Autonomous Driving (AD) and Advanced Driver Assistance Systems (ADAS) are being vigorously developed for improving traffic safety and transportation efficiency. AD and ADAS need to provide smooth and comfortable driving experiences to drivers and passengers as well as accommodation of other traffic. Individual drivers have different driving styles. This paper proposes a driver-adapted narrow road driving assistance system based on the driving style. The trajectory recorded for participants was used to characterize their driving style. Steering assistance gains were calculated according to the trajectory. In experiments conducted with seventeen participants, different driving styles were compared; without assistance, with the proposed driver-adapted assistance, with constant assistance, and with assistance tuned by a professional test driver. The results showed that the proposed driver-adapted assistance system provided the smoothest driving in terms of the sum of assistance force, the maximum steering angle, and steering entropy. Differences were observed by statistical analyses as well.

An equal matrix grammar is a parallel rewriting system. In this paper, we consider the problem of learning equal matrix grammars from examples. We introduce a learning method based on control sets and show two subclasses learnable in polynomial time with learning methods for regular sets. We also show that for any equal matrix language there exists an equal matrix grammar learnable efficiently from positive structural examples only.