The field of robotic systems control is moving towards more efficient and adaptive methods, with a focus on overcoming the challenges of non-linearity, time delays, and uncertainty. Recent developments have highlighted the potential of learning-based approaches, such as neural networks and neuromorphic computing, in achieving smoother and more robust control. These methods have been successfully applied to various robotic systems, including fixed-wing aerial vehicles, soft robots, and robotic manipulators. Notably, innovative control schemes, such as model predictive control and sliding mode control, have been improved upon and extended to address specific challenges in these systems. Some noteworthy papers in this area include: The paper on $\pi$-MPPI, which introduces a projection filter to achieve smooth optimal control of fixed-wing aerial vehicles. The paper on neural networks for on-chip model predictive control, which presents a method for building optimized training datasets and demonstrates its effectiveness in controlling Type-1 Diabetes. The paper on embodied neuromorphic control, which proposes a neuromorphic control framework for controlling 7 degree-of-freedom robotic manipulators and achieves significant improvements in control accuracy. The paper on adaptive task space non-singular terminal super-twisting sliding mode control, which presents a new controller for robust trajectory tracking of a 7-DOF robotic manipulator and demonstrates its effectiveness in simulations and hardware experiments.