Robotic Assistance Research Articles

Exploring the Needle Tip Interaction Force with Retinal Tissue Deformation in Vitreoretinal Surgery.

Recent advancements in age-related macular degeneration treatments necessitate precision delivery into the subretinal space, emphasizing minimally invasive procedures targeting the retinal pigment epithelium (RPE)-Bruch's membrane complex without causing trauma. Even for skilled surgeons, the inherent hand tremors during manual surgery can jeopardize the safety of these critical interventions. This has fostered the evolution of robotic systems designed to prevent such tremors. These robots are enhanced by FBG sensors, which sense the small force interactions between the surgical instruments and retinal tissue. To enable the community to design algorithms taking advantage of such force feedback data, this paper focuses on the need to provide a specialized dataset, integrating optical coherence tomography (OCT) imaging together with the aforementioned force data. We introduce a unique dataset, integrating force sensing data synchronized with OCT B-scan images, derived from a sophisticated setup involving robotic assistance and OCT integrated microscopes. Furthermore, we present a neural network model for image-based force estimation to demonstrate the dataset's applicability.

Community-Dwelling Older Adults' Readiness for Adopting Digital Health Technologies: Cross-Sectional Survey Study.

Digital health technologies offer the potential to improve the daily lives of older adults, maintain their health efficiently, and allow aging in place. Despite increasing evidence of benefits and advantages, readiness for adopting digital interventions among older people remains underexplored. This study aims to explore the relationships between sociodemographic-, health-, and lifestyle-related factors and technology use in everyday life and community-dwelling older adults' readiness to adopt telemedicine, smartphones with texting apps, wearables, and robotics. This was a cross-sectional, population-based survey study with a stratified probabilistic sample of adults aged 75 years or older living in South Tyrol (autonomous province of Bolzano/Bozen, Italy). A random sample of 3600 community-dwelling older adults living at home was invited to complete a questionnaire including single items (older adults' readiness to use health technology) and scales (PRISMA-7; Program of Research on Integration of Services for the Maintenance of Autonomy). Descriptive and logistic regression analyses were performed to analyze the data. In total, 1695 community-dwelling older adults completed the survey (for a response rate of 47%). In terms of potential digital health technology adoption, wearable devices were favored by 33.7% (n=571), telemedicine by 30.1% (n=510), smartphones and texting apps by 24.5% (n=416), and assistant robots by 13.7% (n=232). Sociodemographic-, health- and lifestyle-related factors, as well as the use of technology in everyday life, played a significant role in explaining readiness to adopt digital health technologies. For telemedicine, age ≥85 years (odds ratio [OR] 0.74, 95% CI 0.56-0.96), financial constraints (OR 0.68, 95% CI 0.49-0.95), and less than 2 hours of physical activity per week (OR 0.75, 95% CI 0.58-0.98) were associated with nonreadiness, while Italian-speaking participants (OR 1.54, 95% CI 1.16-2.05) and those regularly using computers (OR 1.74, 95% CI 1.16-2.60), smartphones (OR 1.69, 95% CI 1.22-2.35), and the internet (OR 2.26, 95% CI 1.47-3.49) reported readiness for adoption. Community-dwelling older adults display varied readiness toward the adoption of digital health technologies, influenced by age, mother tongue, living situation, financial resources, physical activity, and current use of technology. The findings underscore the need for tailored interventions and educational programs to boost digital health technology adoption among community-dwelling older adults.

A case of primary total knee arthroplasty revision using CORI system

Total Knee Arthroplasty (TKA) is a common surgical procedure used to treat end-stage osteoarthritis of the knee. The increasing adoption of computer-assisted and robotic assisted techniques in total joint arthroplasty has been found to enhance the accuracy of component placement. Short-term studies have indicated improved survival rates in unicompartmental knee arthroplasty with the use of robotic assistance. While robotic technology has proven beneficial in revising procedures like converting unicompartmental knee arthroplasty to TKA, there is limited information on its application in revising primary TKA. This case report details the use of robotic-assisted technology with CORI system in the revision of TKA. The incorporation of robotic assistance during TKA revision surgeries may contribute to better alignment of components and potentially increase the longevity of the prosthetic implant. However, further research is essential to explore the impact of robotic assistance on the overall survival rates and cost-effectiveness of revision TKA procedures.

J.A.R.V.I.S: A Personal Assistant Robot

Abstract: Personal assistant robots are becoming increasingly popular as versatile devices that can assist individuals in various aspects of daily life. These robots are designed to be small and portable, with user-friendly interaction features that allow them to navigate tight spaces and interact closely with users. Equipped with sensors, cameras, and AI algorithms, personal assistant robots can perceive and respond to their environment, recognize faces and voices, and perform tasks such as setting reminders, providing information, and controlling smart home devices. They offer a range of benefits in different settings, including smart homes, healthcare facilities, and public spaces, where they can serve as personal assistants, health monitors, and information guides. The ability of personal assistant robots to learn and adapt to users' preferences and behaviors over time enables them to provide personalized and intuitive assistance, making them suitable for individuals of all ages. As advancements in their design and capabilities continue, personal assistant robots are expected to have an even greater impact on enhancing daily life in the future

Mechanical marvels: robots in carotid artery stenting - a systematic review of effectiveness in neuroendovascular interventions

Aim: Carotid artery disease, or carotid stenosis, is a critical medical condition carrying the risk of stroke and fatality. The underlying pathology involves the accumulation of atheromatous plaques, leading to luminal constriction and disrupted blood flow. Endovascular interventions, such as carotid artery stenting (CAS), aim to restore vessel patency. Robotic assistance in CAS surgeries is rapidly evolving globally, offering precision and fatigue-free capabilities. Despite growing interest, a dedicated systematic review on robotic applications in CAS is notably absent. Methods: Adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a comprehensive search strategy involving five databases. Data extraction encompassed study origin, patient demographics, procedural details, procedure times, complications, fluoroscopy, and radiation parameters. Results: Over 199 articles were identified from five databases. Seven studies meeting inclusion criteria were analyzed. The predominant robotic system, CorPath GRX, demonstrated advantages such as remote operation, precision, and compatibility with various catheter sizes. Magellan Robotic System, employed in one study, showcased remote-controlled capabilities. These studies involved a total of 44 patients undergoing carotid artery stenosis procedures with robotic assistance. Reported complications included access site conversion, Angio-Seal device failure, and residual stenosis. Mean operation time varied from 34 to 85 min. Conclusions: The integration of robotic assistance in carotid interventions, as demonstrated by the CorPath GRX and Magellan Robotic System, holds significant promise in improving the precision and safety of CAS procedures. However, the limited number of studies, the high risk of bias, and the need for further research and standardization highlight the evolving nature of this technology.

Can Socially Assistive Robots Be Accepted by Older People Living Alone in the Community?: Empirical Findings from a Social Work Project in China

ABSTRACT A pilot study was undertaken between March 2019 and September 2021, loaning socially assistive robots (SARs) for a 7-day trial to older people living alone in China. Quantitative assessments of participants’ acceptance of technology and loneliness were conducted before and after the intervention, supplemented with qualitative interviews. Unexpectedly, participants’ intention to use SARs decreased significantly, largely due to emotional anxiety. Meanwhile, participants’ level of loneliness remained unchanged. Follow-up interviews revealed anxious emotion, hesitant attitudes, unreal social presence, usability difficulties as contributing factors. The study provides social workers with valuable insights into introducing SARs into community care of older people.

A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction.

People with blindness and low vision (pBLV) encounter substantial challenges when it comes to comprehensive scene recognition and precise object identification in unfamiliar environments. Additionally, due to the vision loss, pBLV have difficulty in accessing and identifying potential tripping hazards independently. Previous assistive technologies for the visually impaired often struggle in real-world scenarios due to the need for constant training and lack of robustness, which limits their effectiveness, especially in dynamic and unfamiliar environments, where accurate and efficient perception is crucial. Therefore, we frame our research question in this paper as: How can we assist pBLV in recognizing scenes, identifying objects, and detecting potential tripping hazards in unfamiliar environments, where existing assistive technologies often falter due to their lack of robustness? We hypothesize that by leveraging large pretrained foundation models and prompt engineering, we can create a system that effectively addresses the challenges faced by pBLV in unfamiliar environments. Motivated by the prevalence of large pretrained foundation models, particularly in assistive robotics applications, due to their accurate perception and robust contextual understanding in real-world scenarios induced by extensive pretraining, we present a pioneering approach that leverages foundation models to enhance visual perception for pBLV, offering detailed and comprehensive descriptions of the surrounding environment and providing warnings about potential risks. Specifically, our method begins by leveraging a large-image tagging model (i.e., Recognize Anything Model (RAM)) to identify all common objects present in the captured images. The recognition results and user query are then integrated into a prompt, tailored specifically for pBLV, using prompt engineering. By combining the prompt and input image, a vision-language foundation model (i.e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing environmental objects and scenic landmarks, relevant to the prompt. We evaluate our approach through experiments conducted on both indoor and outdoor datasets. Our results demonstrate that our method can recognize objects accurately and provide insightful descriptions and analysis of the environment for pBLV.

Care-receivers with physical disabilities’ perceptions on having humanoid assistive robots as assistants: a qualitative study

BackgroundPeople with physical disabilities due to disease or injury face barriers to their daily activities and participation in society. Many depend on formal or informal caregivers for assistance to live independently. However, future healthcare challenges due to demographic changes threaten access to home care and assistants. Assistive technologies, such as robots for physical assistance, can support the independence and autonomy of people with physical disabilities. This study explore Norwegian care-receivers’ perceptions of using robot assistance in their homes, including preferences for tasks acceptable or unacceptable for robot assistance and the underlying reasons.MethodPurposive sampling was employed to recruit 18 participants, aged between 18 and 77 years, with differences in physical function including diagnoses such as stroke, spinal cord injury, amputations, and muscular dystrophy. Qualitative data were gathered through four focus group interviews wherein participants watched videos featuring a humanoid assistive robot, EVEr3. The collected data underwent analysis using reflexive thematic analysis.ResultsThree themes with associated sub-themes were constructed: (a) How a robot could assist in daily life, (b) The robot’s appearance and functionality, and (c) Concerns about having a robot as an assistant. The participants welcomed the idea of a future robotic assistant in areas that may contribute to an increased feeling of independence and autonomy.ConclusionA robot assisting in activities of daily living would need to be individually customized to meet the needs of each user in terms of which tasks to assist with, how to assist in these defined tasks, and how it is controlled.

Randomized Controlled Trial of Cardiac Rehabilitation Using the Balance Exercise Assist Robot in Older Adults with Cardiovascular Disease.

Recent studies have investigated the effects of exercise on the functional capacity of older adults; training with a balance exercise assist robot (BEAR) effectively improves posture. This study compared the clinical safety and efficacy of training using BEAR video games to conventional resistance training in older adults with cardiovascular disease (CVD). Ninety patients (mean age: 78 years) hospitalized due to worsening CVD were randomized to cardiac rehabilitation (CR) Group R (conventional resistance training) or Group B (training using BEAR). After appropriate therapy, patients underwent laboratory testing and functional evaluation using the timed up-and-go test (TUG), short physical performance battery (SPPB), and functional independence measure (FIM) just before discharge and 4 months after CR. The rates of CVD readmission, cardiac death, and fall-related fractures were monitored. BEAR had no adverse effects during exercise. At 4 months, TUG and SPPB improved significantly in both groups, with no significant difference between them. FIM motor and the Geriatric Nutritional Risk Index were significantly improved in Group B versus Group R. There was no significant difference in cardiac events and fall-related fractures between the two groups. CR with BEAR is safe and comparable to conventional resistance training for improving balance in older adults with CVD.

On the Remarkable Advancement of Assistive Robotics in Human-Robot Interaction-Based Health-Care Applications: An Exploratory Overview of the Literature

With the rapid advancement of technology, assistive robotic entities have arisen as indispensable instruments within diverse Human-Robot Interaction (HRI)-based health-care applications. By integrating Artificial Intelligence (AI) into these assistive robotic entities, they gain the capacity to autonomously perceive, engage in sophisticated reasoning, and execute actions within highly dynamic and complex environments. In light of these impressive achievements, this paper highlights a three-stage exploratory overview of the literature on the remarkable advancement of assistive robotics in HRI-based health-care applications. The first stage initiates an assessment of assistive robotics spanning historical epochs from ancient to modern times. Following this, the second stage comprehensively explores assistive robotics investigations in the realm of HRI-based health-care with its four sub-fields including rehabilitation, geriatric-care, pediatric-care, and nursing. Finally, the third stage entails a thorough analysis of the common challenges encountered in these pertinent investigations and provides a set of recommendations. This comprehensive paper not only provides an abundance of studies for each concept, method, and application in HRI, but it also presents their theoretical foundations, strengths, gaps, critical challenges, and recommendations. The results of the conducted exploratory overview shed light on the noteworthy prominence of assistive robotic entities within the HRI-based health-care field. The acquired findings emphasize the positive impact of such entities on human health, affirming their pivotal role in contributing to the advancement and effectiveness of health-care interventions. Furthermore, this paper provides an opportunity for scholars and researchers actively engaged in the pertinent field to obtain comprehensive additional insights, serving as a guiding resource for their academic endeavors.

Radiographic and clinical outcomes of robot-assisted pedicle screw instrumentation for adolescent idiopathic scoliosis.

Pedicle screw instrumentation (PSI) serves as the widely accepted surgical treatment for adolescent idiopathic scoliosis (AIS). The accuracy of screw positioning has remarkably improved with robotic assistance. Nonetheless, its impact on radiographic and clinical outcomes remains unexplored. This study aimed to investigate the radiographic and clinical outcomes of robot-assisted PSI vs. conventional freehand method in AIS patients. Data of AIS patients who underwent PSI with all pedicle screws between April 2013 and March 2022 were included and retrospectively analyzed; those with hybrid implants were excluded. Recruited individuals were divided into the Robot-assisted or Freehand group according to the technique used. Radiographic parameters and clinical outcome measures were documented. In total, 50 patients (19, Freehand group; 31, Robot-assisted group) were eligible, with an average age and follow-up period of 17.6 years and 60.2 months, respectively, and female predominance (40/50, 80.0%). The correction rates of Cobb's angles for both groups were significant postoperatively. Compared to freehand, the robot-assisted technique achieved a significantly reduced breech rate and provided better trunk shift and radiographic shoulder height correction with preserved lumbar lordosis, resulting in significantly improved visual analog scale scores for back pain from the third postoperative month. Overall, robot-assisted PSI provides satisfactory radiographic and clinical outcomes in AIS patients.

Robotic-Assisted Minimally Invasive Direct Coronary Artery Bypass Grafting: A Surgical Technique.

In recent years, there has been a growing interest in robotic-assisted coronary artery revascularization in Europe. Two different types of surgery can be performed using a robotic platform: RA-MIDCAB, in which the mammary artery is harvested endoscopically with robotic assistance and off-pump bypass graft is achieved under direct vision through mini thoracotomy, and TE-CAB, completely robotically performed. We started the robotic cardiac surgery program for mitral valve disease in our hospital, Humanitas Gavazzeni (Bergamo, Italy), in 2019; and in 2021, we addressed our experience with RA-MIDCAB. After a learning curve period, we have developed our technique to optimize the benefits offered by the robotic platform, tailoring strategy to individual patients, based on preoperative radiological images.

ZORA robot to assist a caregiver in prospective memory tasks: A preliminary study

The objective of the present study was to evaluate the interest of an assistance robot to help caregivers manage the activities of daily living of institutionalized elderly people with Alzheimer’s disease. Twenty-three institutionalized persons (60% women; average age 89; average MMSE score of 20.8) with Alzheimer Disease (AD) were recruited and invited to participate in prospective memory exercise sessions, conducted either by a caregiver or by a robot (assisted by a caregiver). They were divided into two groups equivalent in age, level of education and MMSE score. In addition, the sessions were recorded in order to compare the interaction behaviors of the 2 groups, using a validated observation grid. The results showed that: 1) prospective memory tasks are better performed when offered by the caregiver; 2) when strong help linked to the recovery index is provided to perform the tasks, the robot or caregiver no longer show significant differences; 3) participants interact more with the caregiver than with the robot. Our results confirm that the use of companion robots is a promising way to help caregivers manage the daily activities of people with Alzheimer’s. However, to optimize this assistance, further investigations should be conducted to improve the fluidity of interactions between the patient and the robot.

A gamified social robotics platform for intensive therapies in neurorehabilitation

The use of social assistive robots for interactive stimulation has strong potential in neurorehabilitation therapies. It is of particular interest in the case of pediatric patients to promote children’s motivation and adherence, specially when those robots are able of guide gamified activities, as it is the case of NAOTherapist. NAOTherapist is a Social Assistive Robotics (SAR) platform for hands-off rehabilitation based on upper-limb activities, that was originally designed for pediatric patients with Cerebral Palsy (CP) or Obstetric Braxial Plexus Palsy (OBPP). Formerly, it endowed the therapists with tools to perform rehabilitation exercises. This paper proposes the gamification of NAOTherapist in order to incorporate additional characteristics which allow its intensive use in new rehabilitation procedures, such as the Hand-Arm Bimanual Intensive Therapy (HABIT). This intensive therapy setting involves daily activities in several consecutive days, which require a strong engagement of the patients with the therapeutic methods and the acceptation of the NAOTherapist as a rehabilitation system. The gamified system shows very accurate results considering the different aspects defined in the USUS methodology; namely Usability, Social acceptance, User experience and Societal impact.

‘Social’ robot and social relations in care settings: Undefined positionality and fixed temporality

Socially assistive robots in eldercare settings, i.e. ‘social’ robots, are currently being promoted and studied, particularly in Japan. Among these studies, clinical evaluation of their effectiveness in experimental research predominates, while studies that critically and analytically describe relations between actors in long-term care settings where robots are present are growing but still scarce. In this paper, we argue that understanding how older adults facing the loss of autonomy and their caregivers interact with robots in relational terms is helpful to explain the usage and non-usage of, and eventual resistance to social robots entering into care settings. This is why, in order to understand human relationships with social robots in elder care homes, this paper combines a ‘script’ approach and a ‘critical care’ one. Based on content analysis of a unique set of reports on trials of a social robot in multiple care facilities in Japan from 2018 to 2020, as well as interviews with stakeholders and ethnographic observations conducted in 2022, we answer two questions: 1) how do social robots shape social relations of care? 2) how do social robots affect social relations between care professionals, care recipients and robots? We proceed to discuss two of the characteristics emphasised in the ethics of care and examine them in depth: the positional and temporal aspects. Our major result is that, while the robot was easily adaptable to care environments because its position in relationships is not defined, embedded clock time flow in the robot was objective and linear, which indicates that some robot-created situations were seen as problematic by actors in care settings.

“I Want to Send a Message to My Friend”: Exploring the Shift of Agency to Older Adults in HRI

Communication among some older adults is affected by cognitive and mobility impairments. This increases isolation, particularly for those residing in care homes, and leads to accelerated cognitive decline. Previous research has leveraged assistive robots to promote recreational routines and communication among older adults, with the robot leading the interaction. However, older adults could have more agency in the interaction, as robots could extend elders’ intentions and needs. Therefore, we explored an approach whereby the robot’s agency is shifted to the older adults who lead the interaction by commanding a robot’s actions using interactive physical blocks (tangible blocks). We conducted sessions with 22 care home dwellers where they could exchange messages and objects using the robot. Based on older adults’ observed behaviors during the sessions and perspectives gathered from interviews with geriatric professionals, we reflect on the opportunities and challenges for increased user agency and the asymmetries that emerged from differing abilities and personality traits. Our qualitative results highlight the potential of robotic approaches to extend the agency and communication of older adults, anchored on human values, such as the exchange of affection, collaboration, and competition.

Cognitive Classifier of Hand Gesture Images for Automated Sign Language Recognition: Soft Robot Assistance Based on Neutrosophic Markov Chain Paradigm

In recent years, Sign Language Recognition (SLR) has become an additional topic of discussion in the human–computer interface (HCI) field. The most significant difficulty confronting SLR recognition is finding algorithms that will scale effectively with a growing vocabulary size and a limited supply of training data for signer-independent applications. Due to its sensitivity to shape information, automated SLR based on hidden Markov models (HMMs) cannot characterize the confusing distributions of the observations in gesture features with sufficiently precise parameters. In order to simulate uncertainty in hypothesis spaces, many scholars provide an extension of the HMMs, utilizing higher-order fuzzy sets to generate interval-type-2 fuzzy HMMs. This expansion is helpful because it brings the uncertainty and fuzziness of conventional HMM mapping under control. The neutrosophic sets are used in this work to deal with indeterminacy in a practical SLR setting. Existing interval-type-2 fuzzy HMMs cannot consider uncertain information that includes indeterminacy. However, the neutrosophic hidden Markov model successfully identifies the best route between states when there is vagueness. This expansion is helpful because it brings the uncertainty and fuzziness of conventional HMM mapping under control. The neutrosophic three membership functions (truth, indeterminate, and falsity grades) provide more layers of autonomy for assessing HMM’s uncertainty. This approach could be helpful for an extensive vocabulary and hence seeks to solve the scalability issue. In addition, it may function independently of the signer, without needing data gloves or any other input devices. The experimental results demonstrate that the neutrosophic HMM is nearly as computationally difficult as the fuzzy HMM but has a similar performance and is more robust to gesture variations.

Sheet‐Based Fluidic Diodes for Embedded Fluidic Circuitry in Soft Devices

The recent development of soft fluidic analogs to electrical components aims to reduce the demand for rigid and bulky electromechanical valves and hard electronic controllers within soft robots. This ongoing effort is advanced in this work by creating sheet‐based fluidic diodes constructed from readily available flexible sheets of polymers and textiles using a layered fabrication approach amenable to manufacturing at scale. These sheet‐based fluidic diodes restrict reverse flow over a wide range of differential pressures—exhibiting a diodicity (the ratio of resistance to reverse vs forward flow) of approximately 100×—to address functional limitations exhibited by prior soft fluidic diodes. By harnessing the diode's highly unidirectional flow, soft devices capable of 1) facilitating the capture and storage of pressurized fluid, 2) performing Boolean operations using diode logic, 3) enabling binary encoding of circuits by preventing interactions between different pressurized input lines, and 4) converting oscillating input pressures to a direct current‐like, positively phased output are realized. This work exemplifies the use of fluidic diodes to achieve complex patterns of actuation and unique capabilities through embedded fluidic circuitry, enabling future development of sheet‐based systems—including wearable and assistive robots made from textiles—as well as other soft robotic devices.

Exploring Human-Exoskeleton Interaction Dynamics: An In-Depth Analysis of Knee Flexion-Extension Performance across Varied Robot Assistance-Resistance Configurations.

Knee rehabilitation therapy after trauma or neuromotor diseases is fundamental to restore the joint functions as best as possible, exoskeleton robots being an important resource in this context, since they optimize therapy by applying tailored forces to assist or resist movements, contributing to improved patient outcomes and treatment efficiency. One of the points that must be taken into account when using robots in rehabilitation is their interaction with the patient, which must be safe for both and guarantee the effectiveness of the treatment. Therefore, the objective of this study was to assess the interaction between humans and an exoskeleton during the execution of knee flexion-extension movements under various configurations of robot assistance and resistance. The evaluation encompassed considerations of myoelectric activity, muscle recruitment, robot torque, and performed movement. To achieve this, an experimental protocol was implemented, involving an individual wearing the exoskeleton and executing knee flexion-extension motions while seated, with the robot configured in five distinct modes: passive (P), assistance on flexion (FA), assistance on extension (EA), assistance on flexion and extension (CA), and resistance on flexion and extension (CR). Results revealed distinctive patterns of movement and muscle recruitment for each mode, highlighting the complex interplay between human and robot; for example, the largest RMS tracking errors were for the EA mode (13.72 degrees) while the smallest for the CR mode (4.47 degrees), a non-obvious result; in addition, myoelectric activity was demonstrated to be greater for the completely assisted mode than without the robot (the maximum activation levels for the vastus medialis and vastus lateralis muscles were more than double those when the user had assistance from the robot). Tracking errors, muscle activations, and torque values varied across modes, emphasizing the need for careful consideration in configuring exoskeleton assistance and resistance to ensure effective and safe rehabilitation. Understanding these human-robot interactions is essential for developing precise rehabilitation programs, optimizing treatment effectiveness, and enhancing patient safety.

Adopting Graph Neural Networks to Analyze Human-Object Interactions for Inferring Activities of Daily Living.

Human Activity Recognition (HAR) refers to a field that aims to identify human activities by adopting multiple techniques. In this field, different applications, such as smart homes and assistive robots, are introduced to support individuals in their Activities of Daily Living (ADL) by analyzing data collected from various sensors. Apart from wearable sensors, the adoption of camera frames to analyze and classify ADL has emerged as a promising trend for achieving the identification and classification of ADL. To accomplish this, the existing approaches typically rely on object classification with pose estimation using the image frames collected from cameras. Given the existence of inherent correlations between human-object interactions and ADL, further efforts are often needed to leverage these correlations for more effective and well justified decisions. To this end, this work proposes a framework where Graph Neural Networks (GNN) are adopted to explicitly analyze human-object interactions for more effectively recognizing daily activities. By automatically encoding the correlations among various interactions detected through some collected relational data, the framework infers the existence of different activities alongside their corresponding environmental objects. As a case study, we use the Toyota Smart Home dataset to evaluate the proposed framework. Compared with conventional feed-forward neural networks, the results demonstrate significantly superior performance in identifying ADL, allowing for the classification of different daily activities with an accuracy of 0.88. Furthermore, the incorporation of encoded information from relational data enhances object-inference performance compared to the GNN without joint prediction, increasing accuracy from 0.71 to 0.77.