In this paper, a novel approach for recognition of walking activities and gait events with wearable sensors is presented. This approach, called adaptive Bayesian inference system (BasIS), uses a probabilistic formulation with a sequential analysis method, for recognition of walking activities performed by participants. Recognition of gait events, needed to identify the state of the human body during the walking activity, is also provided by the proposed method. In addition, the BasIS system includes an adaptive action-perception method for the prediction of gait events. The adaptive approach uses the knowledge gained from decisions made over time by the inference system. The action-perception method allows the BasIS system to autonomously adapt its performance, based on the evaluation of its own predictions and decisions made over time. The proposed approach is implemented in a layered architecture and validated with the recognition of three walking activities:level-ground, ramp ascent and ramp descent. The validation process employs real data from three inertial measurements units attached to the thigh, shanks and foot of participants while performing walking activities. The experiments show that mean decision times of 240 ms and 40 ms are needed to achieve mean accuracies of 99.87% and 99.82% for recognition of walking activities and gait events, respectively. The validation experiments also show that the performance, in accuracy and speed, is not significantly affected when noise is added to sensor measurements. These results show that the proposed adaptive recognition system is accurate, fast and robust to sensor noise, but also capable to adapt its own performance over time. Overall, the adaptive BasIS system demonstrates to be a robust and suitable computational approach for the intelligent recognition of activities of daily living using wearable sensors.

In this paper, we present a novel and robust Bayesian approach for autonomous active exploration of unknown objects using tactile perception and sensorimotor control. Despite recent advances in tactile sensing, robust active exploration remains a challenging problem, which is a major hurdle to the practical deployment of tactile sensors in robots. Our proposed approach is based on a Bayesian perception method that actively controls the sensor with local small repositioning movements to reduce perception uncertainty, followed by explorative movements based on the outcome of each perceptual decision making step. Two sensorimotor control strategies are proposed for improving the accuracy and speed of the active exploration that weight the evidence from previous exploratory steps through either a weighted prior or weighted posterior. The methods are validated both off-line and in real-time on a contour following exploratory procedure. Results clearly demonstrate improvements in both accuracy and exploration time when using the proposed active methods compared to passive perception. Our work demonstrates that active perception has the potential to enable robots to perform robust autonomous tactile exploration in natural environments. Active tactile sensing with biomimetic and soft fingertip sensor.Bayesian perception for intelligent control of robot movements under the presence of uncertainty.Sensorimotor control strategies that improve tactile perception accuracy and speed.Actionperception loop for exploration of unknown object shapes using robot touch and an exploratory procedure.

Wearable assistive robotics is an emerging technology with the potential to assist humans with sensorimotor impairments to perform daily activities. This assistance enables individuals to be physically and socially active, perform activities independently, and recover quality of life. These benefits to society have motivated the study of several robotic approaches, developing systems ranging from rigid to soft robots with single and multimodal sensing, heuristics and machine learning methods, and from manual to autonomous control for assistance of the upper and lower limbs. This type of wearable robotic technology, being in direct contact and interaction with the body, needs to comply with a variety of requirements to make the system and assistance efficient, safe and usable on a daily basis by the individual. This paper presents a brief review of the progress achieved in recent years, the current challenges and trends for the design and deployment of wearable assistive robotics including the clinical and user need, material and sensing technology, machine learning methods for perception and control, adaptability and acceptability, datasets and standards, and translation from lab to the real world.

Motivated by the impact of superresolution methods for imaging, we undertake a detailed and systematic analysis of localization acuity for a biomimetic fingertip and a flat region of tactile skin. We identify three key factors underlying superresolution that enable the perceptual acuity to surpass the sensor resolution: 1) the sensor is constructed with multiple overlapping, broad but sensitive receptive fields; 2) the tactile perception method interpolates between receptors (taxels) to attain subtaxel acuity; and 3) active perception ensures robustness to unknown initial contact location. All factors follow from active Bayesian perception applied to biomimetic tactile sensors with an elastomeric covering that spreads the contact over multiple taxels. In consequence, we attain extreme superresolution with a 35-fold improvement of localization acuity (0.12 mm) over sensor resolution (4 mm). We envisage that these principles will enable cheap high-acuity tactile sensors that are highly customizable to suit their robotic use. Practical applications encompass any scenario where an end-effector must be placed accurately via the sense of touch.

Recognition of movement is a crucial process to assist humans in activities of daily living such as walking. In this work, a high-level method for simultaneous recognition of locomotion and gait phases using wearable sensors is presented. A Bayesian formulation is employed to iteratively accumulate evidence to reduce uncertainty, and to improve the recognition accuracy. This process uses a sequential analysis method to autonomously make decisions, whenever the recognition system perceives that there is enough evidence accumulated. We use data from three wearable sensors, attached to the thigh, shank and foot of healthy humans. Level-ground walking, ramp ascent and descent activities are used for data collection and recognition. In addition, an approach for segmentation of the gait cycle for recognition of stance and swing phases is presented. Validation results show that the simultaneous Bayesian recognition method is capable to recognise walking activities and gait phases with mean accuracies of 99.87% and 99.20%. This process requires a mean of 25 and 13 sensor samples to make a decision for locomotion mode and gait phases respectively. The recognition process is analysed using different levels of confidence to show that our method is highly accurate, fast and adaptable to specific requirements of accuracy and speed. Overall, the simultaneous Bayesian recognition method demonstrates its benefits for recognition using wearable sensors, which can be employed to provide reliable assistance to humans in their walking activities.