Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Levent Guvenc has a total of 68 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Nonlinear Model Predictive Control-Based Reverse Path-Planning and Path-Tracking Control of a Vehicle with Trailer System

    by Xincheng Cao, Haochong Chen, Bilin Aksun-Guvenc, Levent Guvenc, Brian Link, Peter J. Richmond, Dokyung Yim, Shihong Fan, John Harber

    Reverse parking of a vehicle with a trailer is a challenging task to complete for human drivers due to its articulated structure, unstable reverse-motion behaviors, and unintuitive steering responses. This paper proposes a compact, trailer-centric nonlinear model predictive control (NMPC)-based automation routine that integrates local motion generation and feedback control into a single receding-horizon framework, without requiring a separately planned reference path or a dedicated path-tracking controller. The trailer unit is represented as a virtual standalone vehicle, and its motion requirements are mapped to the vehicle unit inputs via inverse kinematics. This allows the trajectory prediction and tracking objective to be represented only with trailer states, hence reducing the dimensions of the horizon-stacked state and weighting matrices compared to using the full vehicle-trailer formulation. The proposed controller is implemented as a single-shooting nonlinear program (NLP) and supports a three-stage maneuver sequence to obtain an improved final parking configuration. Simulation results demonstrate successful vehicle-trailer parking maneuvers, while hardware-in-the-loop (HIL) results further illustrate that online NMPC computation times can remain within the real-time sampling deadline, indicating that the proposed NMPC framework can offer a practical receding-horizon automation routine for vehicle-trailer reverse parking tasks.

  • Open Access

    Nonlinear Model Predictive Control-Based Reverse Path-Planning and Path-Tracking Control of a Vehicle with Trailer System

    by Xincheng Cao, Haochong Chen, Bilin Aksun-Guvenc, Levent Guvenc, Brian Link, Peter J Richmond, Dokyung Yim, Shihong Fan, John Harber

    Reverse parking of a vehicle with trailer is a challenging task to complete for human drivers due to its articulated structure, unstable reverse-motion behaviors and unintuitive steering responses. This paper proposes a compact, trailer-centric nonlinear model predictive control (NMPC)-based automation routine that integrates local motion generation and feedback control into a single receding-horizon framework, without requiring a separately planned reference path or a dedicated path-tracking controller. The trailer unit is represented as a virtual standalone vehicle, and its motion requirements are mapped to the vehicle unit inputs via inverse kinematics. This allows trajectory prediction and tracking objective to be represented only with trailer states, hence reducing the dimensions of the horizon-stacked state and weighting matrices compared to using the full vehicle-trailer formulation. The proposed controller is implemented as a single-shooting nonlinear program (NLP) and supports a three-staged maneuver sequence to obtain an improved final parking configuration. Simulation results demonstrate successful vehicle-trailer parking maneuvers, while hardware-in-the-loop (HIL) results further illustrate that online NMPC computation times can remain within the real-time sampling deadline, indicating that the proposed NMPC framework can offer a practical receding-horizon automation routine for vehicle-trailer reverse parking tasks.

  • Open Access

    A Hierarchical NMPC and TD3-Based Framework for Seamless Cruise-to-Park Automated Valet Parking

    by Dajie Tian, Levent Guvenc

    Automated valet parking requires reliable long-range slot searching and precise low-speed docking in confined structured lots. This paper proposes a hierarchical cruise-to-park framework that combines nonlinear model predictive control (NMPC) for predefined-route cruising with a Twin Delayed Deep Deterministic Policy Gradient (TD3) agent for terminal parking. The system is implemented in a structured Simulink environment with Unreal Engine-based geometry-aware sensing modules. During cruising, a camera-based module detects available slots and triggers the transition to parking. The NMPC uses a custom cost function to improve tracking on curved approaches, while the TD3 policy uses LiDAR feedback and reward shaping with an explicit time penalty to encourage efficient, stable docking. Simulation results demonstrate smooth phase transition, accurate cruising, and effective terminal parking in the training slot. Validation on six previously unseen target slots within the same parking-lot environment shows encouraging intra-lot target-slot transferability without retraining. Additional PPO and SAC comparisons and a time-penalty ablation further evaluate the relative learning performance and the effect of reward design, supporting the proposed architecture as a practical baseline for integrated cruise-to-park automated valet parking studies.


  • Open Access

    A Hierarchical NMPC and TD3-Based Framework for Seamless Cruise-to-Park Automated Valet Parking

    by Dajie Tian, Levent Guvenc

    Automated valet parking requires a difficult balance between reliable long-range empty spot seeking within structured parking lots and precise, low-speed maneuvers into tight terminal poses. Traditional controllers often struggle to bridge these two distinct operational domains. This paper proposes a hierarchical cruise-to-park framework that leverages the strengths of classical and learning-based control by using a Nonlinear Model Predictive Controller (NMPC) for predefined-route cruising and a Twin Delayed Deep Deterministic Policy Gradient (TD3) agent for final parking. The system is implemented in a high-fidelity Simulink environment with Unreal Engine-based sensors. During the cruising phase, a camera-based module detects available slots to trigger a seamless transition to the parking phase. The NMPC utilizes a custom cost function to minimize error on curved approaches, while the TD3 policy is trained with reward shaping and an explicit time penalty to promote efficient and stable low-speed docking using LiDAR feedback. Simulation results demonstrate smooth phase transition, accurate cruising, and effective terminal parking in the training slot. The validation results on six previously unseen target slots within the same structured parking-lot environment show encouraging intra-lot transferability without retraining, supporting the proposed modular architecture as a practical baseline for integrated cruise-to-park automated valet parking studies.


  • Open Access

    Hybrid A*-Based Reverse Path-Planning of a Vehicle with Single Trailer

    by Xincheng Cao, Haochong Chen, Bilin Aksun-Guvenc, Levent Guvenc, Brian Link, Peter J. Richmond, Dokyung Yim, Shihong Fan, John Harber

    Reverse parking maneuvering of a vehicle with a trailer system is a difficult task to complete for human drivers due to the multi-body nature of the system and the unintuitive controls required to orientate the trailer properly. The problem is complicated with the presence of other vehicles that the trailer and its connected vehicle must avoid during the reverse parking maneuver. While path-planning methods in reverse motion for vehicles with trailers exist, there is a lack of results that also offer collision avoidance as part of the algorithm. This paper hence proposes a modified Hybrid A*-based algorithm that can accommodate the vehicle–trailer system as well as collision avoidance considerations with the other vehicles and obstacles in the parking environment. One of the novelties of this proposed approach is its adaptability to the vehicle with trailer system, where limits of usable steering input that prevent the occurrence of jackknife incidents vary with respect to system configuration. The other contribution is the addition of the collision avoidance functionality which the standard Hybrid A* algorithm lacks. The method is developed and presented first, followed by simulation case studies to demonstrate the efficacy of the proposed approach.


  • Open Access

    Hybrid A*-Based Reverse Path-Planning of a Vehicle with Trailer System

    by Xincheng Cao, Haochong Chen, Bilin Aksun-Guvenc, Levent Guvenc, Brian Link, Peter J Richmond, Dokyung Yim, Shihong Fan, John Harber

    Reverse parking maneuvering of a vehicle with trailer system is a difficult task to complete for human drivers due to the multi-body nature of the system and the unintuitive controls required to orientate the trailer properly. The problem is complicated with the presence of other vehicles that the trailer and its connected vehicle must avoid during the reverse parking maneuver. While path planning methods in reverse motion for vehicles with trailers exist, there is a lack of results that also offer collision avoidance as part of the algorithm. This paper hence proposes a modified Hybrid A*-based algorithm that can accommodate the vehicle-trailer system as well as collision avoidance considerations with the other vehicles and obstacles in the parking environment. One of the novelties of this proposed approach is its adaptability to the vehicle with trailer system, where limits of usable steering input that prevent the occurrence of jackknife incidents vary with respect to system configuration. The other contribution is the addition of the collision avoidance functionality which the standard Hybrid A* algorithm lacks. The method is developed and presented first, followed by simulation case studies to demonstrate the efficacy of the proposed approach.


  • Open Access

    Communication Disturbance Observer Based Delay-Tolerant Control for Autonomous Driving Systems

    by Xincheng Cao, Haochong Chen, Levent Guvenc, Bilin Aksun-Guvenc

    With the rapid growth of autonomous vehicle technologies, effective path-tracking control has become a critical component in ensuring safety and efficiency in complex traffic scenarios. When a high-level decision-making agent generates a collision-free path, a robust low-level controller is required to precisely follow this trajectory. However, connected autonomous vehicles (CAV) are inherently affected by communication delays and computation delays, which significantly degrade the performance of conventional controllers such as PID or other more advanced controllers like disturbance observers (DOB). While DOB-based designs have shown effectiveness in rejecting disturbances under nominal conditions, their performance deteriorates considerably in the presence of unknown time delays. To address this challenge, this paper proposes a delay-tolerant communication disturbance observer (CDOB) framework for path-tracking control in delayed systems. The proposed CDOB compensates for the adverse effects of time delays, maintaining accurate trajectory tracking even under uncertain and varying delay conditions. It is shown through a simulation study that the proposed control architecture maintains close alignment with the reference trajectory across various scenarios, including single-lane change, double-lane change, and Elastic Band-generated collision avoidance paths under various time delays. Simulation results further demonstrate that the proposed method outperforms conventional approaches in both tracking accuracy and delay robustness, making it well-suited for connected autonomous driving applications.


  • Open Access

    Communication Disturbance Observer Based Delay Tolerant Control for Autonomous Driving System

    by Xincheng Cao, Haochong Chen, Levent Guvenc, Bilin Aksun-Guvenc

    With the rapid growth of autonomous vehicle technologies, effective path-tracking control has become a critical component in ensuring safety and efficiency in complex traffic scenarios. When a high-level decision-making agent generates a collision-free path, a robust low-level controller is required to precisely follow this trajectory. However, connected autonomous vehicles (CAV) are inherently affected by communication delays and computation delays, which significantly degrade the performance of conventional controllers such as PID or other more advanced controllers like disturbance observers (DOB). While DOB-based designs have shown effectiveness in rejecting disturbances under nominal conditions, their performance deteriorates considerably in the presence of unknown time delays. To address this challenge, this paper proposes a delay-tolerant communication disturbance observer (CDOB) framework for path-tracking control in delayed systems. The proposed CDOB compensates for the adverse effects of time delays, maintaining accurate trajectory tracking even under uncertain and varying delay conditions. It is shown through a simulation study that the proposed control architecture maintains close alignment with the reference trajectory across various scenarios, including single-lane change, double-lane change, and Elastic Band–generated collision-avoidance paths under various time delays. Simulation results further demonstrate that the proposed method outperforms conventional approaches in both tracking accuracy and delay robustness, making it well-suited for connected autonomous driving applications.

  • Open Access

    General Obstacle Avoidance Capability Assessment for Autonomous Vehicles

    by Evan Lowe, Levent Guvenc

    As autonomous vehicle (AV) capabilities expand, it is important to ensure their safety during testing and deployment for public usage. While several testing regulations have been proposed in research, US federal, and even global guidelines for low-speed vehicles in metropolitan settings, regulations for high-speed travel are mainly vacant—this is especially true for regulations relating to AV emergency obstacle avoidance maneuvers (EOAMs). Research in this manuscript introduces a general obstacle avoidance capability assessment (GOACA) for AVs traveling at highway speeds. This GOACA includes test modes including car and bicycle active road objects (AROs) in rural and urban highway settings. These tests were novel in their definitions, methodologies, and execution, especially in the context of AVs driving at highway speeds—critically, this research proposes a test evaluation protocol such that it could serve as a foundation for an official regulation in the future. These GOACA tests included adjacent traffic vehicles which have not been utilized in the prior literature when considering EOAMs within a wholistic AV system context. While the vehicle type will cause simulation results to var, in general, vehicle-to-vehicle (V2V) communication is recommended for usage with AVs at highway speeds for critical safety. This is especially true when considering oncoming traffic and low surface μ conditions.


  • Open Access

    General Obstacle Avoidance Capability Assessment for Autonomous Vehicles

    by Evan Lowe, Levent Guvenc

    As autonomous vehicle (AV) capabilities expand, it is important to assure their safety during testing and deployment for public usage. While several testing regulations have been proposed in research, US federal, and even global guidelines for low-speed vehicles in metropolitan settings, regulations for high-speed travel are mainly vacant. This is especially true for regulations relating to AV emergency obstacle avoidance maneuvers (EOAMs). With the motivation of filling this gap, research reported in this manuscript introduces a general obstacle avoidance capability assessment (GOACA) method for AVs traveling at highway speeds. This GOACA includes test modes including interactions with car and bicycle active road objects (AROs) in rural and urban highway settings. These tests are novel in their definitions, methodologies, and execution, especially in the context of AV driving at highway speeds. This research proposes a test evaluation protocol such that it could serve as a foundation for an official regulation in the future. The proposed GOACA tests include adjacent traffic vehicles which have not been utilized in the prior literature when considering EOAMs within a holistic AV system context. The use of the proposed GOACA method is illustrated using high fidelity simulations of an EOAM algorithm. Based on the assessments, vehicle-to-vehicle (V2V) communication is recommended for usage with AVs at highway speeds for critical safety. This is especially true when considering oncoming traffic and low road surface friction conditions.