Postural Control Mechanisms in Healthy Adults in Sitting and Standing Positions

Serra-Añó, Pilar; Bueno, Laura López; García‐Massó, Xavier; Pellicer-Chenoll, Maite; Moreno, Luís Millán González

doi:10.2466/26.25.pms.121c10x4

Cited by 15 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to assess the performance of the trained AI agent, we conducted testing with randomly generated drop distances while fixing the ground forward and lateral inclination to 0 deg. As shown in Figure 4-a, the iterative agent does outperform the baseline agents within a drop range of [2,4] but performs similarly as the drop distance increases. It is worth noting that fine tuning the coordination neural network does allow for better generalisation over drop distance as shown by comparing the box plots of Baseline and Baseline Refined.…”

Section: Generalisation Over Falling Distancementioning

confidence: 88%

“…motion capture) and biomechanics (e.g. kinesiology) [2][3][4][5][6][7]. While many studies rely on collecting motion capture data (MO-CAP) from participants; studies investigating injuries and surgeries may not have the luxury of trying new setups on humans and thus have to rely on biomechanic simulation such as OpenSim [8], Anybody [9] and, most recently, MASS [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Biomechanic Posture Stabilisation via Iterative Training of Multi-policy Deep Reinforcement Learning Agents

Hossny¹,

Iskander²

2020

Preprint

View full text Add to dashboard Cite

It is not until we become senior citizens do we recognise how much we took maintaining a simple standing posture for granted. It is truly fascinating to observe the magnitude of control the human brain exercises, in real time, to activate and deactivate the lower body muscles and solve a multi-link 3D inverted pendulum problem in order to maintain a stable standing posture. This realisation is even more apparent when training an artificial intelligence (AI) agent to maintain a standing posture of a digital musculoskeletal avatar due to the error propagation problem. In this work we address the error propagation problem by introducing an iterative training procedure for deep reinforcement learning which allows the agent to learn a finite set of actions and how to coordinate between them in order to achieve a stable standing posture. The proposed training approach allowed the agent to increase standing duration from 4 seconds using the traditional training method to 348 seconds using the proposed method. The proposed training method allowed the agent to generalise and accommodate perception and actuation noise for almost 108 seconds.

show abstract

Section: Generalisation Over Falling Distancementioning

confidence: 88%

Section: Introductionmentioning

confidence: 99%

Biomechanic Posture Stabilisation via Iterative Training of Multi-policy Deep Reinforcement Learning Agents

Hossny¹,

Iskander²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…From this is logically derived the question: Why are trial lenses used in a seated position? [38,39].…”

Section: Introductionmentioning

confidence: 99%

The Refraction Assessment and the Electronic Trial Frame Measurement during Standing or Sitting Position Can Affect Postural Stability

Massimo

Nart

Messina

et al. 2022

IJERPH

View full text Add to dashboard Cite

Vision has been shown to influence body posture. The purpose of this study is to investigate the correlations between visual acuity and body postural control both in a standing and seated position. This cohort study included 37 patients examined using Adaptica’s (Italy) Kaleidos and VisionFit. Objective refraction was measured with Kaleidos both in a standing and seated position by the same operator and in the same environmental conditions. The parameters obtained with the device were binocular refraction, monocular refraction, pupil distance, pupil size, head tilt, gaze, phorias, and tropias. The results obtained were then subjectively tested using VisionFit: an electronic trial frame with phoropter functionalities. The study’s outcome revealed that the differences in the visual acuity parameters obtained in standing and seated positions were statistically significant; the Student’s t-test showed a p-value < 0.001 in all parameter averages. Automated refraction is widely being performed and postural control can affect the visual acuity parameters; therefore, it is relevant to consider the possibility of measuring in orthostatism. It might be appropriate to take into account the possibility of measuring in orthostatism and wearing trial frames in orthostatic conditions as well as walking freely around the room, looking outside of a window, sitting, and reading.

show abstract

“…Studies of the biomechanical and physiological aspects of human movement were conducted to understand the neural control needed to maintain the type of movement desired [4,6,[10][11][12][13]. Most of these studies included human participants recruitment, data collection using motion capture techniques, force plates and/or electromyography electrodes (EMGs).…”

Section: Introductionmentioning

confidence: 99%

Just Don’t Fall: An AI Agent’s Learning Journey Towards Posture Stabilisation

Hossny

Iskander

2020

View full text Add to dashboard Cite

Learning to maintain postural balance while standing requires a significant, fine coordination effort between the neuromuscular system and the sensory system. It is one of the key contributing factors towards fall prevention, especially in the older population. Using artificial intelligence (AI), we can similarly teach an agent to maintain a standing posture, and thus teach the agent not to fall. In this paper, we investigate the learning progress of an AI agent and how it maintains a stable standing posture through reinforcement learning. We used the Deep Deterministic Policy Gradient method (DDPG) and the OpenSim musculoskeletal simulation environment based on OpenAI Gym. During training, the AI agent learnt three policies. First, it learnt to maintain the Centre-of-Gravity and Zero-Moment-Point in front of the body. Then, it learnt to shift the load of the entire body on one leg while using the other leg for fine tuning the balancing action. Finally, it started to learn the coordination between the two pre-trained policies. This study shows the potentials of using deep reinforcement learning in human movement studies. The learnt AI behaviour also exhibited attempts to achieve an unplanned goal because it correlated with the set goal (e.g., walking in order to prevent falling). The failed attempts to maintain a standing posture is an interesting by-product which can enrich the fall detection and prevention research efforts.

show abstract

Postural Control Mechanisms in Healthy Adults in Sitting and Standing Positions

Cited by 15 publications

References 33 publications

Biomechanic Posture Stabilisation via Iterative Training of Multi-policy Deep Reinforcement Learning Agents

Biomechanic Posture Stabilisation via Iterative Training of Multi-policy Deep Reinforcement Learning Agents

The Refraction Assessment and the Electronic Trial Frame Measurement during Standing or Sitting Position Can Affect Postural Stability

Just Don’t Fall: An AI Agent’s Learning Journey Towards Posture Stabilisation

Contact Info

Product

Resources

About