Turning a robot, particularly an under-actuated bipedal humanoid robot, is challenging. Several methods proposed in the literature for producing human-like motion in such robots are innovative but are limited in their range of motion. This paper presents an approach to control the orientation of a robot using a control moment gyroscope (CMG). A demonstration platform is developed to test this concept and physical experiments are conducted to determine the prototype's turning range and performance. This concept is then extended to a backpack mount where trials are conducted using human subjects to estimate the performance of the system that can potentially be used to turn bipedal humanoid robots.

The railroad industry expends significant effort to increase operational safety and efficiency by using a variety of sensors for machine health monitoring and inspection purposes. This paper proposes to advance rail technology even further to use similar sensor data for the control of a robotic system designed to automate the uncoupling of freight cars, a hazardous operation that currently requires human operators to interact with moving trains. To automate this process, an intelligent robotic system was developed to detect, track, approach, grasp, and manipulate semi-constrained objects on equipment in motion. This work presents a system prototype that utilizes machine vision, force feedback, and complex end-effector technology capable of autonomously uncoupling full-scale freight cars using visual and tactile feedback. Laboratory tests have proven that modern robotic and sensing hardware can be used to reliably separate pairs of rolling stock at 3.25 kilometers per hour. The results to date suggest that speeds of up to 7 km/h are feasible for a system deployed in a rail yard.