Search

Human activity recognition using wearable and mobile devices is used for decades to monitor humans' daily behaviours. In recent years as smartphones being widely integrated into our daily lives, the use of smartphone's built-in sensors in human activity recognition has been receiving more attention, in which smartphone accelerometer plays the main role. However, in comparison to the standard machine, when developing human activity recognition using a smartphone, the limitations such as processing capability and energy consumption should be taken into consideration, and therefore, a trade-off between performance and computational complexity should be considered. In this paper, we shed light on the importance of feature selection and its impact on simplifying the activity classification process, which enhances the computational complexity of the system. The novelty of this work is related to identifying the most efficient features for the detection of each individual activity uniquely. In an experimental study with human users and using different smartphones, we investigated how to achieve an optimal feature set, using which the system complexity can be decreased while the activity recognition accuracy remains high. For that, in the considered scenario, we instructed the participants to perform different activities, including static, dynamic, going up and down the stairs, and walking fast and slow while freely holding a smartphone in their hands. To evaluate the obtained optimal feature set implementing two major classification algorithms, the decision tree and the Bayesian network, we investigated activity recognition accuracy for different activities. We further evaluated the optimal feature set by comparing the performance of the activity recognition system using the optimal feature set and three feature sets taken from the state-of-the-art. The experimental results demonstrated that replacing a large number of conventional features with an optimal feature set has only a negligible impact on the overall activity recognition system performance while it can significantly decrease the system's complexity, which is essential for smartphone-based systems. [ABSTRACT FROM AUTHOR]

In human-robot teaming, one of the crucial keys for the team's success is that the robot and human teammates can collaborate accordingly in a coordinated manner. Each teammate should be aware of what the other teammate is going to perform and likely to need. In this context, a robot is expected to understand human teammate intention and performance and explain its actions and decisions and its rationale to its teammate. In addition, the capability to model the expectation of a human teammate empowers the robot to collaborate with human understandably and expectedly, leading to effective teaming. Through forming mental modelling, the robot can understand the impact of its own behaviour on the mental model of the human. In addition, the desirable traits in human-robot teaming, including fluent behaviour, adaptability, trust-building, effective communication, and explainability, can be achieved through mental modelling. In this work, we introduce a scenario for human-robot teaming considering all the five desirable traits in teaming with the main focus on explainability and effective communication. Using a general model reconciliation, the expectation of the human teammate of the robot can be modelled, and the explanation can be generated. In a considered scenario including Care-O-bot 4 service robot and a human teammate, we assume that the robot detects the human's current task (analysing his body gesture) and predicts his following action and his expectation from the robot. In a reciprocal interdependence task, the robot coordinates his behaviour and acts accordingly by picking up the relevant tool. Through explanation and communication robot further offers the outcome of his decision to the human teammate and adapts its action by handing the tool to the human upon his desire. [ABSTRACT FROM AUTHOR]

Nowadays, smartphones are gradually being integrated in our daily lives, and they can be considered powerful tools for monitoring human activities. However, due to the limitations of processing capability and energy consumption of smartphones compared to standard machines, a trade-off between performance and computational complexity must be considered when developing smartphone-based systems. In this paper, we shed light on the importance of feature selection and its impact on simplifying the activity classification process which enhances the computational complexity of the system. Through an in-depth survey on the features that are widely used in state-of-the-art studies, we selected the most common features for sensor-based activity classification, namely conventional features. Then, in an experimental study with 10 participants and using 2 different smartphones, we investigated how to reduce system complexity while maintaining classification performance by replacing the conventional feature set with an optimal set. For this reason, in the considered scenario, the users were instructed to perform different static and dynamic activities, while freely holding a smartphone in their hands. In our comparison to the state-of-the-art approaches, we implemented and evaluated major classification algorithms, including the decision tree and Bayesian network. We demonstrated that replacing the conventional feature set with an optimal set can significantly reduce the complexity of the activity recognition system with only a negligible impact on the overall system performance. [ABSTRACT FROM AUTHOR]

In this paper, we propose a reinforcement learning structure for auto-tuning PID gains by solving an optimal tracking control problem for robot manipulators. Capitalizing on the actor–critic framework implemented by neural networks, we achieve optimal tracking performance, estimating unknown system dynamics simultaneously. The critic network is used to approximate the cost function, which serves as an indicator of control performance. With feedback from the critic, the actor network learns time-varying PID gains over time to optimize control input, thereby steering the system toward optimal performance. Furthermore, we utilize Lyapunov's direct method to demonstrate the stability of the closed-loop system. This approach provides an analytical procedure for a stable robot manipulator system to systematically adjust PID gains, bypassing the ad-hoc and painstaking process. The resultant actor–critic PID-like control exhibits stable adaptive and learning capabilities while maintaining a simple structure and inexpensive online computational demands. Numerical simulations underscore the effectiveness and advantages of the proposed actor–critic neural network PID control. [Display omitted] • Actor–critic learning-based adaptive PID control is proposed for robot manipulators. • Auto-tuning of PID gains is provided by solving an optimal tracking control problem. • The stability of the closed-loop system is guaranteed by Lyapunov's direct method. • Bearing the PID structure, the control is simple, inexpensive and easy to implement. • The optimal performance of the system is addressed based on RL learning properties. [ABSTRACT FROM AUTHOR]