English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Autonomous and Robotics Systems (ARSs) are widespread, complex, andincreasingly coming into contact with the public. Many of these systems aresafety-critical, and it is vital to detect software errors to protect againstharm. We propose a family of novel techniques to detect unusual programexecutions and incorrect program behavior. We model execution behavior bycollecting low-level signals at run time and using those signals to buildmachine learning models. These models can identify previously-unseen executionsthat are more likely to exhibit errors. We describe a tractable approach forcollecting dynamic binary runtime signals on ARSs, allowing the systems toabsorb most of the overhead from dynamic instrumentation. The architecture ofARSs is particularly well-adapted to hiding the overhead from instrumentation.We demonstrate the efficiency of these approaches on ARDUPILOT -- a popularopen-source autopilot software system -- and HUSKY -- an unmanned groundvehicle -- in simulation. We instrument executions to gather data from which webuild supervised machine learning models of executions and evaluate theaccuracy of these models. We also analyze the amount of training data needed todevelop models with various degrees of accuracy, measure the overhead added toexecutions that use the analysis tool, and analyze which runtime signals aremost useful for detecting unusual behavior on the program under test. Inaddition, we analyze the effects of timing delays on the functional behavior ofARSs.

Using Dynamic Binary Instrumentation to Detect Failures in Robotics Software