Virtual testing platform for predicting a specific cognitive-affective state of an individual.

Abstract

A virtual testing platform for predicting a specific cognitive-affective state of an individual comprises a simulated environment generator that creates a computer-generated environment representing a workspace seen by the individual, within which the individual must perform an assigned task. The virtual testing platform also includes at least one of the following: one or more physiological sensors that monitor physiological measurements of the individual, and an input device that receives user input generated by the individual, whereby the individual answers one or more survey questions either during or after performing the assigned task via the input device.The virtual test platform includes one or more control units that are in electronic communication with the generator for a simulated environment, the one or more physiological sensors, and the input device.

Description

introduction

[0001] The present description refers to a virtual testing platform for predicting a specific cognitive-affective state of an individual while the individual performs an assigned task in a workspace generated by a generator for a simulated environment.

[0002] Currently, there are various platforms for augmented and virtual reality that can be used in a wide range of applications. Augmented reality is an interactive experience in which a live view of a real-world environment is enhanced with computer-generated perceptual information such as graphics, video, and sound. In contrast, virtual reality is an immersive experience in which a real-world environment is completely replaced by a simulated one.

[0003] Some existing augmented and virtual reality platforms are designed to train and familiarize an individual with an assigned task or technologies related to applications such as, but not limited to, games, sports, and medical treatments. However, these existing platforms do not assess the individual's cognitive and affective state while performing the assigned task. Instead, the current approach to determining an individual's cognitive and affective state while performing an assigned task involves creating a real-world, physical testing platform. Clearly, building or creating such a physical testing platform can be time-consuming, requires numerous resources, and often necessitates various modifications to test different types of use cases and user profiles.

[0004] While current approaches to determining an individual's cognitive-affective state while performing an assigned task fulfill their intended purpose, there is a need for an improved approach to determining an individual's cognitive-affective state while performing the assigned task. Description

[0005] According to several aspects, a virtual testing platform for predicting a specific cognitive-affective state of an individual is disclosed. The virtual testing platform includes a simulated environment generator that creates a computer-generated environment representing a workspace perceived by the individual, within which the individual must perform an assigned task. The virtual testing platform also includes at least one of the following: one or more physiological sensors that monitor physiological measurements of the individual, and an input device that receives user input generated by the individual, whereby the individual answers one or more survey questions via the input device either during or after performing the assigned task.The virtual test platform also includes one or more control units that communicate electronically with the simulated environment generator, the one or more physiological sensors, and the input device. The one or more control units include one or more processors that execute instructions to direct the simulated environment generator to create the computer-generated environment that represents the workspace.The one or more control units predict the individual's specific cognitive-affective state when the individual performs the assigned task, generated by the generator for a simulated environment, based on at least one of the following: physiological measurements from the one or more physiological sensors, and user input received by the input device, indicating the individual's responses to one or more survey questions. The one or more control units then formulate one or more recommendations for implementing the workspace in a real-world environment based on the individual's specific cognitive-affective state.

[0006] In another aspect, one or more processors of one or more control units execute instructions to instruct the generator for a simulated environment to modify one or more experimental parameters related to the assigned task within the workspace, whereby the individual must re-execute the assigned task within the workspace when the one or more experimental parameters related to the assigned task are modified.

[0007] In another aspect, the specific cognitive-affective state of the individual is predicted based on one or more survey questions.

[0008] In one aspect, the one or more processors of the one or more control units execute instructions to instruct the generator for a simulated environment to produce computer-generated perceptual information that poses one or more survey questions to the individual each time the one or more experimental parameters within the workspace are modified.

[0009] Another aspect is that the one or more survey questions include a variety of multiple-choice answers, with each multiple-choice answer including a numerical value that represents a strength of the specific cognitive-affective state that the individual is experiencing.

[0010] Another aspect is that one or more survey questions include free text answers.

[0011] In one aspect, the specific cognitive-affective state of the individual is predicted based on physiological measurements recorded by one or more physiological sensors.

[0012] In another aspect, one or more processors of one or more control units execute instructions to further monitor the physiological measurements of the individual, collected by one or more physiological sensors, when one or more experimental parameters are modified.

[0013] Another aspect is that the one or more physiological sensors include one or more of the following: off-body physiological sensors and on-body physiological sensors.

[0014] One aspect is that the remote physiological sensors include one or more of the following: audio sensors, cameras, thermal cameras, body markers, facial markers, pressure mats, and technology tracking sensors.

[0015] Another aspect is that the body-worn physiological sensors include one or more of the following: pressure sensors, galvanic skin response sensors, eye-tracking sensors, electroencephalography (EEG) sensors, electromyography (EMG) sensors, and functional near-infrared spectroscopy (FNIRS) sensors.

[0016] In another aspect, the one or more processors of the one or more control units execute instructions to classify the physiological measurements of the individual into categories that indicate the specific cognitive-affective state of the individual based on signal values ​​generated by the one or more physiological sensors.

[0017] In one aspect, the one or more processors of the one or more control units execute instructions to assign numerical values ​​to signals generated by the one or more physiological sensors, where the numerical values ​​represent the strength of the specific cognitive-affective state and classify numerical values ​​to a base value representing a neutral cognitive-affective state, where the specific cognitive-affective state predicted by the one or more control units is relative to the neutral specific cognitive-affective state.

[0018] In another aspect, the specific cognitive-affective state of the individual is predicted on the basis of both the physiological measurements recorded by one or more physiological sensors and the one or more survey questions.

[0019] In another aspect, one or more processors of one or more control units execute instructions to predict the specific cognitive-affective state of the individual based on a user-defined classification model that is based on a recurrent neural network (RNN) with internal memory.

[0020] In one aspect, the one or more recommendations include value ranges for one or more experimental parameters that result in the individual having a neutral cognitive-affective state while performing the assigned task within the workspace.

[0021] Another aspect is a virtual testing platform for predicting a specific cognitive-affective state of an individual. The virtual testing platform includes a simulated environment generator that creates a computer-generated environment representing a workspace seen by the individual, within which the individual must complete an assigned task. The virtual testing platform also includes an input device that receives user input generated by the individual, with the individual answering one or more survey questions either during or after performing the assigned task via the input device.The virtual testing platform also includes one or more control units that communicate electronically with the simulated environment generator and the input device. These control units comprise one or more processors that execute instructions to direct the simulated environment generator to create the computer-generated environment that represents the workspace. Based on user input received from the input device and indicating the individual's responses to one or more survey questions, the control units predict the individual's specific cognitive-affective state when performing the assigned task generated by the simulated environment generator.The one or more control units instruct the generator for a simulated environment to modify one or more experimental parameters related to the assigned task within the workspace, whereby the individual must re-perform the assigned task within the workspace whenever the one or more experimental parameters related to the assigned task are modified. The one or more control units instruct the generator for a simulated environment to produce computer-generated perceptual information that poses one or more survey questions to the individual each time the one or more experimental parameters within the workspace are modified.The one or more control units formulate one or more recommendations to implement the work area based on the individual's specific cognitive-affective state in a real-world environment.

[0022] Another aspect is that the one or more survey questions include a variety of multiple-choice answers, with each multiple-choice answer containing a numerical value that represents the strength of the specific cognitive-affective state that the individual is experiencing.

[0023] Another aspect is that one or more survey questions include free text answers.

[0024] In one aspect, a virtual testing platform for predicting a specific cognitive-affective state of an individual is disclosed. The virtual testing platform includes a simulated environment generator, which creates a computer-generated environment representing a workspace perceived by the individual. Within this workspace, the individual must complete an assigned task. The virtual testing platform also includes one or more physiological sensors that monitor the individual's physiological measurements, and one or more control units that communicate electronically with the simulated environment generator and the one or more physiological sensors.The one or more control units comprise one or more processors that execute instructions to direct the simulated environment generator to create the computer-generated environment that represents the workspace. The one or more control units predict the individual's specific cognitive-affective state when the individual performs the assigned task generated by the simulated environment generator, based on physiological measurements from the one or more physiological sensors.The one or more control units instruct the generator for a simulated environment to modify one or more experimental parameters related to the assigned task within the workspace. The individual must re-perform the assigned task within the workspace whenever the one or more experimental parameters related to the assigned task are modified. The one or more control units continue to monitor the individual's physiological measurements, as recorded by the one or more physiological sensors, while the one or more experimental parameters are modified. The one or more control units formulate one or more recommendations for implementing the workspace in a real-world environment, based on the individual's specific cognitive-affective state.

[0025] Further areas of application will become apparent from the present description. It should be understood that the description and specific examples serve only for illustration and are not intended to limit the scope of this disclosure. Brief description of the drawings

[0026] The drawings described here are for illustrative purposes only and are not intended to limit the scope of the present disclosure in any way. Fig. Figure 1 is a schematic diagram of the disclosed virtual test platform comprising one or more control units in electronic communication with a generator for a simulated environment according to an exemplary embodiment; and Fig. Figure 2 is a schematic diagram of an exemplary work area defined by the one shown in Fig. The generator shown in 1 is generated for a simulated environment according to an exemplary embodiment. Detailed description

[0027] The following description is merely exemplary and is not intended to limit the present disclosure, application or uses.

[0028] In Fig. Figure 1 shows an exemplary virtual test platform 10 for predicting a specific cognitive-affective state of an individual 12 while performing an assigned task generated by a simulated environment generator 14. The virtual test platform 10 comprises one or more control units 20 that communicate electronically with the simulated environment generator 14. In addition to the simulated environment generator 14, the one or more control units 20 also communicate electronically with at least one of the following: one or more physiological sensors 22 and an input device 24.The Simulated Environment Generator 14 creates a computer-generated environment that represents a workspace 26 seen by the individual 12, in which the individual 12 must complete the assigned task within the workspace 26 created by the Simulated Environment Generator 14.

[0029] As explained below, the disclosed virtual testing platform 10 predicts the specific cognitive-affective state of individual 12 when individual 12 performs the assigned task within the workspace 26 generated by the generator for a simulated environment 14. The virtual testing platform 10 can also formulate one or more recommendations for implementing workspace 26 in a real-world environment, based on individual 12's specific cognitive-affective state while performing the assigned task. As explained below, individual 12's specific cognitive-affective state is predicted based on physiological measurements acquired by one or more physiological sensors 22, survey data provided by individual 12, or both the physiological measurements and the survey data.Some examples of the specific cognitive-affective state predicted by the virtual testing platform 10 include, but are not limited to, well-being, exhaustion, cognitive workload, and stress.

[0030] The generator for a simulated environment 14 can be any device that creates the computer-generated environment representing the workspace 26, such as, but not limited to, an augmented reality system 14A, a virtual reality system 14B, or a computer device 14C comprising a display 36. For example, the augmented reality system 14A can include a computer device that comprises a display or data glasses that overlay computer-generated perceptual information, such as images and text, onto the real environment to create the computer-generated environment. The virtual reality system 14B can include, for example, a smart headset, a smart helmet, or a display that is part of a computer device that displays a fully virtual, computer-generated environment representing the workspace 26. The computer device 14C can be any type of computer device, e.g., a computer ...For example, a laptop or tablet computer on which the computer-generated environment is displayed on screen 36. Individual 12 sees the computer-generated environment, created by generator 14 for a simulated environment, and performs the assigned task within workspace 26.

[0031] Workspace 26 is a simulated or computer-generated environment that represents a space in which the individual 12 must perform their assigned task, such as, but not limited to, a manufacturing environment, a flight simulation environment for controlling an aircraft, or a driving simulation environment for controlling a vehicle. Some examples of the assigned task include flying the aircraft by operating control units such as a control stick or yoke, and controlling a vehicle by operating driver inputs such as the steering wheel, brake pedal, and accelerator pedal.Some examples of manufacturing environments that can be simulated include a robot-assisted door assembly line, a robot-assisted jack assembly line, a robot-assisted sub-component assembly line, a robot-assisted battery assembly line, a robot-assisted final assembly line, and a robot-assisted engine assembly line.

[0032] In the Fig. In the example shown, the workspace 26 comprises a robot arm 40 including a gripper 42, the robot arm 40 being guided by an overhead rail system 38. The robot arm 40 picks up a colored block 44 from a table 46 located on the opposite side of a room 48 in which the individual 12 is located, travels through the room 48 via the overhead rail system 38 to the individual 12, hands over the colored block 44 to the individual 12, and picks up another colored block 44 from the table 46. In the example shown, the assigned task involves the individual 12 receiving the colored block 44 from the robot arm 40, memorizing a sequence of colored blocks 44 handed to him or her by the robot arm 40, and reciting the sequence of colored blocks 44 aloud.

[0033] With reference to Fig. 1 include the one or more physiological sensors 22 any type of sensor for monitoring physiological measurements that indicate the specific cognitive-affective state of the individual 12 and may include off-body physiological sensors, on-body physiological sensors, or both off-body and on-body physiological sensors.Some examples of off-body physiological sensors include, but are not limited to, audio sensors such as a microphone to capture speech and sounds; cameras that monitor the scene, posture, and movement of individual 12; thermal cameras to capture the thermal profile of individual 12; body markers that capture posture and movement of individual 12; facial markers that capture facial expressions of individual 12; pressure mats that detect weight shifts; and technology-tracking sensors that monitor the use, behavior, and interactions between individual 12 and a specific device used by individual 12. The body and facial markers are tracked by cameras and processed by algorithms to determine individual posture and facial expressions.The technology tracking sensors can include any type of device that receives user-generated input from the individual 12, e.g., but not limited to, a touchscreen, a virtual reality control unit, a keyboard, a computer mouse, or a stylus.

[0034] Some examples of physiological sensors on the body include, but are not limited to, pressure sensors for measuring heart rate and respiration, galvanic skin response sensors for detecting emotional arousal, eye-tracking sensors that detect gaze and gaze direction, electroencephalography (EEG) sensors for detecting electrical activity of the brain, electromyography (EMG) sensors for recording the individual's muscle activity, and functional near-infrared spectroscopy (FNIRS) sensors that measure physiological data such as respiration and the concentration of oxyhemoglobin (O2Hb) and deoxyhemoglobin (Hhb) in the individual's prefrontal cortex.

[0035] It is to be understood that the specific physiological sensors 22 included in the virtual test platform 10 depend on the specific cognitive-affective state being assessed. This is because different types of cognitive-affective states elicit unique and distinct physiological responses in the individual 12. For example, specific cognitive-affective states such as arousal and anxiety lead to physiological effects such as an elevated heart rate, which is why pressure sensors for monitoring heart rate can be included. In the Fig. In the example shown, the specific cognitive-affective state of the individual 12, which is assessed by the virtual test platform 10, is their well-being. Accordingly, the one or more physiological sensors 22 include a camera, a microphone, a galvanic skin response sensor, and pressure sensors for monitoring heart rate.

[0036] With reference to Fig. 1. The input device 24 is any device for receiving user input generated by the individual 12, such as a touchscreen, a keyboard, a computer mouse, or an audio receiver that picks up sounds and words spoken by the individual 12. In one embodiment, the input device 24 is a technology tracking sensor that is part of the remote physiological sensors. In one embodiment, the one or more control units 20 instruct the generator for a simulated environment 14 to produce computer-generated perceptual information that poses one or more survey questions to the individual 12. The one or more control units 20 receive user input from the input device 24, which displays the individual 12's answers to the one or more survey questions.For example, the simulated environment generator 14 can display computer-generated text on a screen that is part of the simulated environment generator 14, which poses one or more survey questions to individual 12. In another example, the simulated environment generator 14 can produce an audible voice through a loudspeaker that poses one or more survey questions to individual 12.

[0037] Individual 12 answers one or more survey questions either during or after performing the assigned task by entering their answer via the input device 24. In one embodiment, instead of entering the answers to the one or more survey questions into the input device 24, individual 12 can answer the one or more survey questions manually by completing documents, and the user input is then entered by a third party using the input device 24. In another implementation, the user input can be entered by methods other than a third party, such as scanning a document for information based on optical mark recognition (OMR) or optical character recognition (OCR).

[0038] The one or more survey questions relate to and are indicative of the specific cognitive-affective state of individual 12. In one embodiment, the one or more survey questions comprise a variety of multiple-choice responses, each multiple-choice response including a numerical value representing the intensity of the specific cognitive-affective state experienced by individual 12. Some examples of predefined numerical scales that represent an individual's specific cognitive-affective state include, but are not limited to, the National Aeronautics and Space Administration Task Load Index (TLX), the Instantaneous Self-Assessment (ISA), and the Multidimensional Fatigue Inventory (MFI). In another embodiment, the one or more survey questions may alternatively include free-text responses.The one or more control units 20 can execute one or more natural language processing (NLP) algorithms to extract word content, semantics, and valence in order to determine the specific cognitive-affective state of the individual 12 while performing the assigned task based on the free-text response.

[0039] It is understood that the one or more control units 20 instruct the generator for a simulated environment 14 to modify one or more experimental parameters with respect to the assigned task within the workspace 26, whereby the individual 12 must re-perform the assigned task within the workspace 26 with the one or more experimental parameters that have been modified with respect to the assigned task. The one or more experimental parameters change the workspace 26 in which the individual 12 performs the assigned task. Each experimental parameter has the potential to influence the specific cognitive-affective state of the individual 12 while the individual 12 performs the assigned task.

[0040] In the Fig. In the example shown, one or more experimental parameters include the speed at which the robot arm 40 moves while guided by the overhead rail system 38, and a braking distance 50 measured between the robot arm 40 and the individual 12, and the specific cognitive-affective state of the individual 12 is well-being. If the speed of the robot arm 40 is increased and the braking distance 50 between the robot arm 40 and the individual 12 is decreased, the level of well-being of the individual 12 may decrease.

[0041] The one or more control units 20 instruct the generator for a simulated environment 14 to produce computer-generated perceptual information by asking the individual 12 one or more survey questions each time the one or more experimental parameters within the workspace 26 are modified. Similarly, the one or more control units 20 continue to monitor the physiological measurements of the individual 12, collected by the one or more physiological sensors 22, as the one or more experimental parameters are modified. In the Fig. In the example shown, it should be noted that, since the specific cognitive-affective state is well-being, the one or more survey questions include the query "Please rate the level of your overall well-being (or discomfort) while working with your robot teammate in the scenario you just experienced," and comprise nine numerically scaled responses ranging from -4 to 4, where -4 indicates extreme discomfort and 4 indicates extreme well-being. It is to be understood that the numerically scaled responses enable the one or more control units 20 to determine a relative change in well-being while modifying the one or more experimental parameters within the work range 26. In one embodiment, one of the survey questions also includes the question "Would you work with the robot arm in a real-world environment?"

[0042] The one or more control units 20 predict the specific cognitive-affective state of the individual 12 either on the basis of the physiological measurements of the individual 12, which are monitored by the one or more physiological sensors 22, the one or more survey questions created by the generator for a simulated environment 14, or both the physiological measurements and the survey questions.In an embodiment in which only the one or more survey questions are considered in predicting the specific cognitive-affective state of individual 12, the one or more survey questions each comprise the multiple-choice answers, and where each answer of the multitude of multiple-choice answers comprises a numerical value representing the strength of the specific cognitive-affective state experienced by individual 12, the one or more control units 20 use one or more statistical approaches to predict the specific cognitive-affective state of individual 12.In particular, the one or more control units 20 use one or more statistical approaches to determine a change in the strength of the individual's specific cognitive-affective state, as reflected in the multitude of multiple-choice responses given by the individual 12, while the one or more experimental parameters relating to the assigned task within the workspace 26 are modified. It is understood that the responses to the multiple-choice answers can be reduced to a single metric for each experimental parameter, based on statistical approaches such as a t-test comparison of continuous ratings of two or more different experimental parameters.

[0043] In an embodiment where only the physiological measurements of individual 12, monitored by the one or more physiological sensors 22, are considered when predicting individual 12's specific cognitive-affective state, the one or more control units 20 predict individual 12's specific cognitive-affective state either based on a classification model or a thresholding technique that considers numerical values ​​representing the intensity of individual 12's specific cognitive-affective state. In particular, the classification model is any type of supervised machine learning technique that classifies individual 12's physiological measurements into categories indicating individual 12's specific cognitive-affective state based on the signals generated by the one or more physiological sensors 22.Some examples of classification models that can be used include, but are not limited to, decision tree classifiers, multinomial logistic regression models, and support vector machine (SVM) classification.

[0044] Alternatively, the one or more control units 20 predict the specific cognitive-affective state of the individual 12 based on the numerical values ​​representing the intensity of the individual's specific cognitive-affective state. In particular, the one or more control units 20 can assign the numerical values ​​to the signals generated by the one or more physiological sensors 22. The numerical values ​​assigned to the signals representing the intensity of the specific cognitive-affective state are indexed to a baseline value representing a neutral cognitive-affective state, and the specific cognitive-affective state predicted by the one or more control units 20 is relative to the neutral specific cognitive-affective state.For example, if the numerical value assigned to the signals generated by one of the physiological sensors 22 includes a value of 5.7, the base value is 2, and the specific cognitive-affective state is stress, then the one or more control units 20 can predict the specific cognitive-affective state of the individual 12 as an increased level of stress.

[0045] The one or more control units 20 can predict the specific cognitive-affective state of the individual 12 based on physiological measurements collected at a single point in time or, alternatively, over a specific period of time. It is also understood that the one or more control units 20 can predict the specific mental state of the individual 12 based on regularly sampled data streams acquired by the one or more physiological sensors 22, irregularly sampled data streams acquired by the one or more physiological sensors 22, the individual's reaction times, the duration of the individual's use of a device, or task-related outcomes.An example of a regularly sampled data stream would include the output from optical sensors measuring heart rate, while an irregularly sampled data stream would include a motion tracker that only detects changes in the movement of individual 12, or an object that intermittently manipulates individual 12, such as a computer mouse.

[0046] The one or more control units 20 can execute one or more preprocessing algorithms to remove extraneous information from the physiological measurements acquired by the one or more physiological sensors 22. Some examples of the preprocessing algorithms include outlier removal, time segmentation to include only relevant time periods, resampling of the data streams to the same frequency, removal of data artifacts, elimination of signal distortions and offsets, and removal of extraneous frequencies.

[0047] In an embodiment in which the physiological data are acquired at a single time point, the one or more control units 20 can use one or more standard statistical approaches such as mean and standard deviation to determine differences in the physiological data between different subsets of experimental parameters or other conditions such as time windows in which the stimuli occurred.In one embodiment where physiological data are collected over a period of time and include timestamps, the one or more control units 20 can aggregate the physiological data over a time window. These time windows are then directly inputted into a classification model, such as a decision tree, logistic regression, or SVM, to determine the presence or absence of a specific cognitive-affective state and to compute the specific cognitive-affective state as a time series. It is understood that the time windows can include aggregated window values, including overlapping and non-overlapping windows. This approach can be used to determine the percentage of time during a recording session in which the individual was in the specific cognitive-affective state.In an embodiment where the physiological data comprises a waveform that fluctuates over time, such as physiological data acquired by EEG or EMG sensors, the one or more control units 20 employ one or more modeling approaches that account for the temporal dependence of past data points, such as, but not limited to, a long short-term memory (LSTM) model, other types of hidden recurrent neural networks (RNNs), and hidden Markov models. In an embodiment where the physiological data comprises image data representing the posture of the individual 12, the one or more control units 20 may include one or more convolutional neural networks (CNNs) to determine the posture of the individual 12.

[0048] In embodiments, the one or more control units 20 can employ one or more signal processing techniques to extract features from the physiological measurements in order to determine the specific cognitive-affective state, such as, but not limited to, time series analysis and frequency analysis. Some examples of time series analysis include signal strength, peak detection, determination of signal distortion, and standard deviation; and some examples of frequency analysis include Fourier analysis, frequency band filtering, power analysis, and frequency ratios. If the physiological measurements include, for example, EEG data, then the physiological signals of interest also include time-bound event-related potentials (ERPs), which are peaks in the data that differ in amplitude and timing depending on the specific cognitive-affective state.Frequency information can be derived from EEG data by considering power levels and / or ratios of well-characterized frequency bands, each with varying effects on cognitive and emotional state, depending on the spatial regions of the individual's scalp from which the EEG signals originate. The well-characterized frequency bands typically include delta (0.5–4 Hz), theta (4–8 Hz), alpha (8–13 Hz), beta (13–30 Hz), and gamma (>30 Hz) waveforms.

[0049] In an embodiment where both the physiological measurements of individual 12, monitored by the one or more physiological sensors 22, and the one or more survey questions are considered in predicting the specific cognitive-affective state of individual 12, the one or more control units 20 can predict the specific cognitive-affective state of individual 12 based on the described approach when only survey questions are considered, when only physiological data are considered, or based on a user-defined classification model. The user-defined classification model is based on any type of recurrent neural network (RNN) with internal memory, such as...a user-defined classification model, a Gated Recurrent Unit (GRU), a Dual-Attention Time-Aware GRU (DATA-GRU), a Velocity-Aware GRU (GRU-TV), an autoregressive moving average (ARMA) model, and a generalized autoregressive conditional heteroskedasticity ARMA (ARMA-GARCH). In particular, in an embodiment where the physiological data acquired by the one or more physiological sensors 22 are time-series data, the user-defined classification model is selected to account for the temporal order of the physiological data, such as an LSTM model. It is understood that the user-defined classification model is adapted for the specific workspace 26 and the specific cognitive-affective state predicted by the virtual test platform 10.

[0050] If the custom classification model is created, the answers to the one or more survey questions can be used as baseline truth data to train the custom classification model, comparing the physiological measurements acquired by the one or more physiological sensors 22 with the baseline truth data.In the present example, once the user-defined classification model has been trained on the basis of the basic truth data, it can predict a numerical value representing the strength of the specific cognitive-affective state experienced by individual 12 based on physiological measurements captured by the one or more physiological sensors 22, or a classification of the specific cognitive-affective state experienced by individual 12 based on subsequent physiological measurements captured by the one or more physiological sensors 22.

[0051] In one embodiment, the one or more control units 20 calculate a score for each prediction of the specific cognitive-affective state generated by the user-defined classification model. This score indicates either the accuracy of the numerical value representing the intensity of the specific cognitive-affective state or the classification of the specific cognitive-affective state. The one or more control units 20 can then create a confusion matrix based on the scores for each prediction of the specific cognitive-affective state predicted by the user-defined classification model. The confusion matrix indicates the accuracy or effectiveness of the specific cognitive-affective state predicted by the user-defined classification model.In one embodiment, if the confusion matrix indicates a satisfactory degree of accuracy or effectiveness of the user-defined classification model, subsequent testing may only require monitoring the physiological sensors 22 without asking the individual 12 the one or more questions.

[0052] Once the virtual testing platform 10 predicts the specific cognitive-affective state, the one or more control units 20 formulate one or more recommendations for implementing the workspace 26 in a real-world environment based on the individual's specific cognitive-affective state while performing the assigned task. Specifically, the one or more recommendations include ranges of values ​​for the one or more experimental parameters that will result in the individual 12 having a neutral cognitive-affective state while performing the assigned task within the workspace 26. In other words, the one or more recommendations suggest a range of values ​​for the one or more experimental parameters that will result in the individual 12 feeling comfortable or in a positive cognitive-affective state (e.g., feeling good).low levels of stress or fatigue) while performing the assigned task in work area 26.

[0053] In the Fig. In the second example shown, the one or more recommendations would include speeds for the robot arm 40 and measurements relating to the braking distance 50, measured between the robot arm 40 and the individual 12, that result in a neutral or elevated level of well-being for the individual 12. Another example: If the workspace 26 represents an autonomous vehicle, then the one or more recommendations would include values ​​for experimental parameters such as cornering speed, acceleration, braking, and merging distances that result in a neutral stress level for the individual 12.

[0054] The virtual testing platform depicted in the figures for predicting an individual's specific cognitive-affective state offers various technical effects and advantages. In particular, the disclosed virtual testing platform provides an approach to predicting the specific cognitive-affective state of an individual performing an assigned task within a virtual or augmented environment, without the need to invest in physical resources to construct a physical workplace. It should also be acknowledged that the specific cognitive-affective state predicted by the virtual testing platform can be used in the development of a physical version of the workplace.

[0055] The control units can refer to or be part of an electronic circuit, a combinational logic circuit, a field-programmable gate array (FPGA), a (shared, dedicated, or grouped) processor that executes code, or a combination of some or all of the above, for example, in a Systemon chip. Furthermore, the control units can be based on a microprocessor, such as a computer with at least one processor, memory (RAM and / or ROM), and associated input and output buses. The processor can operate under the control of an operating system residing in memory. The operating system can manage computer resources so that computer program code, embodied as one or more computer software applications, such as an application residing in memory, can direct instructions from the processor to be executed.In an alternative embodiment, the processor can execute the application directly; in this case, the operating system can be omitted.

[0056] The description of the present revelation is merely exemplary, and variations that do not deviate from the core of the present revelation are to be considered within its scope. Such variations are not to be regarded as a deviation from the spirit and scope of the present revelation.

Claims

[1] A virtual test platform for predicting a specific cognitive-affective state of an individual, the virtual test platform comprising: a simulated environment generator that creates a computer-generated environment representing a workspace seen by the individual, whereby the individual must complete an assigned task within the workspace simulated by the computer-generated environment; at least one of the following: one or more physiological sensors that monitor physiological measurements of the individual, and an input device that receives user input generated by the individual, wherein the individual answers one or more survey questions either during or after performing the assigned task via the input device; and one or more control units in electronic communication with the generator for a simulated environment, the one or more physiological sensors and the input device, wherein the one or more control units comprise one or more processors that execute instructions to: to instruct the generator for a simulated environment to create the computer-generated environment that represents the workspace; to predict the individual's specific cognitive-affective state when the individual performs the assigned task generated by the generator for a simulated environment, based on at least one of the following: the physiological measurements from the one or more physiological sensors, and the user inputs received by the input device indicating the individual's responses to the one or more survey questions; and to formulate one or more recommendations based on the individual's specific cognitive-affective state, to implement the work area in a real environment. [2] Virtual test platform according to claim 1, wherein the one or more processors of the one or more control units execute instructions to: to instruct the generator for a simulated environment to modify one or more experimental parameters related to the assigned task within the workspace, whereby the individual must re-execute the assigned task within the workspace if the one or more experimental parameters related to the assigned task are modified. [3] Virtual testing platform according to claim 2, wherein the specific cognitive-affective state of the individual is predicted based on one or more survey questions. [4] Virtual test platform according to claim 3, wherein the one or more processors of the one or more control units execute instructions to: to instruct the generator for a simulated environment to produce computer-generated perceptual information that poses one or more survey questions to the individual each time one or more experimental parameters within the workspace are modified. [5] Virtual testing platform according to claim 3, wherein the one or more survey questions comprise a plurality of multiple-choice answers and wherein each multiple-choice answer comprises a numerical value representing a strength of the specific cognitive-affective state experienced by the individual. [6] Virtual testing platform according to claim 3, wherein the one or more survey questions comprise free text answers. [7] Virtual testing platform according to claim 2, wherein the specific cognitive-affective state of the individual is predicted based on the physiological measurements acquired by the one or more physiological sensors. [8] Virtual test platform according to claim 7, wherein the one or more processors of the one or more control units execute instructions to: to continue monitoring the physiological measurements of the individual, as recorded by the one or more physiological sensors, when the one or more experimental parameters are modified. [9] Virtual test platform according to claim 7, wherein the one or more physiological sensors comprise one or more of the following: off-body physiological sensors and on-body physiological sensors. [10] Virtual test platform according to claim 9, wherein the off-body physiological sensors comprise one or more of the following: audio sensors, cameras, thermal cameras, body markers, face markers, pressure mats and technology tracking sensors.

Images