Role of context in determining transfer of risk knowledge in roundabouts

Deveaux, Duncan; Higuchi, Takamasa; Uçar, Seyhan; Härri, Jérôme; Altintas, Onur

The ability to predict the exit patterns of vehicles in a roundabout shows
potential to improve the safety and efficiency of roundabout crossings by connected
vehicles. Namely, vehicles seeking to enter a roundabout in the presence
of incoming vehicles, may take educated decisions on whether to enter
the roundabout based on the likelihood of the incoming vehicles not to exit
and cause a merging conflict. In previous work, a machine learning model was
trained to assess the probability of a vehicle to exit a roundabout based on
its observed position relatively to the next exit. Yet, the transferability of the
knowledge of exit probability models was not investigated, i.e., whether the
knowledge of an existing exit probability model can be accurately transferred
in unseen roundabouts, both for model usage and training. In this paper,
we compute a metric similarity of exit probability models trained from eight
real roundabouts. In turn, we identify the contextual features of two roundabouts
which impact the similarity of the resulting exit probability models,
and define three levels of context similarity, i.e., strict, moderate, and low.
Lastly, significant accuracy improvements are obtained by constraining the
knowledge transfer of exit probability models to roundabouts which feature a
similar context. On the one hand, applying exit probability models on distinct
roundabouts with a moderately similar context yielded an average accuracy of
80:44:6%, which is equivalent to the most accurate non-similar models. On
the other hand, training a model for an unseen roundabout using exclusively
training data extracted from roundabouts with a moderately similar context
featured a 80  5% accuracy, which represents a consistent accuracy increase
of 8:5  4:8% compared with knowledge transfer without context constraints.

Systèmes de Communication
Eurecom Ref:
© Elsevier. Personal use of this material is permitted. The definitive version of this paper was published in and is available at :