Real-time monitoring of mental workload (MWL) is critical for designing adaptive human-machine systems. This study introduces a subject-independent EEG classifier trained on spectral power ratios (delta, theta, alpha, beta) from frontal, parietal, and occipital regions. Using a controlled arithmetic task with labeled difficulty levels (easy/hard), a Gaussian Naive Bayes model achieved 75.4% accuracy (LOSOCV) in distinguishing MWL states. Validated in a driving simulator, the model detected higher MWL in urban (overload) vs. rural (underload) scenarios (p < 0.05), aligning with NASA-TLX subjective ratings. Temporal analysis revealed declining MWL over time, reflecting cognitive adaptation, followed by a fatigue-driven rise in prolonged overload tasks. The framework eliminates the need for individualized calibration, offering a scalable solution for real-world applications like automotive safety and virtual reality. By bridging controlled lab settings and naturalistic environments, this work advances EEG-based MWL monitoring for adaptive systems in high-stakes domains like driving and aviation.

Remote driving, as a backup system for automated vehicles, can play a vital role in their commercialization. However, delay is one of the major challenges in the practical application of remote driving. It not only degrades the stability of remote driven vehicles (RDVs) but also introduces delayed driving feedback, such as motion cueing feedback, to remote drivers. This can result in an unpleasant driving experience. This study proposes a square root cubature Kalman filter-based predictor (SRCKP) to compensate for driving feedback delays in remote driving. The SRCKP reduces the limitations of both model-based and model-free predictors (MFPs). Additionally, this article presents an overshoot compensator to address the overshoot problem associated with traditional MFPs. Furthermore, a packet loss predictor (PLP) is designed to mitigate the influence of packet loss during data transmission. Both simulation and hardware-in-the-loop (HIL) experiments during comprehensive driving scenarios are conducted to verify the effectiveness and robustness of the proposed method. The findings indicate that, compared with MFPs, the SRCKP reduces the L₂-norm error by up to 81.2% in simulations and by up to 54.0% in HIL experiments for the best-case conditions.

Remote driving has appeared as an effective solution to address challenges in achieving full autonomy for vehicles, bridging the gap between Level 4 and Level 5autonomy. Beyond autonomous vehicles (AVs), remote driving can be widely applied in various industries, such as mining, timber cutting, and warehouse logistics, where it can enhance safety, efficiency, and operational reliability. Despite its advantages, remote driving faces significant challenges, including latency, and reduced situational awareness, which impact remote drivers’ performance and experience. This thesis delves into these challenges and investigates solutions to enhance teleoperated driving systems, focusing on user experience, driving feedback and delay compensation.

The research is structured around six research questions, examining the influence of driving feedback on driving behavior and user experience, and strategies to mitigate latency in remote driving and its influence on remote drivers, as well as the learning rate of remote drivers. An integrated approach including quantitative and qualitative analysis is employed, combining experimental studies on areal-life remote driving platform and hardware-in-the-loop (HIL) simulations using IPG CarMaker. Comprehensive experiments evaluate the impact of steering force, motion-cueing, and sound and vibration feedback on driving behavior and experience. Additionally, innovative delay compensation strategies, including an enhanced model-free predictor and a square-root cubature Kalman filter-based predictor, are developed and validated to address signal transmission challenges. Finally, the learning rate of remote drivers under the delayed environment are also explored on a driving simulator.

The research results demonstrate that integrating multimodal driving feedback, such as steering force, motion-cueing, sound, and vibration, can substantially enhance remote drivers’ situational awareness and perceived confidence. However, delays in these feedback channels, particularly motion cues, are found to degrade driving precision and control stability. These challenges highlight the need for more robust delay compensation strategies. In response, a square-root cubature Kalman filter-based predictor is developed, significantly outperforming conventional approaches by maintaining accurate state prediction under latency. It is also found that remote drivers can be used for a certain driving task after 4–5 training rounds in delayed scenarios, suggesting a low adaptation threshold. These findings not only validate the technical feasibility of the proposed methods but also offer practical advantages in deploying scalable, operator-friendly remote driving systems in dynamic, real-world environments.

While the experiments provide meaningful results, certain limitations exist, including the use of a single 4G SIM card for communication and controlled testing environments. Future studies could explore dual-carrier 5G setups and advanced feedback systems to further enhance remote driving platforms.

Overall, this research contributes to the growing field of remote driving by addressing critical challenges and proposing actionable solutions, paving the way for safer, more efficient, and scalable remote driving systems across diverse applications.

Fjärrstyrd körning av fordon  har framträtt som en effektiv lösning för att hantera utmaningarna med att uppnå fullständigt självkörande fordon och överbrygga gapet mellan  nivå 4 och nivå 5  i graden av självkörande. Utöver självkörande fordon (AV) kan fjärrstyrning användas  brett inom olika industrier, såsom gruvdrift, skogsavverkning och lagerlogistik, där det kan förbättra säkerheten, effektiviteten och driftsäkerheten. Trots dess fördelar står fjärrstyrd körning inför betydande utmaningar, såsom latens och minskad situationsmedvetenhet, vilket påverkar fjärrförarnas prestation och upplevelse. Denna avhandling undersöker dessa utmaningar och utforskar lösningar för att förbättra fjärrstyrda körsystem med fokus på användarupplevelse, föraråterkoppling och fördröjningskompensation.

Forskningen struktureras kring sex forskningsfrågor, där man undersöker föraråterkopplingens påverkan på körbeteendet och användarupplevelsen, strategier för att mildra latens vid fjärrstyrd körning samt dess effekt på fjärrförare och fjärrförarnas anpassningsförmåga. Kombinerade metoder  används vilket  inkluderar experimentella studier på en verklig plattform för fjärrstyrning, "hardware-in-the-loop" (HIL) med IPG CarMaker, samt kvantitativa och kvalitativa användarenkäter. Omfattande experiment utvärderar effekten av styrkraft, rörelseåterkoppling samt ljud- och vibrationsåterkoppling på körbeteende och upplevelse. Dessutom utvecklas och valideras innovativa strategier för fördröjningskompensation, däribland en förbättrad modellfri kompensator och en kompensator baserad på en kvadratrot-kubatur-Kalmanfilter, för att hantera utmaningar vid signalöverföring. Slutligen undersöks även fjärrförarnas anpassningsförmåga under fördröjda förhållanden med hjälp av en  körsimulator.

Forskningsresultaten visar att integrering av multimodal föraråterkoppling – såsom styrkraft, rörelseåterkoppling, ljud och vibrationer – avsevärt stärker fjärrförarnas situationsmedvetenhet och upplevda trygghet. Studien utgör ett tidigt empiriskt bidrag som kvantifierar dessa effekter med hjälp av både subjektiva och objektiva mått i en realistisk fjärrkörningsmiljö. Den föreslagna prediktionsmodellen, baserad på kvadratrot-kubatur-Kalmanfilter, uppvisar betydligt högre robusthet och noggrannhet jämfört med konventionella metoder under varierande fördröjningsförhållanden. Studien visar också att fjärrförare kan bli van ett specifikt köruppdrag  efter endast 4–5 träningsomgångar i nya scenarier med fördröjning, vilket tyder på en låg inlärningströskel. Sammantaget bekräftar resultaten metodernas tekniska genomförbarhet och pekar på praktiska fördelar vid implementering av skalbara och användarvänliga fjärrkörningssystem i dynamiska, verkliga miljöer.

Även om experimenten ger meningsfulla resultat finns vissa begränsningar, såsom användningen av ett enda 4G SIM-kort för kommunikation och kontrollerade testmiljöer. Framtida studier kan utforska lösningar med dubbla operatörer och avancerade återkopplingssystem för att ytterligare förbättra plattformar för fjärrstyrning. 

Sammantaget bidrar denna forskning till det växande området för fjärrstyrd körning genom att hantera kritiska utmaningar och föreslå konkreta lösningar, vilket banar väg för säkrare, effektivare och mer skalbara system för fjärrstyrning inom olika tillämpningar.

Remote operation of highly automated vehicles (HAVs) may include occasional assistance from a human remote operator that is located outside the HAVs. Remote assistance typically delegates only high-level guidance tasks to the remote operators such as authorizing a driving maneuver or specifying a new driving path. As remote assistance is fairly unexplored, there are still several research challenges. These challenges were discussed by experts from academia and industry in a multidisciplinary workshop at the 2023 IEEE Intelligent Vehicles Symposium. As a result of the workshop, this paper presents a list of most pressing research questions in the following areas: human-machine interaction and human factors, design of the remote station, design of the HAVs. It also outlines a roadmap for future research on remote assistance of HAV, thereby informing interdisciplinary studies and facilitating the benefits of HAVs before full autonomy can be reached.

The steer-by-wire (SbW) system is seen as the next generation of vehicle steering system. However, there is a possibility of system failure, and it is not yet clear how failure modes will impact driving behaviour. This work studies the impact of different SbW failure modes on driving safety. Firstly, potential failure modes in the SbW system were identified with the help of a hazard and operability (HAZOP) study. Secondly, a physical model based steering force feedback, with the possibility to simulate the failure modes, was implemented in Matlab/Simulink. Third, two test scenarios were constructed, including driving on a country road at 70 km/h and driving on a highway at 110 km/h. Additionally, a driver-in-the-loop experiment was performed using a stationary driving simulator, where subjective and objective data was collected. Then, in terms of result analysis, both subjective and objective evaluation methods were used for severity assessment. Finally, the result of the severity analysis in the form of yaw rate is shown.

Remote driving plays an essential role in coordinating automated vehicles in some challenging situations. Due to the changed driving environment, the experiences and behaviors of remote drivers would undergo some changes compared to conventional drivers. To study this, a continuous real-life and remote driving experiment is conducted under different driving conditions. In addition, the effect of steering force feedback (SFF) on the driving experience is also investigated. In order to achieve this, three types of SFF modes are compared. According to the results, no SFF significantly worsens the driving experience in both remote and real-life driving. Additionally, less force and returnability on steering wheel are needed in remote driving, and the steering force amplitude appears to influence the steering velocity of remote drivers. Furthermore, there is an increase in lane following deviation during remote driving. Remote drivers are also prone to driving at lower speeds and have a higher steering reversal rate. They also give larger steering angle inputs when crossing the cones in a slalom manoeuvre and cause the car to experience larger lateral acceleration. These findings provide indications on how to design SFF and how driving behavior and experience change in remote driving.

Remote driving plays a vital role in coordinating automated vehicles in challenging situations. Data transmission latency, however, can cause several problems in remote driving. Firstly, it can degrade the performance of remote-controlled vehicles, evident in issues like lane-following deviation and vehicle stability. Additionally, the remote control tower's driving feedback is affected by delayed vehicle signals, leading to delayed driving experience. To address this, a model-free-based predictor is employed to compensate for the delay in remote driving. This approach does not require any dynamic model of the system and only needs tuning of two parameters to reduce communication delay. This study enhances the previous work by mitigating the amplitude of overshoot around peak points. It leverages the principle of the second-order derivative to predict the signal's peak time and uses it to address the predictor's overshoot issue. The effectiveness of the proposed method is validated using real car data from multiple participants in two scenarios, including Slalom and lane-following. Simulation results indicate that the proposed method can reduce prediction error by nearly 25% compared to previous works. Moreover, the solutions in this study are capable of managing not only delays in remote driving vehicles but also in traditional mechanical systems, such as CAN bus delays in conventional cars.

Driving feedback is an important way of providing remote drivers with physical world information during teleoperation. In this study, a teleoperation experiment is conducted to explore how sound, vibration and motion-cueing feedback influence the drivers’ driving experience and behaviour. To this end, four types of driving feedback modes are used as variables to investigate this, including no feedback, motion-cueing feedback, sound and vibration feedback, and a combination of sound, vibration, and motion-cueing feedback. A prototype of teleoperation platform is first built, which includes a teleoperated vehicle and a driving station capable of generating sound, vibration, and motion-cueing feedback. Then, the scenario with disturbances is built to investigate how the driving behaviour changes under various driving feedback modes. Both subjective and objective assessments are used in this study. For driving experience, the driving feeling, such as presence feeling, road surface feeling, etc, are explored. For driving behaviour, the throttle reversal rate is investigated. Furthermore, the relationship between throttle reversal rate and driving experience is studied. The results show that the combined feedback mode could provide drivers with the highest rated driving experience; the motion-cueing feedback could provide better road surface feeling while the sound and vibration feedback could provide better speed feeling. The throttle reversal rate with motion-cueing feedback is higher than without it, which may be caused by the increased road surface feeling provided by motion cues.

Teleoperation is considered as a viable option to control fully automated vehicles (AVs) of Level 4 and 5 in special conditions. However, by bringing the remote drivers in the loop, their driving experience should be realistic to secure safe and comfortable remote control. Therefore, the remote control tower should be designed such that remote drivers receive high quality cues regarding the vehicle state and the driving environment. In this direction, the steering feedback could be manipulated to provide feedback to the remote drivers regarding how the vehicle reacts to their commands. However, until now, it is unclear how the remote drivers' steering feel could impact occupant's motion comfort. This paper focuses on exploring how the driver feel in remote (RD) and normal driving (ND) are related with occupants' motion comfort. More specifically, different types of steering feedback controllers are applied in (a) the steering system of a Research Concept Vehicle-model E (RCV-E) and (b) the steering system of a remote control tower. An experiment was performed to assess driver feel when the RCV-E is normally and remotely driven. Subjective assessment and objective metrics are employed to assess drivers' feel and occupants' motion comfort in both remote and normal driving scenarios. The results illustrate that motion sickness and ride comfort are dominated by steering velocity variations in remote driving, while throttle input variations dominate in normal driving. The results demonstrate that motion sickness and steering velocity increase both around 25% from normal to remote driving.

This literature survey explores the domain of remote driving of road vehicles within autonomous vehicles, focusing on challenges and state-of-the-art solutions related to driving feedback, latency, support control, as well as remote driving platform and real applications. The advancement towards Level-5 autonomy faces challenges, including sensor reliability and diverse scenario feasibility. Currently, remote driving is identified as vital for commercialization, however, it comes with challenges like low situational awareness, latency, and a lack of comprehensive feedback mechanisms. Solutions proposed include enhancing visual feedback, developing haptic feedback, employing prediction techniques, and use control methods to support driver. This paper reviews the existing literature on remote driving in these fields, revealing research gaps and areas for future studies. Additionally, this paper reviews the industry applications of remote driving and shows the state-of-art use cases.