SCSeungwon Choi

Seungwon Choi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Seungwon Choi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Fallback Approach for In-Lane Stop on Curved Roads Using Differential Braking

    by Jihoon Sung, Seungwon Choi, Kunsoo Huh

    Due to the importance of safety in the development of Automated Driving Systems (ADS), research is ongoing on fallback functions for ADS. Scenarios involving steering actuator failures during curved road driving are particularly dangerous, with limited available fallback options. This paper proposes a method for achieving a safer in-lane stop using differential braking when steering actuator failure occurs. Lateral motion is induced by the difference in longitudinal forces between the left and right sides, facilitating an in-lane stop maneuver. The vehicle’s lateral behavior under differential braking and changes in front-wheel steering angle are modeled. A model-based estimator using a Kalman filter estimates the vehicle’s state and steering angle. Based on these estimations and lane information, a controller employing a linear quadratic regulator (LQR) is developed. The effectiveness of the differential braking in-lane stop system is validated through simulation.


  • Real-Time Terrain Condition Detection for Off-Road Driving Based on Transformer

    by Hyukju Shon, Seungwon Choi, Kunsoo Huh

    Off-road driving is dangerous due to the deformation and irregularities of the road surface. The diverse nature of off-road surfaces makes it difficult to identify the safety of the driving surface. In this study, a Transformer-based neural network is proposed to estimate the drivability of various off-road surfaces, aiming to discern whether the terrain is safe to drive or potentially dangerous. The network only utilizes Controller Area Network (CAN)-bus signals from the vehicle, which makes it easy to implement on a readily available vehicle. To train the network, driving data was collected from a diverse range of off-road environments, from areas where novice drivers can drive safely to hazardous areas where expert drivers get stuck. We also propose a post-processing algorithm to filter out false estimations and limit frequent changes in estimation, as these can have detrimental effects on real-world systems. The performance of our algorithm was evaluated in real-time on various off-road surfaces showing high level of accuracy.


  • A Differential Brake-Actuated Steering System for Redundancy of Steer-by-Wire

    by Jihoon Sung, Seungwon Choi, Kunsoo Huh

    Steer-by-Wire (SbW) system offers advantages for vehicle electrification and autonomous driving. To utilize SbW system, it is essential to prioritize safety and develop reliable backup systems. This paper introduces a backup system that employs longitudinal differential forces to address SbW system failures. When the SbW system malfunctions and cannot perform its intended function, the proposed system controls lateral motion instead. The proposed system achieves this control by utilizing the differential longitudinal forces between the left and right sides. The system model incorporates the lateral motion and wheel steering models to consider the effect of the differential longitudinal forces. Additionally, sensitivity analysis is conducted for the model representing the changes in the front wheel steering angle. As a result, the parameters are mapped with respect to the vehicle speed which has the most significant impact. A model-based state observer based on Kalman filter estimates the unobservable vehicle states. A controller based on a linear quadratic regulator is developed to accurately perform the steering motion of the vehicle according to the driver's intention. The proposed brake-actuated steering system is validated through simulations and real-world experiments. The results show that it enables the vehicle to perform critical operations, such as lane changes, when SbW fails.


  • Interpretable Vehicle Speed Estimation Based on Dual Attention Network for 4WD Off-Road Vehicles

    by Seungwon Choi, Hyukju Shon, Kunsoo Huh

    The difficulty of calculating the speed of Four Wheel Drive (4WD) vehicles in off-road terrain is well known, especially at a low speed. This difficulty stems from the common occurrence of wheel slippage because all wheels are driven and the unpaved terrain interacts with the vehicle during driving. To address this issue, this paper presents a robust vehicle speed estimation algorithm based on dual attention networks for 4WD off-road vehicles. The algorithm identifies important signals and time in order to capture the interaction between the vehicle and the terrain. Instead of estimating vehicle speed directly, the algorithm estimates wheel slip ratios, which are then used to calculate the vehicle speed, providing interpretability and comprehension of how the vehicle speed is obtained. The effectiveness of the proposed method is demonstrated through real-world driving data collected in various off-road terrains, such as sand, mud, and rock, and verified through comparative studies and real-time estimation. Additionally, the proposed algorithm is capable of estimating vehicle speed without the need for external sensors, reducing costs.


  • Open Access

    Driving Style-Based Conditional Variational Autoencoder for Prediction of Ego Vehicle Trajectory

    by Dongchan Kim, Hyukju Shon, Nahyun Kweon, Seungwon Choi, Chanuk Yang, Kunsoo Huh

    Trajectory prediction of the ego vehicle is essential for advanced driver assistance systems to function properly. By recognizing various driving styles and predicting trajectories reflecting them, the prediction performance is enhanced, and a personalized trajectory can be generated. Therefore, we propose to combine driving style recognition and trajectory prediction tasks using only in-vehicle CAN-bus sensor data for possible application to normal vehicles. The DeepConvLstm network was utilized for driving style recognition, and a generative-based model was used for trajectory prediction. The classified driving style was added as a condition to the network. In addition, the past trajectory of the ego vehicle is estimated and utilized as an additional input for performance improvement. The performance of the proposed method is analyzed in terms of the root mean squared error (RMSE) and mean absolute error (MAE) compared with the case wherein the driving style and the past trajectory are not conditioned or given, respectively. The results demonstrate the effectiveness of the proposed method.


  • Open Access

    An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network

    by Dongchan Kim, Gihoon Kim, Seungwon Choi, Kunsoo Huh

    An integration scheme for sideslip angle estimation is proposed where a deep neural network and a simple kinematics-based model are combined in an unscented Kalman filter. The deep neural network contains two modules: a sensor filtering network designed to overcome the limitations of the kinematics-based model and a deep ensemble network to estimate the sideslip angle and its uncertainty. Both networks use recurrent neural networks with long short-term memory to analyze sequential sensor data. The networks were trained using only input signal sets that can be obtained from on- board sensor measurements. The filtering network reduces the noise and bias of the input signals to match the model used for the unscented Kalman filter. Next, the initial estimate and its uncertainty obtained from the deep ensemble network are utilized as a new measurement in the unscented Kalman filter, inducing an adaptive measurement variance. The algorithm was verified through both simulation and experiment, and the results demonstrate the effectiveness of the proposed algorithm.