Autonomous Articulated Vehicle Control via Deep Reinforcement Learning and High-Dimensional Perception

dc.contributor.authorSchnapp, Benjamin David
dc.date.accessioned2026-11-18T18:23:05Z
dc.date.issued2026-11-18
dc.date.submitted2026-09-05
dc.description.abstractAutonomous control of articulated tractor-trailer vehicles is difficult because the passive hitch adds a revolute degree of freedom whose reverse dynamics are open-loop unstable, driving the trailer toward the jackknife regime. This thesis develops and evaluates a learning-based controller for this setting, targeting the confined low-speed maneuvers typical of distribution yard and loading-dock operations, and carries it from simulation onto physical hardware. A Twin Delayed Deep Deterministic Policy Gradient (TD3) agent is trained in a custom Gymnasium simulation of a shunt-truck tractor-trailer. Controlled ablations isolate the learning algorithm, reward formulation, and observation modality. TD3 under a multiplicative reward that jointly penalizes tracking error and hitch articulation produces the highest and most consistent reverse completion while also reducing tracking and articulation errors. A compact engineered state representation is more reliable than higher-dimensional LiDAR or bird’s-eye-view (BEV) image observations under an otherwise identical training recipe. Training a policy directly on the raw image fails, but controlled experiments show that the image contains sufficient task-relevant information and identify the off-policy actor-critic training process as the primary source of failure. Geometry distillation addresses this failure by training a supervised encoder to recover the vehicle’s path geometry from the BEV image and freezing that encoder during policy optimization. The resulting policy restores reliable from-scratch learning to near engineered-state performance in both forward and reverse lane following. The same approach extends to obstacle navigation, where the image-derived representation provides both an avoidance path and a measure of layout difficulty, allowing the learned controller to follow feasible detours and stop when a layout should not be attempted. The geometry-encoded BEV policies are deployed on a physical articulated platform, an AgileX Hunter SE with a scale trailer. Deployment uses a stripped-down Autoware stack whose planning and control layers are replaced by an RL bridge that reproduces the observation and action interfaces used during training. Four formal lane-following trials, two forward and two reverse, were conducted and all reached the goal under policy control. Forward tracking transferred with low error, while reverse tracking exhibited a sustained, steering-rate-limited articulation oscillation that was absent from simulation. The hardware results therefore demonstrate physical transfer of the learned controller while identifying reverse articulation dynamics as the dominant remaining sim-to-real limitation.
dc.identifier.urihttps://hdl.handle.net/10012/24706
dc.language.isoen
dc.pendingfalse
dc.publisherUniversity of Waterlooen
dc.subjectautonomous vehicles
dc.subjectarticulated vehicle control
dc.subjectdeep reinforcement learning
dc.titleAutonomous Articulated Vehicle Control via Deep Reinforcement Learning and High-Dimensional Perception
dc.typeMaster Thesis
uws-etd.degreeMaster of Applied Science
uws-etd.degree.departmentMechanical and Mechatronics Engineering
uws-etd.degree.disciplineMechanical Engineering
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.embargo.terms0
uws.contributor.advisorKhajepour, Amir
uws.contributor.advisorArami, Arash
uws.contributor.affiliation1Faculty of Engineering
uws.peerReviewStatusUnrevieweden
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Schnapp_Benjamin_David.pdf
Size:
8.47 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
6.4 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections