Spatial Perception Research Articles

Scene Representations for Robotic Spatial Perception

The ability of a robot to build a persistent, accurate, and actionable model of its surroundings through sensor data in a timely manner is crucial for autonomous operation. While representing the world as a point cloud might be sufficient for localization, denser scene representations are required for obstacle avoidance. On the other hand, higher-level semantic information is often crucial for breaking down the necessary steps to autonomously complete a complex task, such as cooking. So the looming question is, What is a suitable scene representation for the robotic task at hand? This survey provides a comprehensive review of key approaches and frameworks driving progress in the field of robotic spatial perception, with a particular focus on the historical evolution and current trends in representation. By categorizing scene modeling techniques into three main types—metric, metric–semantic, and metric–semantic–topological—we discuss how spatial perception frameworks are transitioning from building purely geometric models of the world to more advanced data structures incorporating higher-level concepts, such as the notion of object instances and places. Special emphasis is placed on approaches for real-time simultaneous localization and mapping, their integration with deep learning for enhanced robustness and scene understanding, and their ability to handle scene dynamicity as some of the hottest topics of interest driving robotics research today. We conclude with a discussion of ongoing challenges and future research directions in the quest to develop robust and scalable spatial perception systems suitable for long-term autonomy.

A deep learning model of dorsal and ventral visual streams for DVSD

Artificial intelligence (AI) methods attempt to simulate the behavior and the neural activity of the brain. In particular, Convolutional Neural Networks (CNNs) offer state-of-the-art models of the ventral visual stream. Furthermore, no proposed model estimates the distance between objects as a function of the dorsal stream. In this paper, we present a quantitatively accurate model for the visual system. Specifically, we propose a VeDo-Net model that comprises both ventral and dorsal branches. As in the ventral visual stream, our model recognizes objects. The model also locates and estimates the distance between objects as a spatial relationship task performed by the dorsal stream. One application of the proposed model is in the simulation of visual impairments. In this study, however, we show how the proposed model can simulate the occurrence of dorsal stream impairments such as Autism Spectrum Disorder (ASD) and cerebral visual impairment (CVI). In the end, we explore the impacts of learning on the recovery of the synaptic disruptions of the dorsal visual stream. Results indicated a direct relationship between the positive and negative changes in the weights of the dorsal stream’s last layers and the output of the dorsal stream under an allocentric situation. Our results also demonstrate that visual–spatial perception impairments in ASD may be caused by a disturbance in the last layers of the dorsal stream.

Exploring the influence of body movements on spatial perception in landscape and interior design

This study investigates the influence of body movements on spatial perception in both landscape and interior design environments, focusing on how physical interactions shape spatial understanding beyond visual perception alone. Grounded in the theory of embodied cognition, the research examines how gait, posture, and movement dynamics affect spatial awareness. The study captures detailed data on movement patterns and visual engagement across different spatial contexts using a combination of real-world observations and Virtual Reality (VR) simulations, motion-tracking systems, wearable sensors, and eye-tracking technology. A total of 157 participants, aged 20 to 65, navigated both outdoor landscapes and indoor environments, with key variables such as surface materials, spatial layout, and lighting conditions manipulated to assess their effects on spatial perception. The study measured gait speed, step frequency, path deviations, time to destination, visual attention, and subjective ratings of perceived openness, ease of movement, and emotional response. Key findings include that surface materials significantly influenced gait speed and step frequency. For example, participants walking on concrete had a significantly faster gait speed (mean difference = 0.5220, p = 0.001) than those walking on gravel. In terms of spatial layout, the two-way Analysis of variance (ANOVA) results showed that winding paths led to more path deviations (F-statistic = 350.00, p = 3.19 × 10−8) and longer times to destination (F-statistic = 1744.00, p = 2.39 ´ 10−11) compared to straight paths. The environment type (landscape vs. interior) also significantly affected navigation, with landscape participants showing a more significant deviation from direct paths (F-statistic = 19.60, p = 2.37 × 10−3). Visual engagement data, analyzed through a chi-square test, indicated that vertical elements like walls approached significance in attracting visual attention (Chi-square = 2.88, p = 0.0896), while other elements like trees and benches had less impact. The Wilcoxon signed-rank test results showed significant differences between real-world and VR experiences in perceived openness (W-statistic = 0.0, p = 0.001953), ease of movement (W-statistic = 0.0, p = 0.001953), and comfort (W-statistic = 0.0, p = 0.001953), highlighting VR’s limitations in replicating the full embodied experience of physical spaces.

Inability to pursue nonrigid motion produces instability of spatial perception.

Vision generates a stable representation of space by combining retinal input with internal predictions about the visual consequences of eye movements. We report a type of nonrigid motion that disrupts the connection between eye movements and perception, causing visual instability. This motion is accurately perceived during fixation, but it cannot be pursued. Catch-up saccades are accurately directed to the moving target but the motion stimulus appears to jump in space with each saccade. Our results reveal four major findings about perception and the visuomotor system: (i) Pursuit fails for certain types of motion; (ii) pursuit and catch-up saccades are independently controlled; (iii) prediction of saccade consequences is independent from saccade control; and (iv) the visual stability of moving objects relies on similar motion mechanisms as pursuit.

From traditional to digital contexts: new characteristics of the public’s spatial perception of urban streets in the age of technology

The constant development of internet technology in the digital age has changed the way people interact with space. To explore whether and what changes have occurred in the public’s spatial perception of the street during the shift from the traditional to the digital age, this paper compares the public’s spatial perception characteristics in the two contexts through a classical theory review and empirical coding analysis with the Xiaolouxiang historic district as an empirical case. The frameworks of public spatial perception characteristics are similar in both contexts, with a focus on the three dimensions of objects, buildings and spaces, and activities. However, compared with that in the traditional context, the public’s spatial perception of the street in the digital context of Xiaolouxiang has undergone new changes in three aspects: from focusing on the three-dimensional experience of space to focusing on the two-dimensional visual aesthetics of space, from emphasizing spatial totality to focusing on spatial details, and from focusing on the use of space to emphasizing the cultural characteristics of space. Research emphasizes that, within the context of digitalization, spatial design should place greater emphasis on visual aesthetics, detail processing, and cultural expression to better meet the needs and expectations of the public. This work identifies new features of the public’s perception of urban street space in the context of digitalization and accordingly provides suggestions for the future design of urban street space. The findings of this study not only enrich the foundational research content of spatial perception theory but also offer new perspectives for designers and planners in the practice of urban block renovation.

Investigation of the differences in designers' spatial perception in interior spaces using Kokedama

The word kokedama consists of the Japanese words "koke" (moss) and "dama" (ball). Due to its easily accessible materials and easy construction, it has become an application that almost everyone can do, and its use is expected to become widespread. The aim of this study is to investigate the differences in the spatial perceptions of designers who have received basic design education in different faculties in the case of interiors that including kokedama. To measure the differences in spatial perception, photographs of 8 different public interiors were processed and a survey was administered to the subjects. The survey results were analyzed statistically. According to the results of the study, the increase in the value of the perceptibility and simplicity criteria also increases the value of other criteria. As the value of perceptibility and simplicity increases in kokedama applications, the perception of complexity decreases. This data explains that the use of kokedama contributes positively to spatial perception. The criteria that have the most effect when they are together are the structure/identity and perceptibility criteria. The highest scorers on the criteria affecting spatial perception were graduates of the faculty of fine arts, while the lowest scorers were graduates of the faculty of agriculture.

Multi-channel neural audio decorrelation using generative adversarial networks

The degree of correlation between the sounds received by the ears significantly influences the spatial perception of a sound image. Audio signal decorrelation is, therefore, a commonly used tool in various spatial audio rendering applications. In this paper, we propose a multi-channel extension of a previously proposed decorrelation method based on generative adversarial networks. A separate generator network is employed for each output channel. All generator networks are optimized jointly to obtain a multi-channel output signal with the desired properties. The training objective includes a number of individual loss terms to control both the input-output and the inter-channel correlation as well as the quality of the individual output channels. The proposed approach is trained on music signals and evaluated both objectively and through formal listening tests. Thereby, a comparison with two classical signal processing-based multi-channel decorrelators is performed. Additionally, the influence of the number of output channels, the individual loss term weightings, and the employed training data on the proposed method’s performance is investigated.

Visual Perceptual Confidence: Exploring Discrepancies Between Self-reported and Actual Distance Perception In Virtual Reality.

Virtual Reality (VR) systems are widely used, and it is essential to know if spatial perception in virtual environments (VEs) is similar to reality. Research indicates that users tend to underestimate distances in VR. Prior work suggests that actual distance judgments in VR may not always match the users self-reported preference of where they think they most accurately estimated distances. However, no explicit investigation evaluated whether user preferences match actual performance in a spatial judgment task. We used blind walking to explore potential dissimilarities between actual distance estimates and user-selected preferences of visual complexities, VE conditions, and targets. Our findings show a gap between user preferences and actual performance when visual complexities were varied, which has implications for better visual perception understanding, VR applications design, and research in spatial perception, indicating the need to calibrate and align user preferences and true spatial perception abilities in VR.

Використання теорії невизначеності при дослідженні показників просторового сприйняття в єдиноборствах

Purpose: to study the indicators of spatial perception of martial artists using the provisions of uncertainty theories. Material and Methods. Research methods: analysis and synthesis of scientific and methodological literature, psychophysiological measurements, mathematical and statistical methods using licensed programs RStudio and Numbers. The study was conducted in several stages. At the first stage, taking into account the peculiarities of martial artists' sports activities, a mobile application «Spatial Perception» was developed to assess their spatial perception. At the second stage, the use of the application in the field was tested and the capabilities of the mobile application were expanded in terms of obtaining detailed characteristics of measurements using the provisions of the theory of uncertainty. The study involved junior taekwondo athletes aged 14-17 years (n=25, qualification: 1st category and candidates for master of sports of Ukraine). Results: according to the measurements of the studied martial artists, it can be noted that the highest frequency of reaction time indicators lies within 583 ms (n=291). At the second stage of the test exercise, where the performer needs to react to non-moving 3D figures, there is an increase in the interquartile range by 22 ms and a violation of the symmetry of the data. It was at this stage that the largest value of the standard deviation was noted (SD=172,0 ms). This indicates a high variability of reaction time (V=22,7 %). Also, we can see an increase in reaction time at the fourth stage compared to the result of the third stage by 11,5 ms and an increase in the percentage of errors by 1,4 % (at this stage, the highest percentage of errors was recorded at 8,2 %). Based on the use of membership functions, fuzzy sets were created, which made it possible to evaluate each indicator on a scale from 0 to 1. The analysis of the test exercise performance by martial artists who have the category of KMS (candidate for master of sports) shows that the overall score for the entire test is «Good», the weighting factor is 0,74, which is closer to the «Excellent» score. It should be noted that the highest weighting coefficient was observed in the second stage of the test task. The high weighting factor (0,79) at this stage reflects the ability to quickly recognize 3D shapes in space based on the analysis of individual parts of the shapes. We can also note the low percentage of errors (3 %) at the fourth, most difficult stage. This may indicate the ability to maintain attention on the object and resistance to disturbing visual stimuli. According to the results of the martial artists who have the 1st category, it was noted that they performed the test exercise with a score of «Good» and have a total weighting factor of 0,34. The score at each stage of the test is «Good», but the values of the weighting coefficients are closer to the «Satisfactory» score. The values of the weighting coefficients demonstrate that the level of spatial perception of this group of athletes is below average. It is also worth noting the increase in the percentage of errors, especially at the fourth stage (11,7 %), which indicates a negative impact on the reaction time of additional visual stimuli. The biggest difference between weight coefficients of the studied groups was noted at the second stage and made 49 %, the smallest at the fourth stage – 27 %. Conclusions. The use of fuzzy logic methods is a promising area of activity and finds its application in sports activities. The levels of manifestation of spatial perception by weight coefficients have been determined. Thus, a group of sportsmen with a category of CMS received an overall mark for the whole test «Good»with a weight coefficient of 0,74, and martial artists of the 1st category received an overall mark for the whole test «Good» with a weight coefficient of 0,34. Comparison of results of the estimation of reaction time of martial artists with a category of CMS with sportsmen of the 1st category testifies that there are statistically significant differences between indicators (p<0,05). The use of the theory of uncertainty in the assessment of spatial perception makes it possible to create flexible assessment systems and allows combining different indicators into one complex result.

Bacterial film-based degradable triboelectric nanogenerator for both contact and non-contact sensing

As an emerging environmentally friendly energy conversion device, degradable triboelectric nanogenerators (TENGs) play an important role in self-powered sensing, health care and human–machine interaction. However, traditional degradable materials used in TENGs often suffer from limited material sources and complex preparation processes, restricting large-scale production for widespread applications. Here, we propose a simple and efficient way to prepare degradable TENGs with inactivated bacterial film, taking advantage of wide source, self-proliferation and easy culture properties of bacteria. The prepared bacterial film-based TENG (BF-TENG) has stable electrical output, good durability and fatigue resistance, along with superior capabilities in both contact and non-contact sensing. In contact mode, the BF-TENG can generate a peak voltage of up to 83.3 V, which is employed for accurate Morse code transmission. In non-contact mode, the BF-TENG is capable of effectively perceiving the target polymer at a distance of 150 cm. The non-contact LED control circuit and a sensing array based on BF-TENG further demonstrate its practical potential for gesture recognition and spatial position perception. Furthermore, the fully degradable nature of BF-TENG ensures effortless disposal after use without environmental impact, serving as a promising solution for the new generation of eco-friendly and sustainable sensing devices.

A Framework for Multimodal Medical Image Interaction.

Medical doctors rely on images of the human anatomy, such as magnetic resonance imaging (MRI), to localize regions of interest in the patient during diagnosis and treatment. Despite advances in medical imaging technology, the information conveyance remains unimodal. This visual representation fails to capture the complexity of the real, multisensory interaction with human tissue. However, perceiving multimodal information about the patient's anatomy and disease in real-time is critical for the success of medical procedures and patient outcome. We introduce a Multimodal Medical Image Interaction (MMII) framework to allow medical experts a dynamic, audiovisual interaction with human tissue in three-dimensional space. In a virtual reality environment, the user receives physically informed audiovisual feedback to improve the spatial perception of anatomical structures. MMII uses a model-based sonification approach to generate sounds derived from the geometry and physical properties of tissue, thereby eliminating the need for hand-crafted sound design. Two user studies involving 34 general and nine clinical experts were conducted to evaluate the proposed interaction framework's learnability, usability, and accuracy. Our results showed excellent learnability of audiovisual correspondence as the rate of correct associations significantly improved (p < 0.001) over the course of the study. MMII resulted in superior brain tumor localization accuracy (p < 0.05) compared to conventional medical image interaction. Our findings substantiate the potential of this novel framework to enhance interaction with medical images, for example, during surgical procedures where immediate and precise feedback is needed.

A Review of Intelligent Depth Distance Perception Research for Power Transmission Line Corridor Scenarios

Transmission lines are essential carriers for the transmission of electrical energy, and their safe operation is fundamental to ensuring reliable power supply. However, the environment of transmission line corridors is complex and variable, posing numerous risks of external damage. With the development of smart power systems, information technologies such as video monitoring provide effective means for monitoring and managing external damage to transmission lines. Nonetheless, the current technology for identifying external damage and safe distances for transmission lines is weak, leading to frequent false alarms and low efficiency in practical applications. To address this issue, this paper systematically reviews and summarizes the progress of distance recognition technology in power systems. First, it outlines the spatial distance perception performance requirements for models in transmission line corridor scenarios and summarizes the spatial distance data characteristics of these corridors. Second, the paper categorizes existing common safety distance recognition methods from the perspectives of active and passive ranging, analyzing their advantages and disadvantages in the context of transmission line corridors. Finally, this paper summarizes the types and performance characteristics of current deep learning-based distance recognition methods and proposes a potential application framework for these methods in transmission line corridor scenarios. It also discusses the future application prospects and challenges faced by this framework.

The Effect of Noise and Reverberation on Spatial Perception in Sequential Bilateral Cochlear Implant Users

Abstract Background Spatial orientation is an executive function which includes vital activities and auditory organization according to daily bodily movements, directionality, and environmental information. It is directly linked to the vision and hearing and used throughout life, building complex relationships with these systems, based on learning. Purpose Our purpose in our study is to try to see the effects of noise and reverberation on the users by comparing the localization and auditory performances of the cochlear implant (CI) user individuals in a silent, noisy environment and reverberation. Research Design All subjects were subjected to immitancemetric/audiological tests, language development test (TIFALDI, Receptive/Expressive Language Test score 7 years and above), localization determination in noise, and localization determination test in reverberation. Study sample: In our study, 18 female and 16 male bilateral CI users with profound sensorineural hearing loss were included. The age range of subjects was 8 years 4 months and 10 years 11 months. Data Collection and Analysis Data from subjects were collected prospectively. Data analysis was analyzed with SPSS 21 program. Results It was observed that the subjects did not have difficulty in determining the direction in silent condition, but they had a significant difficulty in localizing the 135-, 225-, and 315-degree angles especially when the noise was signal-to-noise ratio (SNR) –10 dB and the reverberation was 06 and 09 second (p ≤ 0.005). Subjects' performances were significantly altered in sequential implanted users both when the SNR was changed and in the presence of reverberation (p &lt; 0.05). Conclusion As a result of our study, it is thought that individuals with hearing loss will experience intense difficulties, especially in noisy and reverberant environments such as schools, and using assistive listening devices in these environmental conditions will contribute positively to their academic development.

Integrating Virtual Reality and Colour Psychology in the Design of Small Liveable Spaces

Virtual reality (VR) technology has quickly advanced, providing new ways for immersive and interactive experiences. This research aims to integrate colour theories into the practical application of Vanspace 3D software. The study investigates the perceptual dimensions of colour schemes, lighting, and their collective impact on spatial perception within confined living spaces. Through a step-by-step equipping and furnishing process, the software's versatility is demonstrated, accommodating various design elements, from solar panels to custom furniture. Monochromatic and analogous schemes align with nature-inspired living, while triadic schemes emphasise balance. Complementary and tetradic schemes showcase harmonious and rich designs, and warm and cold colour schemes present contrasting atmospheres, highlighting design adaptability. Exploration of contrast, saturation, and lighting underscores their influence on aesthetics and functionality. Findings suggest that colour choices significantly impact perceived size and ambience, offering recommendations for creating spacious illusions in confined spaces.

Exploring the Mechanisms and Functions of the Impact of Ketamine on Spatial Orientation Decision Making

The aim of the study is to explore the impact of ketamine on sound perception and spatial orientation decision making, and the mechanism of how ketamine impacts perception and decision abilities. The methods used include behavioral and histology approaches. From the results, it can be concluded one of the brain regions affected by ketamine is TeA(temporal association area), which plays a vital role in sound perception and spatial orientation. An unexpected finding is that ketamine impacts left turning and right turning decisions at different degree, which requires further research on ketamine’s different impact on two cerebral hemispheres. In all, the study’s findings help people further understand how ketamine impacts spatial and sound perception.

MonoCAPE: Monocular 3D object detection with coordinate-aware position embeddings

3D monocular detection remains to be a focal point of research, particularly due to its capacity to deliver available precision under conditions of low cost and simplified configurations, making it especially valuable in fields like autonomous driving. Current 3D object detection methods often overlook the spatial information missing from images, which is critical to spatial perception, and optimize bounding box attributes separately, failing to meet the requirements of autonomous driving. We introduce MonoCAPE, a novel 3D detection framework addressing these issues by encoding spatial information and co-optimizing attributes through a Coordinate-Aware Position Encoding (CAPE) Generator and a Task Co-optimization Strategy (TCS). The CAPE Generator produces sparse positional embeddings, enabling spatial awareness with low computational cost, while the TCS utilizes Gaussian modeling to prevent suboptimal outputs. In this way, our framework comprehensively takes into account what existing approaches ignore. Extensive experiments on the KITTI dataset demonstrate MonoCAPE significantly improves AP3D and APBEV metrics compared to existing advanced methods.

Development and enhancement of spatial perception among university students for better retention

During the compilation of this article, the primary aim was the exploration of the available opportunities regarding the development and improvement of spatial perception, and the creation of a future plan for assessing the spatial intelligence of engineering students attending the University of Miskolc. After carefully studying several publications, the Barke-style test was chosen, which is showcased in detail in this article. In my version, the essence of the test would remain the same, only the the tasks would be altered, and the incoming engineering students would participate in the survey, in a way similar to the mathematical competency survey that already exists at the university. Depending on the results of the survey, my plans include the creation of recommendations as part of my research, aimed at strengthening spatial competency among the engineering students attending the University of Miskolc.

Analysis of Spatial Vitality Characteristics and Influencing Factors of Old Neighborhoods: A Case Study of Ya’an Xicheng Neighborhood

Amidst the pursuit of sustainable urban development, bolstering the spatial vitality of historic neighborhoods emerges as a pivotal endeavor. This study, centering on the Xicheng neighborhood in Ya’an City, employs a multifaceted data analysis approach to unravel the intricate spatial vitality patterns. By adopting a dual lens focusing on both “people” and “space”, we delve into the intricate interplay between spatial vitality, spatial perception, and various influencing factors, such as the spatial environment, business format layout, and place atmosphere. Leveraging spatial correlation analysis, we meticulously examine the extent to which these multifarious factors shape spatial vitality and perception. Our findings reveal a profound connection between the emotional dimension of perception and the distribution of spatial vitality. Notably, aspects of spatial character—green rating, accessibility, and interface richness—exert the most pronounced influence on vitality. Furthermore, the creation of a distinctive atmosphere in a place is more likely to resonate with a person’s spatial perception than the physical environment itself.

Improving speech intelligibility in noise and spatial perception: the critical role of hearing aid microphone position.

Hearing aid (HA) manufacturers have introduced behind-the-ear (BTE) models where the microphone is positioned in the ear canal, which could impact auditory performance by distorting the pinna's acoustic cues. This study aimed to compare two different BTE HAs with varying microphone positions: the receiver in the ear (RITE) and the transducer in the ear (TIE). The study involved 10 participants who had never used HAs before. They used both RITE and TIE HAs bilaterally for 3 weeks. Auditory performance was assessed through free field hearing assessments (hearing thresholds, speech recognition threshold, and speech discrimination score), the Turkish Matrix Sentence Test (TURMatrix), a sound localization test, and the Satisfaction with Amplification in Daily Living (SADL) questionnaire. There was no significant difference between TIE and RITE in the free field hearing assessments. However, TIE outperformed RITE in non-adaptive TURMatrix scores in quiet, adaptive TURMatrix scores in noise, and sound localization accuracy at various angles. SADL sub-scores (Positive Effect, Service and Cost, and Personal Image) and overall satisfaction scores were significantly better for TIE. The microphone position in HAs can influence auditory performance. This study demonstrated that TIE provided better speech intelligibility, localization accuracy, and user satisfaction compared to RITE.

Multi-Sensory Interaction and Spatial Perception in Urban Microgreen Spaces: A Focus on Vision, Auditory, and Olfaction

As important recreational spaces for urban residents, urban microgreen parks enhance the urban living environment and alleviate psychological pressure on residents. The visual, auditory, and olfactory senses are crucial forms of perception in human interaction with nature, and the sustainable perceptual design of miniature green parks under their interaction has become a recent research hotspot. This study aimed to investigate the effects of the visual, acoustic, and olfactory environments (e.g., aromatic green vegetation) on human perception in miniature green parks. Participants were evenly divided into eight groups, including single-sensory groups, multi-sensory interaction groups, and a control group. Eye-tracking technology, blood pressure monitoring, and the Semantic Differential (SD) scales and Profile of Mood State (POMS) were used to assess the effectiveness of physical and mental perception recovery in each group. The results revealed that in an urban microgreen space environment with relatively low ambient noise, visual–auditory, visual–olfactory, and visual–auditory–olfactory interactive stimuli were more effective in promoting the recovery of visual attention than single visual stimuli. Additionally, visual–auditory–olfactory interactive stimuli were able to optimize the quality of spatial perception by using positive sensory inputs to effectively mask negative experiences. Simultaneously, environments with a high proportion of natural sounds had the strongest stimuli, and in the visual–auditory group, systolic blood pressure at S7 and heart rate at S9 significantly decreased (p &lt; 0.05), with reductions of 18.60 mmHg and 20.15 BPM, respectively. Aromatic olfactory sources were more effective in promoting physical and mental relaxation compared to other olfactory sources, with systolic blood pressure reductions of 24.40 mmHg (p &lt; 0.01) for marigolds, 23.35 mmHg (p &lt; 0.01) for small-leaved boxwood, and 27.25 mmHg (p &lt; 0.05) for camphor trees. Specific auditory and olfactory conditions could guide visual focus, such as birdsong directing attention to trees, insect sounds drawing attention to herbaceous plants, floral scents attracting focus to flowers, and leaf scents prompting observation of a wider range of natural vegetation. In summary, significant differences exist between single-sensory experiences and multi-sensory modes of spatial perception and interaction in urban microgreen parks. Compared to a silent and odorless environment, the integration of acoustic and olfactory elements broadened the scope of visual attention, and In the visual–auditory–olfactory interactive perception, the combination of natural sounds and aromatic camphor tree scents had the best effect on attention recovery, thereby improving the quality of spatial perception in urban microgreen parks.