data logging; to high‐level data that provide an explanation of the robot's behaviour. This study examines the impact on the robot system of a custom log engine based on a custom ROS logging node and investigates pros and cons when used together with a NoSQL database locally and in a cloud environment. Results allow to characterize these alternatives and explore the best strategy for offering a fully log‐based accountability engine that maximizes the mapping between robot behaviour and robot logs.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%