Biomechanics has strong implications in both medicine and robotics as it is concerned with the study of biological systems from an engineering point of view. In this work we propose a physics-based system for accurate simulation of dogpsilas spine at walking gait. The spinal column has been modeled as a set of rigid bodies, representing the vertebrae, connected by joints. Real-time dynamic simulation has been carried out from motion captured data collected from skin markers. A feedback controller has been developed for error minimization. The main contribution of the paper is the development of a tool for analyzing the forces acting on the spine. We report experiments performed with a boxer dog walking on a treadmill. Potential applications of this study involve bio-inspired robotics and computer graphics, as well as diagnostic applications for live animals.