Publication

Autonomy Artificial Intelligence Robotics (AAIR)
2013

TORIS: A SYSTEM FOR SMOOTH GROUND VEHICLE TELEOPERATION IN HIGH LATENCY CONDITIONS

by Karl C. Kluge; Alberto Lacaze; Zach La Celle; Steve Legowik; Karl Murphy; Rob Thomson

Abstract

Latencies as small as 170 msec significantly degrade ground vehicle teleoperation performance and latencies greater than a second usually lead to a “move and wait” style of control. TORIS (Teleoperation Of Robots Improvement System) mitigates the effects of latency by providing the operator with a predictive display showing a synthetic latency-corrected view of the robot’s relationship to the local environment and control primitives that remove the operator from the high-frequency parts of the robot control loops. TORIS uses operator joystick inputs to specify relative robot orientations and forward travel distances rather than rotational and translational velocities, with control loops on the robot making the robot achieve the commanded sequence of poses. Because teleoperated ground vehicles vary in sensor suite and on-board computation, TORIS supports multiple predictive display methods. Future work includes providing obstacle detection and avoidance capabilities to support guarded teleoperation and supervised autonomy in high-latency environments.