Demo @ Hannover Messe 2018

This work describes the development of a robotic system that acquires knowledge incrementally through human interaction where new objects and motions are taught on the fly. The robotic system developed was one of the five finalists in the KUKA Innovation Award competition and demonstrated during the Hannover Messe 2018 in Germany.

The main contributions of the system are

• A novel incremental object learning module - a deep learning based localization and recognition system - that allows a human to teach new objects to the robot

• An intuitive user interface for specifying 3D motion task associated with the new object

• A hybrid force-vision control module for performing compliant motion on an unstructured surface.

Demo @ IROS 2017

The hybrid force/vision control architecture allows the robot to follow an arbitrary user-defined path on unstructured surfaces.

[ICRA 2017]

This work present the design and implementation of a flexible force-vision-based interface; allowing local operators to visually specify a path constraint to a remote robot manipulator in an online fashion during the teleoperation. Using bilateral and unilateral configurations, we compare our system to direct teleoperation through user studies. The trials show that our system outperforms direct teleoperation and reduces cognitive load.

Our findings show that the performance of a unilateral teleop configuration with visual-force constraints surpass a bilateral teleop configuration in terms of displacement error and variance, as well as allowing users to complete tasks faster and with a smoother trajectory.

Work package 4 (WP4) - Control

• Developing Control algorithms for robot (Motion/Force) Interaction during Contact with environment

Work package 8 (WP8) - Robot Application Development Software

• Develop a Robot Application Development and Operating Environment (RADOE). RADOE is a software for developing robot applications and operating robotic systems. It has a graphical user interface for

  • task definition

  • robot setup, configuration and registration (including calibration)

  • robot programming

  • supervisory monitoring and control

  • user actions, including corrective actions and error recovery

[IEEE Trans. Automatic Control]

A model predictive control (MPC) approach for a switching linear system where the switching signal is prescribed with unknown future values. Under such a setting, the MPC optimization problem has to allow for all admissible switching sequences within a given horizon length. Such a formulation necessitates several other features: the use of a modified returnable set as the terminal constraint; the introduction of consistency constraints on the predicted controls; a min-max optimization criterion as the cost function; the splitting of the horizon into two portions for recursive feasibility consideration and exponential stability of the closed-loop system.

[Automatica]

This work introduces the concept and characterization of Disturbance-Dwell-Time invariance (DDT-invariance) and Constraint Admissible DDT-invariance (CADDT-invariance) for constrained systems with additive disturbance for switched systems. Using the characterization, necessary & sufficient conditions for DDT-invariance and algorithms for the computation of the minimal and maximal constraint admissible convex DDT-invariant sets are provided.

[Automatica]

This work introduces the concept of constraint admissible returnable sets for switching systems.

Main contributions include

• Characterization for returnable sets;

• Algorithm for computation of the maximal returnable set;

• Necessary and sufficient condition for asymptotic stability of the origin of the switching systems;

• Generalized Lyapunov functions for time-dependant switching systems;

• Algorithm for the computation of the minimal dwell time needed for stability.