← Back

/

Control and Systems Engineering

The design of control systems for dynamic processes, including feedback control, robotics, automation, adaptive systems, and the integration of sensors and actuators in intelligent systems

3 papers in this specialization

Paperzilla Papers in Control and Systems Engineering

Learning Unified Force and Position Control for Legged Loco-Manipulation

This paper presents a novel unified policy for legged robots that enables joint force and position control without relying on physical force sensors, instead estimating forces from historical robot states. Through reinforcement learning and experiments on quadrupedal and humanoid robots, the policy demonstrates enhanced success rates (approx. 39.5% higher) in contact-rich tasks like wiping and opening cabinets compared to position-only methods. However, the force estimation accuracy can degrade in high-frequency interactions and at the edges of the robot's workspace, and sim-to-real gaps exist.

Potential, challenges and future directions for deep learning in prognostics and health management applications

This paper reviews the potential, challenges, and future directions of deep learning in prognostics and health management (PHM). It highlights the opportunities and difficulties of applying deep learning to PHM applications, discussing aspects such as data processing, model development, and practical considerations for industrial settings.

★

☆

1-s2.0-S0952197620301184-main.pdf

Jul 14, 10:36 AM

The effect of gamma value on support vector machine performance with different kernels

This paper explored the effect of the gamma parameter on SVM classifier performance using polynomial, RBF, and sigmoid kernels across five datasets. The results indicated an uneven influence of gamma on accuracy, with polynomial and sigmoid kernels showing greater sensitivity to changes in gamma than the RBF kernel. Optimal gamma values varied across datasets and kernel functions, suggesting the need for careful parameter tuning.