Human gait is a key biomarker for health, independence and quality of life. Advances in wearable inertial sensor technologies have paved the way for out-of-the-lab human gait analysis, which is important for the assessment of mobility and balance in natural environments and has applications in multiple fields from healthcare to urban planning. Automatic recognition of the environment where walking takes place is a prerequisite for successful characterisation of terrain-induced gait alterations. A key question which remains unexplored in the field is how minimum data requirements for high terrain classification accuracy change depending on the sensor placement on the body. To address this question, we evaluate the changes in performance of five canonical machine learning classifiers by varying several data sampling parameters including sampling rate, segment length, and sensor configuration. Our analysis on two independent datasets clearly demonstrate that a single inertial measurement unit is sufficient to recognise terrain-induced gait alterations, accuracy and minimum data requirements vary with the device position on the body, and choosing correct data sampling parameters for each position can improve classification accuracy up to 40% or reduce data size by 16 times. Our findings highlight the need for adaptive data collection and processing algorithms for resource-efficient computing on mobile devices.

Abstract Automatic gait analysis in free‐living environments using inertial sensors requires individualized approach as local acceleration and velocity profiles vary with the walker and the topological properties of the environment (e.g., walking in the forest vs. walking on sand). Here, we propose a smartphone‐based gait assessment architecture which consists of two data processing modules. The first module employs a set of personalized classifiers for automatic recognition of the walking environment. The second module provides accurate step time estimates by selecting the optimal filtering frequency tailored to the predicted environment. The performance of the architecture was evaluated using experimental data collected from 10 participants walking in 10 different conditions typically encountered during daily living. Compared with ground truth data, the architecture successfully recognized the walking environments; the percentage of correctly classified instances was above 92%. It also estimated step time with high accuracy; the mean absolute error was less than 10 ms, outperforming or at the very least matching the performance levels achieved in controlled laboratory trials (indoor flat surface walking). Compared with using one filtering frequency for all environments, using optimal frequency tailored to each environment reduced step time estimation error by more than 39%. To the best of our knowledge, this is the first study which successfully demonstrates that parameter tuning can improve gait characterization in outdoor environments. However, further research using a larger data set (including more participants with varying demographics and degree of impairment) is needed to confirm this result. Our findings highlight the importance of environment‐aware gait analysis, and lay the groundwork for a smartphone‐based technology that can be used in the community.

Underwater vehicles do not localise or navigate with respect to the flow, an ability needed for many underwater tasks. In this paper we implement rheotaxis behaviour in a fish robot, a behaviour common to many aquatic species. We use two pressure sensors on the head of the robot to identify the pressure differences on the left and right side and control the heading of the fish robot by turning a servo-motor actuated tail. The controller is inspired by the Braitenberg vehicle 2b, a simple biological model of tropotaxis, that has been used in many robotic applications. The experiments, conducted in a flow pipe with a uniform flow, show that the robot is able to orient itself, and keep the orientation, to the incoming current. Our results demonstrate that guidance of a fish robot relative to a flow can be implemented as a simple rheotaxis behaviour using two sensors and a Braitenberg 2b controller.

Turbulent flows are often treated as a noisy environment by control algorithms of underwater robots. However, aquatic animals such as fish have learned to take advantage of certain unsteady flow. Periodic complex flow, such as that found in the wake of cylinders has been shown to offer energy saving opportunities to fish. We built a fish-like robot with an integrated pressure sensor array housed in the head. The robot can control its tail beat synchronization with respect to the periodic oscillations in the flow behind a cylinder. We show that vortices, represented here by pressure maxima, can be detected and exploited to increase the swimming efficiency of the robot fish while it remains rigidly mounted to a force plate. Force measurements show an efficiency gain of 23% when the tail beat of the robotic fish is synchronized at a particular phase lag.

Within the broader scope of underwater biomimetics, in this paper we address the relevance of factors such as shape and elasticity distribution in the ability of a compliant device to imitate the kinematic behaviour of a fish. We assess the viability of myometry as a tool to determine candidate mechanical parameters without relying solely on analytical models; we show that we can obtain elasticity distributions that are both consistent with previous theoretical investigations and experimentally better adherent to the passive kinematics of a biological embodiment (rainbow trout).

Increasingly, personalised robots - robots especially designed and programmed for an individual's needs and preferences - are being used to support humans in their daily lives, most notably in the area of service robotics. Arguably, the closer the robot is programmed to the individual's needs, the more useful it is, and we believe that giving people the opportunity to program their own robots, rather than programming robots for them, will push robotics research one step further in the personalised robotics field. However, traditional robot programming techniques require specialised technical skills from different disciplines and it is not reasonable to expect end-users to have these skills. In this paper, we therefore present a new method of obtaining robot control code - programming by demonstration through system identification - which algorithmically and automatically transfers human behaviours into robot control code, using transparent, analysable mathematical functions. Besides providing a simple means of generating perception-action mappings, they have the additional advantage that can also be used to form hypotheses and theoretical analysis of robot behaviour. We demonstrate the viability of this approach by teaching a Scitos G5 mobile robot to achieve wall following and corridor passing behaviours.