Human activity recognition (HAR) is essential for the development of robots to assist humans in daily activities. HAR is required to be accurate, fast and suitable for low-cost wearable devices to ensure portable and safe assistance. Current computational methods can achieve accurate recognition results but tend to be computationally expensive, making them unsuitable for the development of wearable robots in terms of speed and processing power. This paper proposes a light-weight architecture for recognition of activities using five inertial measurement units and four goniometers attached to the lower limb. First, a systematic extraction of time-domain features from wearable sensor data is performed. Second, a small high-speed artificial neural network and line search method for cost function optimization are used for activity recognition. The proposed method is systematically validated using a large dataset composed of wearable sensor data from seven activities (sitting, standing, walking, stair ascent/descent, ramp ascent/descent) associated with eight healthy subjects. The accuracy and speed results are compared against methods commonly used for activity recognition including deep neural networks, convolutional neural networks, long short-term memory and convolutional–long short-term memory hybrid networks. The experiments demonstrate that the light-weight architecture can achieve a high recognition accuracy of 98.60%, 93.10% and 84.77% for seen data from seen subjects, unseen data from seen subjects and unseen data from unseen subjects, respectively, and an inference time of 85 $\mathsf{\mu }$s. The results show that the proposed approach can perform accurate and fast activity recognition with a reduced computational complexity suitable for the development of portable assistive devices.

Autonomous Underwater Vehicles (AUVs) are essential for applications such as seabed mapping, environmental monitoring, offshore infrastructure inspection, and search-and-rescue operations. However, achieving accurate trajectory tracking remains a fundamental challenge due to nonlinear and strongly coupled six-degree-of-freedom dynamics, hydrodynamic parameter uncertainties, environmental disturbances, and limitations introduced by sensor noise, actuator faults, and imperfect modeling of added mass, damping, and Coriolis–centripetal forces. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, this review systematically classifies trajectory-tracking control strategies for AUVs into three main categories. (i) Classical controllers, including PID and Sliding Mode Control (SMC), are analyzed for their simplicity, robustness, and ease of implementation. (ii) Intelligent controllers, such as Fuzzy Logic Control (FLC), Reinforcement Learning (RL), and Physics-Informed Neural Networks (PINNs), are reviewed for their adaptability, learning capabilities, and effectiveness in handling nonlinearities and time-varying disturbances, while addressing challenges related to data availability and computational cost. (iii) Hybrid approaches, including Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Physics-Informed Reinforcement Learning (PI-RL), Fault-Tolerant Control (FTC), and Sim-to-Real Transfer (SRT) techniques, are examined for their ability to integrate model-based reliability with data-driven adaptability and improve resilience under uncertainties, noise, and faults. Classical controllers provide structural simplicity and robustness but suffer reduced accuracy in highly nonlinear and noisy environments. Intelligent methods like RL and PINNs improve adaptability and reduce tracking errors but demand extensive data and computational resources. Hybrid approaches, particularly ANFIS and PI-RL, achieve high tracking accuracy and maintain robust performance under various uncertainties. Sim-to-Real Transfer (SRT) techniques further enhance real-world deployment. A meta-analysis of 120 peer-reviewed studies quantifies performance trends in terms of root-mean-square error (RMSE), settling time, robustness, and computational cost. The review highlights future research opportunities in domain randomization, adaptive fault-tolerant control, and physics-guided hybrid learning to enable reliable real-world AUV operations.

This manuscript presents the dynamic modeling process of an autonomous underwater vehicle considering all physical parameters related to the vehicle mass properties and geometry as well as acting hydrostatic/hydrodynamic forces & moments and the control action produced by a particular thruster configuration. Moreover, the paper introduces the LQR control algorithm implemented to fully control 4 degrees of freedom of vehicle motion simultaneously by assigning different thrust values to the vehicle thrusters to achieve stable depth control, steering angle control, roll and pitch angles' stabilization, in addition to controlling all linear and angular velocities of the vehicle relative to the body frame.

This paper proposes a computationally-efficient controller for an AUV which could be implemented using a single-purpose microcontroller. The AUV under study has a complex eight-thruster mechanical configuration. Such system imposes concerns like non-linear behavior, coupled dynamics and parameter uncertainty. An extensive study on vehicle kinematics/dynamics is proposed, followed by formulating a non-linear model for the test vehicle. Dynamic decoupling is applied to break the system into two sub-systems controlled using two independent simple controllers. An LQR controller is used for stabilizing vehicle depth and roll/pitch attitude. A self-tuning PID controller is used for trajectory tracking of surge velocity and yaw attitude. The combined LQR/Adaptive PID control architecture deals very well with noise and uncertainty with minimal computational effort. The controller is verified experimentally using multiple motion scenarios for a test AUV.

This manuscript describes the design methodology of a lower limb bipedal robot which was controlled to achieve a stable walking gait. The proposed design has 12 DOF to mimic human gait in the most daily living activities. The design process started by creating dynamically equivalent lower limb segments based on the human anthropometric data. A linear inverted pendulum model of human walking was developed to produce the trajectory of the robot center of mass (COM), and then generate the feet trajectories, as well as applying inverse kinematics model. An iterative optimization algorithm was used to find the angular correction. The system was simulated on MATLAB/SIMULINK simulation environment and the results were satisfactory.

This manuscript presents an effective method for online real time walking pattern generation using non-linear optimization of the model predictive control cost function under given constraints and applies this method to the NAO humanoid robot to achieve stable dynamic walking. This paper explains how the data generated is used to create a balanced robot center of mass trajectory along with smooth feet trajectories. The paper introduces a computationally efficient method for joint angle trajectory generation using inverse kinematics combined with iterative optimization to achieve desired center of mass trajectory. Finally the above mentioned modules were integrated together in MATLAB/SIMULINK environment to construct a NAO gait generation engine based on desired robot walking path input and the overall ZMP root mean square error in steady state is around 0.002 m which is very small relative to the support polygon area.