Adaptive Feeding Robot With Multisensor Feedback and Predictive Control Using Autoregressive Integrated Moving Average–Feed-Forward Neural Network: Simulation Study
Background: Eating is a primary daily activity crucial for maintaining independence and quality of life. Individuals with neuromuscular impairments often struggle with eating due to limitations in current assistive devices, which are predominantly passive and lack adaptive capabilities. Objective: This study introduces an adaptive feeding robot that integrates time series decomposition, autoregressive integrated moving average (ARIMA), and feedforward neural networks (FFNN). The goal is to enhance feeding precision, efficiency, and personalisation, thereby promoting autonomy for individuals with motor impairments. Methods: The proposed feeding robot combines information from sensors and actuators to collect real-time data, i.e., facial landmarks, mouth status (open/closed), fork-to-mouth and plate distances, the force and angle required for food handling based on the food type. ARIMA and FFNN algorithms analyse data to predict user behaviour and adjust feeding actions dynamically. A strain gauge sensor ensures precise force regulation, an ultrasonic sensor optimises positioning, and facial recognition algorithms verify safety by monitoring mouth conditions and plate contents. Results: The combined ARIMA+FFNN model achieved an MSE of 0.008 and an R2 of 94%, significantly outperforming standalone ARIMA (MSE = 0.015, R2 = 85%) and FFNN (MSE = 0.012, R2 = 88%). Feeding success rate improved from 75% to 90% over 150 iterations (P < .001), and response time decreased by 28% (from 3.6 s to 2.2 s). ANOVA revealed significant differences in success rates across scenarios (F = 12.34, P = .002), with Scenario 1 outperforming Scenario 3 (P = .030) and Scenario 4 (P = .010). Object detection showed high accuracy (face detection precision = 97%, recall = 96%, 95% CI [94%, 99%]). Force application matched expected ranges with minimal deviation (Apple: 24 ± 1N; Strawberry: 7 ± 0.5N). Conclusions: Combining predictive algorithms and adaptive learning mechanisms enables the feeding robot to demonstrate substantial improvements in precision, responsiveness, and personalisation. These advancements underline its potential to revolutionise assistive technology in rehabilitation, delivering safe and highly person-alised feeding assistance to individuals with motor impairments, thereby enhancing their independence.