The　new　draft　AASHTO　standard　practice　PP70-10　and　PP69-10　are　promising　to　change　the　landscape　of　rut　measurement.　PP70-10　specifies　the　technical　requirements　for　transverse　profiling　and　PP69-10　defines　multiple　parameters　such　as　percent　deformation　and　rut　cross-sectional　area　to　characterize　a　rut.　Per　PP70-10,　an　inspection　device　should　cover　at　least　4.0　m　(13　ft)　transverse　width　in　order　to　cover　the　full　lane　under　vehicle　wandering.　However,　for　many　existing　transverse　profilers,　it　is　challenging　to　identify　the　lane　markings　from　the　raw　images　in　a　consistent　manner.　This　deficiency　would　prevent　these　systems　from　accurately　calculating　PP69-10-based　rut　attributes.　In　this　study,　with　the　field　data　collected　in　Arkansas　national　highway　systems　(NHS)　using　an　automated　system　called　PaveVision3D　Ultra,　the　impact　of　lane　offsets　on　PP69-10-based　rut　attributes　is　investigated.　The　rut　attributes　calculated　with　programs　embedded　in　the　system,　where　accurate　lane　locations　are　semiautomated　extracted　from　both　2D　and　3D　images,　are　set　up　as　base　values.　It　is　found　that　lane　offsets　greater　than　50　mm　would　cause　significant　errors　in　rut　measurement.　To　reduce　the　negative　effect　of　inaccurate　lane　identification　on　rut　characterization,　a　methodical　framework　is　proposed　in　this　research.　A　case　study　is　performed　to　demonstrate　that　machine　learning　approaches　could　satisfactorily　aid　in　increasing　the　accuracy　of　rut　characterization　even　when　the　locations　of　actual　lane　markings　are　unknown.　This　research　would　improve　the　reliability　and　accuracy　of　the　new　AASHTO　rut　measurement.　(C)　2015　American　Society　of　Civil　Engineers.