https://sam.ensam.eu:443 The DSpace digital repository system captures, stores, indexes, preserves, and distributes digital research material. Wed, 16 Sep 2026 09:40:23 GMT 2026-09-16T09:40:23Z http://hdl.handle.net/10985/14236 Speed Profile Optimization for Enhanced Passenger Comfort: An Optimal Control Approach WANG, Yuyang; MERIENNE, Frédéric; CHARDONNET, Jean-Rémy Autonomous vehicles are expected to start reaching the market within the next years. However in practical applications, navigation inside dynamic environments has to take many factors such as speed control, safety and comfort into consideration, which is more paramount for both passengers and pedestrians. In this paper, a novel speed profile planner based on an optimal control approach considering passenger comfort is proposed. The approach is accomplished by minimizing jerk under certain comfort constraints, which inherently gives a speed profile for the central nervous system to follow naturally. Imposed with the same conditions, the widely used Jerk Limitation method is interpreted as an equivalent of the minimum time control method, the latter being used to verify that our method can ensure better continuity and smoothness of the speed profiles. A validation test was specifically designed and performed in order to show the feasibility of our method. Mon, 01 Jan 2018 00:00:00 GMT http://hdl.handle.net/10985/14236 2018-01-01T00:00:00Z WANG, Yuyang MERIENNE, Frédéric CHARDONNET, Jean-Rémy Autonomous vehicles are expected to start reaching the market within the next years. However in practical applications, navigation inside dynamic environments has to take many factors such as speed control, safety and comfort into consideration, which is more paramount for both passengers and pedestrians. In this paper, a novel speed profile planner based on an optimal control approach considering passenger comfort is proposed. The approach is accomplished by minimizing jerk under certain comfort constraints, which inherently gives a speed profile for the central nervous system to follow naturally. Imposed with the same conditions, the widely used Jerk Limitation method is interpreted as an equivalent of the minimum time control method, the latter being used to verify that our method can ensure better continuity and smoothness of the speed profiles. A validation test was specifically designed and performed in order to show the feasibility of our method. http://hdl.handle.net/10985/15255 A Semiautomatic Navigation Interface to Reduce Visually Induced Motion Sickness in Virtual Reality WANG, Yuyang; MERIENNE, Frédéric; CHARDONNET, Jean-Rémy Navigation in a real environment is a common task that human beings conduct easily and subconsciously. However transposing this task in virtual environments (VEs) remains challenging due to input devices and techniques which may induce cybersickness and frustration among users. Considering the well-described sensory conflict theory, we present a semiautomatic navigation method based on path planning algorithms, aiming at reducing the generation of conflicted signals that may confuse the central nervous system (CNS). We carried out experiments where participants were asked to navigate in a VE equipped with an HTC Vive headset. Compared to joystick-based navigation which induces unsmoother and jerkier movements in VEs, objective and subjective evaluations indicated that semiautomatic navigation was more effective and accurate and enabled more concentration and immersion, leading to a significant reduction of visually-induced cybersickness. Mon, 01 Jan 2018 00:00:00 GMT http://hdl.handle.net/10985/15255 2018-01-01T00:00:00Z WANG, Yuyang MERIENNE, Frédéric CHARDONNET, Jean-Rémy Navigation in a real environment is a common task that human beings conduct easily and subconsciously. However transposing this task in virtual environments (VEs) remains challenging due to input devices and techniques which may induce cybersickness and frustration among users. Considering the well-described sensory conflict theory, we present a semiautomatic navigation method based on path planning algorithms, aiming at reducing the generation of conflicted signals that may confuse the central nervous system (CNS). We carried out experiments where participants were asked to navigate in a VE equipped with an HTC Vive headset. Compared to joystick-based navigation which induces unsmoother and jerkier movements in VEs, objective and subjective evaluations indicated that semiautomatic navigation was more effective and accurate and enabled more concentration and immersion, leading to a significant reduction of visually-induced cybersickness. http://hdl.handle.net/10985/16819 CBCRS: An open case-based color recommendation system HONG, Yan; ZENG, Xianyi; WANG, Yuyang; BRUNIAUX, Pascal; CHEN, Yan In this paper, a case-based color recommendation system (CBCRS) is proposed for online color ranges (CRs) recommendation. This system can help designers and consumers to obtain the most appropriate CR of consumer-products (e.g., garments, cars, architecture, furniture …) based on the color image perceptual data of each specific user. The proposed system is an open system, permitting to dynamically integrate new CRs by progressively learning from users’ and designers’ perceptual data. For this purpose, a Color Image Space (CIS) is initially established by using Basic Color Sensory Attributes (BCSAs) to obtain the color image perceptual data of both designers and consumers. Emotional Color Image Words (CIWs) representing CRs are measured in the proposed CIS through a knowledge-based Kansei evaluation process performed by designers using fuzzy aggregation operators and fuzzy similarity measurement tools. Using this method, new CIWs and related CRs from open resources (such as new color trends) can be integrated into the system. In a new recommendation, user's color image perceptual data measured in the proposed CIS regarding different BCSAs will be compared with those of CIWs previously defined in the system in order to recommend new CRs. CBCRS is an adaptive system, i.e. satisfied CRs will be further retained in a Successful Cases Database (SCD) so as to adapt recommended CRs to new consumers, who have similar user profiles. The general working process of the proposed system is based on case-based learning. Through repeated interactions with the proposed system by performing the cycle of Recommendation – Display - Evaluation – SCD adjustment, users (consumer or designer) will obtain satisfied CRs. Meanwhile, the quality of the SCD can be improved by integrating new recommendation cases. The proposed recommendation system is capable of dynamically generating new CIWs, CRs and new cases based on open resources. Mon, 01 Jan 2018 00:00:00 GMT http://hdl.handle.net/10985/16819 2018-01-01T00:00:00Z HONG, Yan ZENG, Xianyi WANG, Yuyang BRUNIAUX, Pascal CHEN, Yan In this paper, a case-based color recommendation system (CBCRS) is proposed for online color ranges (CRs) recommendation. This system can help designers and consumers to obtain the most appropriate CR of consumer-products (e.g., garments, cars, architecture, furniture …) based on the color image perceptual data of each specific user. The proposed system is an open system, permitting to dynamically integrate new CRs by progressively learning from users’ and designers’ perceptual data. For this purpose, a Color Image Space (CIS) is initially established by using Basic Color Sensory Attributes (BCSAs) to obtain the color image perceptual data of both designers and consumers. Emotional Color Image Words (CIWs) representing CRs are measured in the proposed CIS through a knowledge-based Kansei evaluation process performed by designers using fuzzy aggregation operators and fuzzy similarity measurement tools. Using this method, new CIWs and related CRs from open resources (such as new color trends) can be integrated into the system. In a new recommendation, user's color image perceptual data measured in the proposed CIS regarding different BCSAs will be compared with those of CIWs previously defined in the system in order to recommend new CRs. CBCRS is an adaptive system, i.e. satisfied CRs will be further retained in a Successful Cases Database (SCD) so as to adapt recommended CRs to new consumers, who have similar user profiles. The general working process of the proposed system is based on case-based learning. Through repeated interactions with the proposed system by performing the cycle of Recommendation – Display - Evaluation – SCD adjustment, users (consumer or designer) will obtain satisfied CRs. Meanwhile, the quality of the SCD can be improved by integrating new recommendation cases. The proposed recommendation system is capable of dynamically generating new CIWs, CRs and new cases based on open resources. http://hdl.handle.net/10985/16255 Design of a Semiautomatic Travel Technique in VR Environments WANG, Yuyang; MERIENNE, Frédéric; CHARDONNET, Jean-Rémy Travel in a real environment is a common task that human beings conduct easily and subconsciously. However transposing this task in virtual environments (VEs) remains challenging due to input devices and techniques. Considering the well-described sensory conflict theory, we present a semiautomatic travel method based on path planning algorithms and gaze-directed control, aiming at reducing the generation of conflicted signals that may confuse the central nervous system. Since gaze-directed control is user-centered and path planning is goal-oriented, our semiautomatic technique makes up for the deficiencies of each with smoother and less jerky trajectories. Tue, 01 Jan 2019 00:00:00 GMT http://hdl.handle.net/10985/16255 2019-01-01T00:00:00Z WANG, Yuyang MERIENNE, Frédéric CHARDONNET, Jean-Rémy Travel in a real environment is a common task that human beings conduct easily and subconsciously. However transposing this task in virtual environments (VEs) remains challenging due to input devices and techniques. Considering the well-described sensory conflict theory, we present a semiautomatic travel method based on path planning algorithms and gaze-directed control, aiming at reducing the generation of conflicted signals that may confuse the central nervous system. Since gaze-directed control is user-centered and path planning is goal-oriented, our semiautomatic technique makes up for the deficiencies of each with smoother and less jerky trajectories. http://hdl.handle.net/10985/16276 VR Sickness Prediction for Navigation in Immersive Virtual Environments using a Deep Long Short Term Memory Model WANG, Yuyang; MERIENNE, Frédéric; CHARDONNET, Jean-Rémy This paper proposes a new objective metric of visually induced motion sickness (VIMS) in the context of navigation in virtual environments (VEs). Similar to motion sickness in physical environments, VIMS can induce many physiological symptoms such as general discomfort, nausea, disorientation, vomiting, dizziness and fatigue. To improve user satisfaction with VR applications, it is of great significance to develop objective metrics for VIMS that can analyze and estimate the level of VR sickness when a user is exposed to VEs. One of the well-known objective metrics is the postural instability. In this paper, we trained a LSTM model for each participant using a normal-state postural signal captured before the exposure, and if the postural sway signal from post-exposure was sufficiently different from the pre-exposure signal, the model would fail at encoding and decoding the signal properly; the jump in the reconstruction error was called loss and was proposed as the proposed objective measure of simulator sickness. The effectiveness of the proposed metric was analyzed and compared with subjective assessment methods based on the simulator sickness questionnaire (SSQ) in a VR environment, achieving a Pearson correlation coefficient of .89. Finally, we showed that the proposed method had the potential to be deployed within a closed-loop system and get real-time performance to predict VR sickness, opening new insights to develop user-centered and customized VR applications based on physiological feedback. Tue, 01 Jan 2019 00:00:00 GMT http://hdl.handle.net/10985/16276 2019-01-01T00:00:00Z WANG, Yuyang MERIENNE, Frédéric CHARDONNET, Jean-Rémy This paper proposes a new objective metric of visually induced motion sickness (VIMS) in the context of navigation in virtual environments (VEs). Similar to motion sickness in physical environments, VIMS can induce many physiological symptoms such as general discomfort, nausea, disorientation, vomiting, dizziness and fatigue. To improve user satisfaction with VR applications, it is of great significance to develop objective metrics for VIMS that can analyze and estimate the level of VR sickness when a user is exposed to VEs. One of the well-known objective metrics is the postural instability. In this paper, we trained a LSTM model for each participant using a normal-state postural signal captured before the exposure, and if the postural sway signal from post-exposure was sufficiently different from the pre-exposure signal, the model would fail at encoding and decoding the signal properly; the jump in the reconstruction error was called loss and was proposed as the proposed objective measure of simulator sickness. The effectiveness of the proposed metric was analyzed and compared with subjective assessment methods based on the simulator sickness questionnaire (SSQ) in a VR environment, achieving a Pearson correlation coefficient of .89. Finally, we showed that the proposed method had the potential to be deployed within a closed-loop system and get real-time performance to predict VR sickness, opening new insights to develop user-centered and customized VR applications based on physiological feedback. http://hdl.handle.net/10985/17242 Knowledge-Based Open Performance Measurement System (KBO-PMS) for a Garment Product Development Process in Big Data Environment HONG, Yan; WU, Tianyu; ZENG, Xianyi; WANG, Yuyang; YANG, Wen; PAN, Zhijuan Globally, customers are getting increasingly demanding in terms of personalization of products and are asking for shorter product development periods with more predictable product performance, especially in fashion industry. Current market pressures drive firms to adapt new design process in product development (PD) processes. Nevertheless, choosing the effective PD process is a challenging, complex decision. There is a critical need to develop a performance measurements system (PMS) for choosing appropriate product development (PD) processes in garment design to support product mangers to effectively respond to market. This paper presents a knowledge-based open performance measurement system (KBO-PMS) in big data environment, in order to support complex industrial decision-making for new product development. Its dynamic and flexible structure enables the whole system to be more adapted to knowledge sharing of product managers and processing of various time-varying data. The proposed KBO-PMS is composed of an interactive structure, capable of both integrating new KPIs from the open resource and tracking the evolution of the KBO-PMS components with time. The proposed KBO-PMS has been validated by realizing the performance evaluation of product development (PD) in fashion industry. It can be regarded as an application of open-resource based dynamic group decision-making in fashion big data environment. Tue, 01 Jan 2019 00:00:00 GMT http://hdl.handle.net/10985/17242 2019-01-01T00:00:00Z HONG, Yan WU, Tianyu ZENG, Xianyi WANG, Yuyang YANG, Wen PAN, Zhijuan Globally, customers are getting increasingly demanding in terms of personalization of products and are asking for shorter product development periods with more predictable product performance, especially in fashion industry. Current market pressures drive firms to adapt new design process in product development (PD) processes. Nevertheless, choosing the effective PD process is a challenging, complex decision. There is a critical need to develop a performance measurements system (PMS) for choosing appropriate product development (PD) processes in garment design to support product mangers to effectively respond to market. This paper presents a knowledge-based open performance measurement system (KBO-PMS) in big data environment, in order to support complex industrial decision-making for new product development. Its dynamic and flexible structure enables the whole system to be more adapted to knowledge sharing of product managers and processing of various time-varying data. The proposed KBO-PMS is composed of an interactive structure, capable of both integrating new KPIs from the open resource and tracking the evolution of the KBO-PMS components with time. The proposed KBO-PMS has been validated by realizing the performance evaluation of product development (PD) in fashion industry. It can be regarded as an application of open-resource based dynamic group decision-making in fashion big data environment. http://hdl.handle.net/10985/25246 IEEE VR 2023 Workshop: Datasets for developing intelligent XR applications (DATA4XR) WANG, Yuyang; CHARDONNET, Jean-Rémy; LEE, Lik-Hang; HUI, Pan The 2nd workshop on Datasets for Developing Intelligent XR Applications (DATA4XR) aims to address the challenges of public datasets and reproducibility in Extended Reality, also known as XR (Augmented Reality, Virtual Reality, and Mixed Reality) research. The workshop brings together experts to discuss the availability, privacy concerns, and ethics related to open-sourcing the datasets used in XR research for algorithm training and user behavior analysis. By examining the ethical, moral, and privacy concerns. Sun, 26 Mar 2023 00:00:00 GMT http://hdl.handle.net/10985/25246 2023-03-26T00:00:00Z WANG, Yuyang CHARDONNET, Jean-Rémy LEE, Lik-Hang HUI, Pan The 2nd workshop on Datasets for Developing Intelligent XR Applications (DATA4XR) aims to address the challenges of public datasets and reproducibility in Extended Reality, also known as XR (Augmented Reality, Virtual Reality, and Mixed Reality) research. The workshop brings together experts to discuss the availability, privacy concerns, and ethics related to open-sourcing the datasets used in XR research for algorithm training and user behavior analysis. By examining the ethical, moral, and privacy concerns. http://hdl.handle.net/10985/20097 Using Fuzzy Logic to Involve Individual Differences for Predicting Cybersickness during VR Navigation WANG, Yuyang; OVTCHAROVA, Jivka; MERIENNE, Frédéric; CHARDONNET, Jean-Rémy Many studies have explored how individual differences can affect users’ susceptibility to cybersickness in a VR application. However, the lack of strategy to integrate the influence of each factor on cybersickness makes it difficult to utilize the results of existing research. Based on the fuzzy logic theory that can represent the effect of different factors as a single value containing integrated information, we developed two approaches including the knowledge-based Mamdani-type fuzzy inference system and the data-driven Adaptive neuro-fuzzy inference system (ANFIS) to involve three individual differences (Age, Gaming experience and Ethnicity). We correlated the corresponding outputs with the simulator sickness questionnaire (SSQ) scores in a simple navigation scenario. The correlation coefficients obtained through a 4-fold cross validation were found statistically significant with both fuzzy logic approaches, indicating their effectiveness to influence the occurrence and the level of cybersickness. Our work provides insights to establish customized experiences for VR navigation by involving individual differences. Fri, 01 Jan 2021 00:00:00 GMT http://hdl.handle.net/10985/20097 2021-01-01T00:00:00Z WANG, Yuyang OVTCHAROVA, Jivka MERIENNE, Frédéric CHARDONNET, Jean-Rémy Many studies have explored how individual differences can affect users’ susceptibility to cybersickness in a VR application. However, the lack of strategy to integrate the influence of each factor on cybersickness makes it difficult to utilize the results of existing research. Based on the fuzzy logic theory that can represent the effect of different factors as a single value containing integrated information, we developed two approaches including the knowledge-based Mamdani-type fuzzy inference system and the data-driven Adaptive neuro-fuzzy inference system (ANFIS) to involve three individual differences (Age, Gaming experience and Ethnicity). We correlated the corresponding outputs with the simulator sickness questionnaire (SSQ) scores in a simple navigation scenario. The correlation coefficients obtained through a 4-fold cross validation were found statistically significant with both fuzzy logic approaches, indicating their effectiveness to influence the occurrence and the level of cybersickness. Our work provides insights to establish customized experiences for VR navigation by involving individual differences. http://hdl.handle.net/10985/19784 Enhanced cognitive workload evaluation in 3D immersive environments with TOPSIS model WANG, Yuyang; MERIENNE, Frédéric; CHARDONNET, Jean-Rémy Research puts forward perception-based cognitive workload evaluation methods to help VR developers and users measuring their workload when playing with a VR application. Approaches to measure workload based on biosensors have progressed significantly, while evaluation based on subjective methods still rely on standard questionnaires such as the NASA-TLX table, the Subjective Workload Assessment Technique and the Modified Cooper Harper scale. The pre-defined questions enable operators to carry out experiments and analyse the data more easily than with biofeedback. However, the subjective evaluation process can bias the results because of unperceived internal changes and unknown factors among users. It is therefore necessary to have a method to handle and analyse this uncertainty. We propose to use the Technique for Order Performance by Similarity to Ideal Solution (TOPSIS) model to analyse the NASA-TLX table for measuring the overall user workload instead of using the classical weighted sum method. To show the advantage of the TOPSIS approach, we performed a user experiment to validate the approach and its application to VR, considering factors including the VR platform and the scenario density. Three different weighting methods, including the fuzzy Analytic Hierarchy Process (AHP) from fuzzy logic, the classical weighting based on pairwise comparison and the uniform weighting method, were tested to see the applicability of the TOPSIS model. The results from TOPSIS were consistent with those from other evaluation methods; a significant reduction in the coefficient of variation (CV) was observed when using the TOPSIS model to analyse the NASA-TLX scores, indicating an enhanced precision of the workload evaluation by the TOPSIS method. Our work has a potential application for VR designers and experimenters to compare cognitive workload among conditions and to optimize the settings. Fri, 01 Jan 2021 00:00:00 GMT http://hdl.handle.net/10985/19784 2021-01-01T00:00:00Z WANG, Yuyang MERIENNE, Frédéric CHARDONNET, Jean-Rémy Research puts forward perception-based cognitive workload evaluation methods to help VR developers and users measuring their workload when playing with a VR application. Approaches to measure workload based on biosensors have progressed significantly, while evaluation based on subjective methods still rely on standard questionnaires such as the NASA-TLX table, the Subjective Workload Assessment Technique and the Modified Cooper Harper scale. The pre-defined questions enable operators to carry out experiments and analyse the data more easily than with biofeedback. However, the subjective evaluation process can bias the results because of unperceived internal changes and unknown factors among users. It is therefore necessary to have a method to handle and analyse this uncertainty. We propose to use the Technique for Order Performance by Similarity to Ideal Solution (TOPSIS) model to analyse the NASA-TLX table for measuring the overall user workload instead of using the classical weighted sum method. To show the advantage of the TOPSIS approach, we performed a user experiment to validate the approach and its application to VR, considering factors including the VR platform and the scenario density. Three different weighting methods, including the fuzzy Analytic Hierarchy Process (AHP) from fuzzy logic, the classical weighting based on pairwise comparison and the uniform weighting method, were tested to see the applicability of the TOPSIS model. The results from TOPSIS were consistent with those from other evaluation methods; a significant reduction in the coefficient of variation (CV) was observed when using the TOPSIS model to analyse the NASA-TLX scores, indicating an enhanced precision of the workload evaluation by the TOPSIS method. Our work has a potential application for VR designers and experimenters to compare cognitive workload among conditions and to optimize the settings. http://hdl.handle.net/10985/24566 A Deep Cybersickness Predictor through Kinematic Data with Encoded Physiological Representation LI, Ruichen; WANG, Yuyang; YIN, Handi; CHARDONNET, Jean-Rémy; HUI, Pan Users would experience individually different sickness symptoms during or after navigating through an immersive virtual environment, generally known as cybersickness. Previous studies have predicted the severity of cybersickness based on physiological and/or kinematic data. However, compared with kinematic data, physiological data rely heavily on biosensors during the collection, which is inconvenient and limited to a few affordable VR devices. In this work, we proposed a deep neural network to predict cybersickness through kinematic data. We introduced the encoded physiological representation to characterize the individual susceptibility; therefore, the predictor could predict cybersickness only based on a user’s kinematic data without counting on biosensors. Fifty-three participants were recruited to attend the user study to collect multimodal data, including kinematic data (navigation speed, head tracking), physiological signals (e.g., electrodermal activity, heart rate), and Simulator Sickness Questionnaire (SSQ). The predictor achieved an accuracy of 97.8% for cybersickness prediction by involving the pre-computed physiological representation to characterize individual differences, providing much convenience for the current cybersickness measurement. Mon, 16 Oct 2023 00:00:00 GMT http://hdl.handle.net/10985/24566 2023-10-16T00:00:00Z LI, Ruichen WANG, Yuyang YIN, Handi CHARDONNET, Jean-Rémy HUI, Pan Users would experience individually different sickness symptoms during or after navigating through an immersive virtual environment, generally known as cybersickness. Previous studies have predicted the severity of cybersickness based on physiological and/or kinematic data. However, compared with kinematic data, physiological data rely heavily on biosensors during the collection, which is inconvenient and limited to a few affordable VR devices. In this work, we proposed a deep neural network to predict cybersickness through kinematic data. We introduced the encoded physiological representation to characterize the individual susceptibility; therefore, the predictor could predict cybersickness only based on a user’s kinematic data without counting on biosensors. Fifty-three participants were recruited to attend the user study to collect multimodal data, including kinematic data (navigation speed, head tracking), physiological signals (e.g., electrodermal activity, heart rate), and Simulator Sickness Questionnaire (SSQ). The predictor achieved an accuracy of 97.8% for cybersickness prediction by involving the pre-computed physiological representation to characterize individual differences, providing much convenience for the current cybersickness measurement.