Publication

Autonomy Artificial Intelligence Robotics (AAIR)
2010

ROBOTIC IED DETECTION USING SUPERVISED AUTONOMY TO REDUCE OPERATOR STRESS AND FATIGUE

by Brian Frederick; Daniel Rodgers; John Martin; John Hutchison

Abstract

Autonomous robots can maneuver into dangerous situations without endangering Soldiers. The Soldier tasked with the supervision of a route clearing robot vehicle must be located beyond the physical effect of an exploding IED but close enough to understand the environment in which the robot is operating. Additionally, mission duration requirements discourage the use of low level, fatigue inducing, teleoperation. Techniques are needed to reduce the Soldier’s mental stress in this demanding situation, as well as to blend the high level reasoning of a remote human supervisor with the local autonomous capability of a robot to provide effective, long term mission performance. GDRS has developed an advanced supervised autonomy version of its Robotics Kit (GDRK) under the Robotic Mounted Detection System (RMDS) program that provides a cost effective, high-utility automation solution that overcomes the limitations and burden of a purely teleoperated system. GDRK is a modular robotic appliqué operated by a common controller capable of transforming any tactical platform or payload into an optionally manned system. RMDS is a government program to enable robotic control of a Husky route clearance vehicle with a mine detection sensor payload. This program provides the user with standard teleoperation control of the vehicle as well as semi-autonomous modes including cruise control, precision waypoint navigation with operator error correction and a visual mode allowing the operator to enter waypoints in the current video feed. The use of autonomy is tailored to give the operator maximum control of the robotic vehicle‘s path while minimizing the effort required to maintain the desired route. Obstacle avoidance sensors are employed to protect the mine detection sensor. Practical issues and lessons learned during integration and testing are presented.