Quantifying the “Mechanicalness” of Autonomous Trajectory Tracking: A Real-Vehicle Comparison with Human Drivers

{"Autonomous":[0],"driving":[1,185],"systems":[2],"often":[3],"exhibit":[4],"trajectory":[5,51],"tracking":[6,28],"behavior":[7],"that":[8,87],"differs":[9],"markedly":[10],"from":[11],"human":[12],"drivers,":[13,110],"a":[14,37,42,56,90,151],"phenomenon":[15],"intuitively":[16],"described":[17],"as":[18,133],"\\"mechanicalness.''":[19],"This":[20],"study":[21],"moves":[22],"beyond":[23],"the":[24,47],"traditional":[25],"focus":[26],"on":[27,55],"accuracy":[29],"to":[30,71,156],"systematically":[31],"analyze":[32],"these":[33],"behavioral":[34],"differences":[35],"through":[36],"real-vehicle":[38],"comparative":[39],"experiment.":[40],"Using":[41],"steer-by-wire":[43],"vehicle":[44],"equipped":[45],"with":[46,117],"open-source":[48],"Autoware":[49,88],"platform,":[50],"data":[52],"were":[53],"collected":[54],"closed":[57],"campus":[58],"road":[59],"under":[60],"straight":[61],"and":[62,82,106,123,143,159,170,177],"curved":[63],"conditions.":[64],"A":[65],"five-dimensional":[66],"evaluation":[67],"framework":[68],"is":[69],"established":[70],"quantify":[72],"control":[73,186],"continuity,":[74],"prediction":[75,145,168],"horizon,":[76],"error":[77],"response":[78],"mode,":[79],"style":[80],"adaptability,":[81],"interaction":[83],"friendliness.":[84],"Results":[85],"show":[86],"exhibits":[89],"\\"high-precision,":[91],"low-smoothness,":[92],"zero-tolerance''":[93],"mechanical":[94,157],"style,":[95],"characterized":[96],"by":[97],"high-frequency":[98],"micro-corrections,":[99],"reactive":[100],"curve":[101],"entry,":[102],"rigid":[103],"speed":[104],"tracking,":[105,138],"segmented":[107],"braking.":[108],"Human":[109],"in":[111],"contrast,":[112],"employ":[113],"an":[114],"organic":[115],"mode":[116],"discrete":[118],"corrections,":[119],"elastic":[120],"path":[121],"tolerance,":[122],"anticipatory":[124],"coordination.":[125,172],"The":[126,147],"technical":[127],"origins":[128],"of":[129],"mechanicalness":[130],"are":[131],"identified":[132],"four":[134],"algorithmic":[135],"paradigms:":[136],"geometric":[137],"decoupled":[139],"control,":[140,158],"error-driven":[141],"logic,":[142],"limited":[144],"horizon.":[146],"findings":[148],"further":[149],"reveal":[150],"systematic":[152],"safety-comfort":[153],"trade-off":[154],"inherent":[155],"suggest":[160],"optimization":[161],"directions":[162],"including":[163],"adaptive":[164],"dead-zone":[165],"mechanisms,":[166],"extended":[167],"horizons,":[169],"lateral-longitudinal":[171],"These":[173],"insights":[174],"provide":[175],"theoretical":[176],"engineering":[178],"foundations":[179],"for":[180],"developing":[181],"more":[182],"human-like":[183],"autonomous":[184],"strategies.":[187]}

Authors

Publication Details

Journal
Vehicles
Published
2026-09-07
DOI
https://doi.org/10.3390/vehicles8090210
Primary Topic
Vehicle Dynamics and Control Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Quantifying the “Mechanicalness” of Autonomous Trajectory Tracking: A Real-Vehicle Comparison with Human Drivers

Xinjian Yuan, Yanlun Ren, Zhaona Lu, Mei Cao et al.
Vehicles
Vehicle Dynamics and Control Systems
article

Quantifying the “Mechanicalness” of Autonomous Trajectory Tracking: A Real-Vehicle Comparison with Human Drivers

Xinjian Yuan, Yanlun Ren, Zhaona Lu, Mei Cao, Ruijie Ma
article en

Abstract

Autonomous driving systems often exhibit trajectory tracking behavior that differs markedly from human drivers, a phenomenon intuitively described as "mechanicalness.'' This study moves beyond the traditional focus on tracking accuracy to systematically analyze these behavioral differences through a real-vehicle comparative experiment. Using a steer-by-wire vehicle equipped with the open-source Autoware platform, trajectory data were collected on a closed campus road under straight and curved conditions. A five-dimensional evaluation framework is established to quantify control continuity, prediction horizon, error response mode, style adaptability, and interaction friendliness. Results show that Autoware exhibits a "high-precision, low-smoothness, zero-tolerance'' mechanical style, characterized by high-frequency micro-corrections, reactive curve entry, rigid speed tracking, and segmented braking. Human drivers, in contrast, employ an organic mode with discrete corrections, elastic path tolerance, and anticipatory coordination. The technical origins of mechanicalness are identified as four algorithmic paradigms: geometric tracking, decoupled control, error-driven logic, and limited prediction horizon. The findings further reveal a systematic safety-comfort trade-off inherent to mechanical control, and suggest optimization directions including adaptive dead-zone mechanisms, extended prediction horizons, and lateral-longitudinal coordination. These insights provide theoretical and engineering foundations for developing more human-like autonomous driving control strategies.

VehiclesVol. 8(9)
Openalex Percentile: Top 37%
Vehicle Dynamics and Control Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.