To　provide　a　better　understanding　of　individual　driver＇s　driving　style　classification　in　a　traditional　and　a　CV　environment,　spatiotemporal　characteristics　of　vehicle　trajectories　on　a　road　tunnel　were　extracted　through　a　driving　simulator-based　experiment.　Speed,　acceleration,　and　rate　of　acceleration　changes　are　selected　as　clustering　indexes.　The　dynamic　time　warping　and　k-means　clustering　were　adopted　to　classify　participants　into　different　risk　level　groups.　To　assess　the　driver　behavior　benefits　in　a　CV　environment,　an　indicator　BI　(behavior　indicator,　BI)　was　defined　based　on　the　standard　deviation　of　speed,　the　standard　deviation　of　acceleration,　and　the　standard　deviation　of　the　rate　of　acceleration　change.　Then,　the　index　BI　of　each　driver　was　calculated.　Furthermore,　this　paper　explored　driving　style　classification,　not　in　terms　of　traditional　driving　environment,　but　rather　the　transition　patterns　from　a　traditional　driving　environment　to　a　CV　environment.　The　results　revealed　that　inside　a　long　tunnel,　80　%　of　drivers　benefited　from　a　CV　environment.　Moreover,　drivers　might　need　training　before　using　a　CV　system,　especially　female　drivers　who　have　low　driving　mileage.　In　addition,　the　results　showed　that　the　driving　style　of　69　%　of　the　drivers＇　transferred　from　a　high　risk-level　to　a　low　risk-level　when　driving　in　a　CV　environment.　The　study　results　can　be　expected　to　improve　driving　training　education　programs　and　also　to　provide　a　valuable　reference　for　developing　individual　in-vehicle　human-machine　interface　projects　and　other　proactive　safety　countermeasures.