Flexible Automation Driven by Demonstration: Leveraging Strategies that Simplify Robotics

An important question for production engineers is, "How do I automate this task?" In traditional industrial automation, e.g., a car factory, robots perform a small set of tasks for long periods of time. Robots are selected because their kinematic structure and strength suit the task requirements, and their motions are preprogrammed by a skilled programmer. In flexible manufacturing environments, tasks can change daily or hourly. The classic approach to automation is less suitable here; buying a dedicated robot for each set of tasks is inefficient, and coding each task is very time-consuming. Furthermore, qualified programmers with the requisite knowledge may not be available. To solve these problems, we propose a framework for modular robots that determines their structure and program based on human demonstrations.

[1]  Carme Torras,et al.  Learning Physical Collaborative Robot Behaviors From Human Demonstrations , 2016, IEEE Transactions on Robotics.

[2]  Christiaan J. J. Paredis,et al.  Kinematic Design of Serial Link Manipulators From Task Specifications , 1993, Int. J. Robotics Res..

[3]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[4]  Andrea Giusti,et al.  On-the-Fly Control Design of Modular Robot Manipulators , 2018, IEEE Transactions on Control Systems Technology.

[5]  Jan Peters,et al.  Probabilistic Movement Primitives , 2013, NIPS.

[6]  Matthias Althoff,et al.  Evolutionary cost-optimal composition synthesis of modular robots considering a given task , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

[8]  Darwin G. Caldwell,et al.  An Approach for Imitation Learning on Riemannian Manifolds , 2017, IEEE Robotics and Automation Letters.

[9]  Matthias Althoff,et al.  Cost-optimal composition synthesis for modular robots , 2016, 2016 IEEE Conference on Control Applications (CCA).

[10]  B. Siciliano,et al.  The unit quaternion: a useful tool for inverse kinematics of robot manipulators , 1999 .

[11]  B. Siciliano,et al.  Second-order kinematic control of robot manipulators with Jacobian damped least-squares inverse: theory and experiments , 1997 .

[12]  Andrea Giusti,et al.  Automatic centralized controller design for modular and reconfigurable robot manipulators , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  Alessandro De Luca,et al.  A modified newton-euler method for dynamic computations in robot fault detection and control , 2009, 2009 IEEE International Conference on Robotics and Automation.

[14]  Andrea Giusti,et al.  A task-driven algorithm for configuration synthesis of modular robots , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Aude Billard,et al.  Learning from Humans , 2016, Springer Handbook of Robotics, 2nd Ed..

[16]  Matthias Althoff,et al.  Online motion synthesis with minimal intervention control and formal safety guarantees , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).