System Design and Implementation of UCF-MANUS—An Intelligent Assistive Robotic Manipulator
ABSTRACT This paper reports on the system design for integrating the various processes needed for end-to-end implementation of a smart assistive robotic manipulator. Specifically, progress is reported in the empowerment of the UCF-MANUS system with a suite of sensory, computational, and multimodal interface capabilities so that its autonomy can be made accessible to users with a wide range of disabilities. Laboratory experiments are reported to demonstrate the ability of the system prototype to successfully and efficiently complete object retrieval tasks. Benchmarking of the impact of the various interface modalities on user performance is performed via empirical studies with healthy subjects operating the robot in a simulated instrumental activities of daily living tasks setup. It is seen through a analysis of the collected quantitative data that the prototype is interface neutral and shows robustness to variations in the tasks and the environment. It is also seen that the prototype autonomous system is quantitatively superior to Cartesian control for all tested tasks under a “number of commands” metric, however, under a “time to task completion” metric, the system is seen to be superior for “hard” tasks but not for “easy” tasks.
- SourceAvailable from: Martin F. Stoelen[Show abstract] [Hide abstract]
ABSTRACT: The teleoperation of robot manipulators over the internet suffers from variable delays in the communications. Here we address a tele-assistance scenario, where a remote operator assists a disabled or elderly user on daily life tasks. Our behavioral approach uses local environment information from robot sensing to help enable faster execution for a given movement tolerance. This is achieved through a controller that automatically slows the operator down before having collisions, using a set of distributed proximity sensors. The controller is made to gradually increase the assistance in situations similar to those where collisions have occurred in the past. Thus adapting to the given operator, robot and task-set. Two controlled virtual experiments for tele-assistance with a 5 DOF manipulator were performed, with 300 ms and 600 ms mean variable round-trip delays. The results showed significant improvements in the median times of 12.6% and 16.5%, respectively. Improvements in the subjective workload were also seen with the controller. A first implementation on a physical robot manipulator is described.Paladyn 04/2015;