Within the context of Nonlinear Model Predictive Control (NMPC) design for autonomous mobile robots, which face challenges such as parametric uncertainty and measurement inaccuracies, focusing on dynamic modelling and parameter identification becomes crucial. This paper presents a novel safety-critical control framework for a mobile robot system that utilises NMPC with a prediction model derived entirely from noisy measurement data. The Sparse Identification of Nonlinear Dynamics (SINDY) is employed to predict the system's state under actuation effects. Meanwhile, the Control Barrier Function (CBF) is integrated into the NMPC as a safety-critical constraint, ensuring obstacle avoidance even when the robot's planned path is significantly distant from these obstacles. The closed-loop system demonstrates Input-to-State Stability (ISS) with respect to the prediction error of the learned model. The proposed framework undergoes exhaustive analysis in three stages, training, prediction, and control, across varying noise levels in the state data. Additionally, validation in Matlab and Gazebo illustrates that the NMPC-SINDY-CBF approach enables smooth, accurate, collision-free movement, even with measurement noise and short prediction times. Our findings, supported by tests conducted with the Husky A200 robot, confirm the approach's applicability in real-time scenarios.
Over the years, deep reinforcement learning (DRL) has shown great potential in mapless autonomous robot navigation and path planning. These DRL methods rely on robots equipped with different light detection and range (LiDAR) sensors with a wide field of view (FOV) configuration to perceive their environment. These types of LiDAR sensors are expensive and are not suitable for small-scale applications. In this paper, we address the performance effect of the LiDAR sensor configuration in DRL models. Our focus is on avoiding static obstacles ahead. We propose a novel approach that determines an initial FOV by calculating an angle of view using the sensor’s width and the minimum safe distance required between the robot and the obstacle. The beams returned within the FOV, the robot’s velocities, the robot’s orientation to the goal point, and the distance to the goal point are used as the input state to generate new velocity values as the output action of the DRL. The cost function of collision avoidance and path planning is defined as the reward of the DRL model. To verify the performance of the proposed method, we adjusted the proposed FOV by ±10° giving a narrower and wider FOV. These new FOVs are trained to obtain collision avoidance and path planning DRL models to validate the proposed method. Our experimental setup shows that the LiDAR configuration with the computed angle of view as its FOV performs best with a success rate of 98% and a lower time complexity of 0.25 m/s. Additionally, using a Husky Robot, we demonstrate the model’s good performance and applicability in the real world.