arXiv subjects

Myounggyu Won

Publications and source records attributed to Myounggyu Won.

At least 19 recordsLinked to original sources

arXiv2026

BucketKD: A Safety-Aware Bucket-Based Knowledge Distillation Framework for End-to-End Motion Planning

End-to-end motion planning has emerged as a promising paradigm in autonomous driving, directly mapping raw sensor data to control commands via deep neural networks. Despite its advantages, its large model size hinders deployment in resource-constrained platforms. In this paper, we present BucketKD, a bucket-based knowledge distillation framework that yields compact and safety-aware end-to-end planners. Compared to the state-of-the-art approach, which relies on simplified planning state representations, BucketKD discretizes critical environmental variables into adaptive buckets that capture richer scene semantics while preserving efficiency. In addition, we design a safety-aware waypoint attention mechanism that evaluates each waypoint's risk level by accounting for both obstacle proximity and relative motion through a time-to-collision (TTC) formulation widely used in transportation research. This enables the student model to better retain safety-critical behaviors during distillation. Extensive experiments in CARLA using the Bench2Drive dataset show that BucketKD significantly outperforms the state-of-the-art in both planning accuracy and safety while maintaining strong compression ratios.

cs.RO↗

arXiv2026

PALCAS: A Priority-Aware Intelligent Lane Change Advisory System for Autonomous Vehicles using Federated Reinforcement Learning

We present a priority-aware intelligent lane change advisory system based on multi-agent federated reinforcement learning, namely PALCAS, for autonomous vehicles (AVs). While existing lane-change approaches typically focus on single-agent systems or centralized multi-agent systems, we introduce a federated reinforcement learning-based multi-agent lane change system prioritizing lane changing based on vehicle destination urgency. PALCAS incorporates a novel priority-aware safe lane-change reward function to enable judicious lane-change decisions in both mandatory and discretionary scenarios. PALCAS leverages the parameterized deep Q-network (PDQN) algorithm to facilitate effective cooperation among agents, enabling both lateral and longitudinal motion controls of AVs. Extensive simulations conducted using the SUMO traffic simulator and Mosaic V2X communication framework demonstrate that PALCAS significantly improves traffic efficiency, driving safety, comfort, destination arrival rates, and merging success rates compared to baseline methods.

cs.RO↗

arXiv2025

Z-Merge: Multi-Agent Reinforcement Learning for On-Ramp Merging with Zone-Specific V2X Traffic Information

Ramp merging is a critical and challenging task for autonomous vehicles (AVs), particularly in mixed traffic environments with human-driven vehicles (HVs). Existing approaches typically rely on either lane-changing or inter-vehicle gap creation strategies based solely on local or neighboring information, often leading to suboptimal performance in terms of safety and traffic efficiency. In this paper, we present a V2X (vehicle-to-everything communication)-assisted Multiagent Reinforcement Learning (MARL) framework for on-ramp merging that effectively coordinates the complex interplay between lane-changing and inter-vehicle gap adaptation strategies by utilizing zone-specific global information available from a roadside unit (RSU). The merging control problem is formulated as a Multiagent Partially Observable Markov Decision Process (MA-POMDP), where agents leverage both local and global observations through V2X communication. To support both discrete and continuous control decisions, we design a hybrid action space and adopt a parameterized deep Q-learning approach. Extensive simulations, integrating the SUMO traffic simulator and the MOSAIC V2X simulator, demonstrate that our framework significantly improves merging success rate, traffic efficiency, and road safety across diverse traffic scenarios.

cs.RO↗

arXiv2024

VRPD-DT: Vehicle Routing Problem with Drones Under Dynamically Changing Traffic Conditions

The vehicle routing problem with drones (VRP-D) is to determine the optimal routes of trucks and drones such that the total operational cost is minimized in a scenario where the trucks work in tandem with the drones to deliver parcels to customers. While various heuristic algorithms have been developed to address the problem, existing solutions are built based on simplistic cost models, overlooking the temporal dynamics of the costs, which fluctuate depending on the dynamically changing traffic conditions. In this paper, we present a novel problem called the vehicle routing problem with drones under dynamically changing traffic conditions (VRPD-DT) to address the limitation of existing VRP-D solutions. We design a novel cost model that factors in the actual travel distance and projected travel time, computed using a machine learning-driven travel time prediction algorithm. A variable neighborhood descent (VND) algorithm is developed to find the optimal truck-drone routes under the dynamics of traffic conditions through incorporation of the travel time prediction model. A simulation study was performed to evaluate the performance compared with a state-of-the-art VRP-D heuristic solution. The results demonstrate that the proposed algorithm outperforms the state-of-the-art algorithm in various delivery scenarios.

cs.CY↗

arXiv2024

SmartPathfinder: Pushing the Limits of Heuristic Solutions for Vehicle Routing Problem with Drones Using Reinforcement Learning

The Vehicle Routing Problem with Drones (VRPD) seeks to optimize the routing paths for both trucks and drones, where the trucks are responsible for delivering parcels to customer locations, and the drones are dispatched from these trucks for parcel delivery, subsequently being retrieved by the trucks. Given the NP-Hard complexity of VRPD, numerous heuristic approaches have been introduced. However, improving solution quality and reducing computation time remain significant challenges. In this paper, we conduct a comprehensive examination of heuristic methods designed for solving VRPD, distilling and standardizing them into core elements. We then develop a novel reinforcement learning (RL) framework that is seamlessly integrated with the heuristic solution components, establishing a set of universal principles for incorporating the RL framework with heuristic strategies in an aim to improve both the solution quality and computation speed. This integration has been applied to a state-of-the-art heuristic solution for VRPD, showcasing the substantial benefits of incorporating the RL framework. Our evaluation results demonstrated that the heuristic solution incorporated with our RL framework not only elevated the quality of solutions but also achieved rapid computation speeds, especially when dealing with extensive customer locations.

cs.CY↗

arXiv2023

WatchPed: Pedestrian Crossing Intention Prediction Using Embedded Sensors of Smartwatch

The pedestrian crossing intention prediction problem is to estimate whether or not the target pedestrian will cross the street. State-of-the-art techniques heavily depend on visual data acquired through the front camera of the ego-vehicle to make a prediction of the pedestrian's crossing intention. Hence, the efficiency of current methodologies tends to decrease notably in situations where visual input is imprecise, for instance, when the distance between the pedestrian and ego-vehicle is considerable or the illumination levels are inadequate. To address the limitation, in this paper, we present the design, implementation, and evaluation of the first-of-its-kind pedestrian crossing intention prediction model based on integration of motion sensor data gathered through the smartwatch (or smartphone) of the pedestrian. We propose an innovative machine learning framework that effectively integrates motion sensor data with visual input to enhance the predictive accuracy significantly, particularly in scenarios where visual data may be unreliable. Moreover, we perform an extensive data collection process and introduce the first pedestrian intention prediction dataset that features synchronized motion sensor data. The dataset comprises 255 video clips that encompass diverse distances and lighting conditions. We trained our model using the widely-used JAAD and our own datasets and compare the performance with a state-of-the-art model. The results demonstrate that our model outperforms the current state-of-the-art method, particularly in cases where the distance between the pedestrian and the observer is considerable (more than 70 meters) and the lighting conditions are inadequate.

cs.CV↗

arXiv2023

LCS-TF: Multi-Agent Deep Reinforcement Learning-Based Intelligent Lane-Change System for Improving Traffic Flow

Discretionary lane-change is one of the critical challenges for autonomous vehicle (AV) design due to its significant impact on traffic efficiency. Existing intelligent lane-change solutions have primarily focused on optimizing the performance of the ego-vehicle, thereby suffering from limited generalization performance. Recent research has seen an increased interest in multi-agent reinforcement learning (MARL)-based approaches to address the limitation of the ego vehicle-based solutions through close coordination of multiple agents. Although MARL-based approaches have shown promising results, the potential impact of lane-change decisions on the overall traffic flow of a road segment has not been fully considered. In this paper, we present a novel hybrid MARL-based intelligent lane-change system for AVs designed to jointly optimize the local performance for the ego vehicle, along with the global performance focused on the overall traffic flow of a given road segment. With a careful review of the relevant transportation literature, a novel state space is designed to integrate both the critical local traffic information pertaining to the surrounding vehicles of the ego vehicle, as well as the global traffic information obtained from a road-side unit (RSU) responsible for managing a road segment. We create a reward function to ensure that the agents make effective lane-change decisions by considering the performance of the ego vehicle and the overall improvement of traffic flow. A multi-agent deep Q-network (DQN) algorithm is designed to determine the optimal policy for each agent to effectively cooperate in performing lane-change maneuvers. LCS-TF's performance was evaluated through extensive simulations in comparison with state-of-the-art MARL models. In all aspects of traffic efficiency, driving safety, and driver comfort, the results indicate that LCS-TF exhibits superior performance.

cs.CY↗

arXiv2023

RLPG: Reinforcement Learning Approach for Dynamic Intra-Platoon Gap Adaptation for Highway On-Ramp Merging

A platoon refers to a group of vehicles traveling together in very close proximity using automated driving technology. Owing to its immense capacity to improve fuel efficiency, driving safety, and driver comfort, platooning technology has garnered substantial attention from the autonomous vehicle research community. Although highly advantageous, recent research has uncovered that an excessively small intra-platoon gap can impede traffic flow during highway on-ramp merging. While existing control-based methods allow for adaptation of the intra-platoon gap to improve traffic flow, making an optimal control decision under the complex dynamics of traffic conditions remains a challenge due to the massive computational complexity. In this paper, we present the design, implementation, and evaluation of a novel reinforcement learning framework that adaptively adjusts the intra-platoon gap of an individual platoon member to maximize traffic flow in response to dynamically changing, complex traffic conditions for highway on-ramp merging. The framework's state space has been meticulously designed in consultation with the transportation literature to take into account critical traffic parameters that bear direct relevance to merging efficiency. An intra-platoon gap decision making method based on the deep deterministic policy gradient algorithm is created to incorporate the continuous action space to ensure precise and continuous adaptation of the intra-platoon gap. An extensive simulation study demonstrates the effectiveness of the reinforcement learning-based approach for significantly improving traffic flow in various highway on-ramp merging scenarios.

cs.CY↗

arXiv2022

LSTM-Based Adaptive Vehicle Position Control for Dynamic Wireless Charging

Dynamic wireless charging (DWC) is an emerging technology that allows electric vehicles (EVs) to be wirelessly charged while in motion. It is gaining significant momentum as it can potentially address the range limitation issue for EVs. However, due to significant power loss caused by wireless power transfer, improving charging efficiency remains as a major challenge for DWC systems. This paper presents the first LSTM-based vehicle motion control system for DWC designed to maximize charging efficiency. The dynamics of the electromagnetic field generated by the transmitter coils of a DWC system are modeled based on a multi-layer LSTM. The LSTM model is used to make a prediction of the lateral position where the electromagnetic strength is expected to be maximal and to control the EV motion accordingly to optimize charging efficiency. Simulations were conducted to demonstrate that our LSTM-based approach achieves by up to 162.3% higher charging efficiency compared with state-of-the-art vehicle motion control systems focused on keeping an EV in the center of lane.

eess.SP↗

arXiv2021

Towards Fully Autonomous Drone-Based Last-Mile Delivery

The drone-based last-mile delivery is an emerging technology to deliver parcels using drones loaded on a truck. As more and more autonomous vehicles (AVs) will be available for delivery services, an opportunity is arising to fully automate drone-based last-mile delivery. In this paper, we integrate AVs with drone-based last-mile delivery aiming to fully automate the last-mile delivery process. We define a new problem called the autonomous vehicle routing problem with drones (A-VRPD). A-VRPD is to select AVs from a pool of available AVs and to schedule them to serve customers with an objective of minimizing the total operational cost. We formulate A-VRPD as an Integer Linear Programming (ILP) and propose a greedy algorithm to solve the problem based on real-world operational costs for different types of AVs, traveling distances calculated considering the current traffic conditions, and varying load capacities of AVs. Extensive simulations performed under various random delivery scenarios demonstrate that the proposed algorithm effectively increases profits for both the delivery company and AV owners compared with traditional VRP-D (and TSP-D) algorithm-based approaches.

cs.CY↗

arXiv2021

SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning

We present a novel adaptive cruise control (ACC) system namely SAINT-ACC: {S}afety-{A}ware {Int}elligent {ACC} system (SAINT-ACC) that is designed to achieve simultaneous optimization of traffic efficiency, driving safety, and driving comfort through dynamic adaptation of the inter-vehicle gap based on deep reinforcement learning (RL). A novel dual RL agent-based approach is developed to seek and adapt the optimal balance between traffic efficiency and driving safety/comfort by effectively controlling the driving safety model parameters and inter-vehicle gap based on macroscopic and microscopic traffic information collected from dynamically changing and complex traffic environments. Results obtained through over 12,000 simulation runs with varying traffic scenarios and penetration rates demonstrate that SAINT-ACC significantly enhances traffic flow, driving safety and comfort compared with a state-of-the-art approach.

cs.RO↗

arXiv2021

Reducing Operation Cost of LPWAN Roadside Sensors Using Cross Technology Communication

Low-Power Wide-Area Network (LPWAN) is an emerging communication standard for Internet of Things (IoT) that has strong potential to support connectivity of a large number of roadside sensors with an extremely long communication range. However, the high operation cost to manage such a large-scale roadside sensor network remains as a significant challenge. In this article, we propose Low Operation-Cost LPWAN (LOC-LPWAN), a novel optimization framework that is designed to reduce the operation cost using the cross-technology communication (CTC). LOC-LPWAN allows roadside sensors to offload sensor data to passing vehicles that in turn forward the data to a LPWAN server using CTC aiming to reduce the data subscription cost. LOC-LPWAN finds the optimal communication schedule between sensors and vehicles to maximize the throughput given an available budget. Furthermore, LOC-LPWAN optimizes the fairness among sensors by preventing certain sensors from dominating the channel for data transmission. LOC-LPWAN can also be configured to ensure that data packets are received within a specific time bound. Extensive numerical analysis performed with real-world taxi data consisting of 40 vehicles with 24-hour trajectories demonstrate that LOC-LPWAN reduces the cost by 50% compared with the baseline approach where no vehicle is used to relay packets. The results also show that LOC-LPWAN improves the throughput by 72.6%, enhances the fairness by 65.7%, and reduces the delay by 28.8% compared with a greedy algorithm given the same amount of budget.

cs.NI↗

arXiv2021

D-ACC: Dynamic Adaptive Cruise Control for Highways with Ramps Based on Deep Q-Learning

An Adaptive Cruise Control (ACC) system allows vehicles to maintain a desired headway distance to a preceding vehicle automatically. It is increasingly adopted by commercial vehicles. Recent research demonstrates that the effective use of ACC can improve the traffic flow through the adaptation of the headway distance in response to the current traffic conditions. In this paper, we demonstrate that a state-of-the-art intelligent ACC system performs poorly on highways with ramps due to the limitation of the model-based approaches that do not take into account appropriately the traffic dynamics on ramps in determining the optimal headway distance. We then propose a dynamic adaptive cruise control system (D-ACC) based on deep reinforcement learning that adapts the headway distance effectively according to dynamically changing traffic conditions for both the main road and ramp to optimize the traffic flow. Extensive simulations are performed with a combination of a traffic simulator (SUMO) and vehicle-to-everything communication (V2X) network simulator (Veins) under numerous traffic scenarios. We demonstrate that D-ACC improves the traffic flow by up to 70% compared with a state-of-the-art intelligent ACC system in a highway segment with a ramp.

cs.CY↗

arXiv2021

Characterizing Power Consumption of Dual-Frequency GNSS of a Smartphone

Location service is one of the most widely used features on a smartphone. More and more apps are built based on location services. As such, demand for accurate positioning is ever higher. Mobile brand Xiaomi has introduced Mi 8, the world's first smartphone equipped with a dual-frequency GNSS chipset which is claimed to provide up to decimeter-level positioning accuracy. Such unprecedentedly high location accuracy brought excitement to industry and academia for navigation research and development of emerging apps. On the other hand, there is a significant knowledge gap on the energy efficiency of smartphones equipped with a dual-frequency GNSS chipset. In this paper, we bridge this knowledge gap by performing an empirical study on power consumption of a dual-frequency GNSS phone. To the best our knowledge, this is the first experimental study that characterizes the power consumption of a smartphone equipped with a dual-frequency GNSS chipset and compares the energy efficiency with a single-frequency GNSS phone. We demonstrate that a smartphone with a dual-frequency GNSS chipset consumes 37% more power on average outdoors, and 28% more power indoors, in comparison with a singe-frequency GNSS phone.

eess.SP↗

arXiv2021

L-Platooning: A Protocol for Managing a Long Platoon with DSRC

Vehicle platooning is an automated driving technology that enables a group of vehicles to travel very closely together as a single unit to improve fuel efficiency and driver safety and reduces CO2 emission. The significant benefits of platooning attracted huge interests from academia and industry, especially from logistics companies for utilizing platoons of "long-body" trailer trucks because of the huge cost savings. In this paper, we demonstrate that existing DSRC-based platooning solutions, however, fail to support formation of such "long" platoons consisting of typical trailer trucks because of the limited communication range of DSRC. To address this problem, we propose L-Platooning, the first platooning protocol that enables seamless, reliable, and rapid formation of a long platoon. We introduce a novel concept called Virtual Leader that refers to a vehicle that acts like a platoon leader to extend the coverage of the original platoon leader. A virtual leader election algorithm is developed to effectively designate a virtual leader based on the novel metric called the Virtual Leader Quality Index (VLQI) which quantifies the effectiveness of a vehicle serving as a platoon leader. We also develop mechanisms for L-Platooning to support the vehicle join and leave maneuvers specifically for a long platoon. Through extensive simulations using the combination of Veins (Plexe) and SUMO, we demonstrate that L-Platooning enables long-body trailer trucks to form a long platoon effectively and maintain the desired inter-vehicle distance precisely. We also show that L-Platooning handles seamlessly the vehicle join and leave maneuvers for a long platoon.

cs.NI↗

arXiv2021

An Experimental Study on Direction Finding of Bluetooth 5.1: Indoor vs Outdoor

The Bluetooth Special Interest Group (Bluetooth SIG) introduced a new feature for highly accurate localization called the Direction Finding in the Bluetooth Core Specification 5.1. Since this new localization feature is relatively new, despite the significant interest of industry and academia in the accurate positioning of Bluetooth devices/tags, there are only a handful of experimental studies conducted to evaluate the performance of the new technology. Furthermore, these experimental works are constrained to only indoor environments or performed with hardware emulation of Bluetooth 5.1 via Universal Software Radio Peripherals (USRPs). In this paper, we perform an experimental study on the positioning accuracy of the direction finding using COTS Bluetooth 5.1 devices in booth indoor and outdoor environments to provide insights on the performance gap under these different experimental settings. Our results demonstrate that the average angular error in an outdoor environment is 0.28 degrees, significantly improving the angular error measured in an indoor environment by 73%. It is also demonstrated that the average positioning accuracy measured in an outdoor environment is 22cm which is 39.7% smaller than that measured in an indoor environment.

cs.NI↗

arXiv2020

Intelligent Traffic Monitoring Systems for Vehicle Classification: A Survey

A traffic monitoring system is an integral part of Intelligent Transportation Systems (ITS). It is one of the critical transportation infrastructures that transportation agencies invest a huge amount of money to collect and analyze the traffic data to better utilize the roadway systems, improve the safety of transportation, and establish future transportation plans. With recent advances in MEMS, machine learning, and wireless communication technologies, numerous innovative traffic monitoring systems have been developed. In this article, we present a review of state-of-the-art traffic monitoring systems focusing on the major functionality--vehicle classification. We organize various vehicle classification systems, examine research issues and technical challenges, and discuss hardware/software design, deployment experience, and system performance of vehicle classification systems. Finally, we discuss a number of critical open problems and future research directions in an aim to provide valuable resources to academia, industry, and government agencies for selecting appropriate technologies for their traffic monitoring applications.

cs.CY↗

arXiv2020

DeepWiTraffic: Low Cost WiFi-Based Traffic Monitoring System Using Deep Learning

A traffic monitoring system (TMS) is an integral part of Intelligent Transportation Systems (ITS). It is an essential tool for traffic analysis and planning. One of the biggest challenges is, however, the high cost especially in covering the huge rural road network. In this paper, we propose to address the problem by developing a novel TMS called DeepWiTraffic. DeepWiTraffic is a low-cost, portable, and non-intrusive solution that is built only with two WiFi transceivers. It exploits the unique WiFi Channel State Information (CSI) of passing vehicles to perform detection and classification of vehicles. Spatial and temporal correlations of CSI amplitude and phase data are identified and analyzed using a machine learning technique to classify vehicles into five different types: motorcycles, passenger vehicles, SUVs, pickup trucks, and large trucks. A large amount of CSI data and ground-truth video data are collected over a month period from a real-world two-lane rural roadway to validate the effectiveness of DeepWiTraffic. The results validate that DeepWiTraffic is an effective TMS with the average detection accuracy of 99.4% and the average classification accuracy of 91.1% in comparison with state-of-the-art non-intrusive TMSs.

cs.CY↗