A researcher at has developed a new feedback system to remotely control mobile robots. This innovative research will allow robots to operate with minimal supervision and could eventually lead to a robot that can learn or even become autonomous.
The research, developed by Dr. Jagannathan Sarangapani, makes use of current formation moving robots and introduces a fault tolerant control design to improve the probability of completing a set task. Currently there is a lot of potential growth in this field, as very few robotic systems have this redundancy because of costs.
The new feedback system, funded in part by the National Science Foundation, will allow a follower robot to take over as the leader robot if the original leader has a system or mechanical failure. In a leader and follower formation, the lead robot is controlled through a nonholonomic system, meaning that the trajectory is set in advance, and the followers are tracing the same pattern that the leader takes by using sonar.
When a problem occurs and roles need to change to continue, the fault tolerant control system comes into use. It uses reinforcement learning and active critique, both inspired by behaviorist psychology to show how machines act in environments to maximize work rate, to help the new, unmanned robot to estimate its new course. Without this, the follower would not have a path to follow and the task would fail.
Reviewed 2013-10-03