Using the Whole Body Control online planner with TIAGo robot

Making programmers’ life (much, much) easier

Whole Body Control concept (based on the research done by N. Mansard, O. Stasse, P. Evrard, and A. Kheddar) when coding robot applications.

We are sure Whole Body Control is the future: robots with a high amount of Degrees of Freedom require software that abstracts the complexity of the platform for easily developing high-level applications. In this post, you will discover how does it work and to what extent it enhances robots like the mobile manipulator TIAGo!

PAL Robotics’ online planner is designed to command high-level tasks in an incredibly simple way so the robot robustly executes it, and the programmer skips any effort of low-level coding.

The Whole Body Control takes into account different goals, such as, for example, respecting joint limits, avoiding self-collision, or maintaining the end effector in a certain position or space volume. These objectives are defined by the programmer and are prioritized into a stack of tasks by the software.

Such tasks and their priority level are not rigid: they can be modified online. This makes a great difference, as the robot can instantly react to both unexpected events or changes. You can see it in this demo of TIAGo pointing at a fiducial marker, where the robot is constantly processing the new information and adapting its movements to accomplish the goal:

In essence, the Whole Body Control is useful for redundancy resolution. For instance, TIAGo’s 7 DoF arm can execute a task that takes only 3 DoF in multiple ways. The Whole Body Control optimizes cases like that and finds the optimal movement to accomplish with the high-level task.

From technical to practical: the power of Whole Body Control

Besides saving time when developing robotics applications, the main outcome of using Whole Body Control is to make the robot behaviour more robust, reasonable, interactive, safer and natural. PAL Robotics’ bipedal humanoids are mostly using it, especially for undertaking tasks while keeping the balance. TIAGo robot widely benefits from the Whole Body Control software too:

As an example, the Whole Body Control can equip TIAGo robot with admittance control thanks to the combination of this software plug-in with the feedback from its force/torque sensor, turning the robot compliant, which is crucial for doing tasks in which a human is involved.

Take an application for assisted living at home, or TIAGo as a collaborative robot in the Factory of the Future. Human-Robot Interaction demands robustness and fast reaction times. Other complex actions for a robot interacting with human equipment, like cleaning a table or opening a sliding door (without adapting the situation to the robot, of course), or the robot teleoperation in real time, are also much more effective with such versatile software.

Read more about AI in service robotics and deep learning.

Interested?

Why spending endless time to program a complex application when you can optimize it all? If you have a TIAGo robot, contact us to learn more about WBC and how you can implement this software into your mobile manipulator! Visit our blog about robotics and read all our news!

If you have any question or curiosity, don’t hesitate to contact us!

Related articles
Uncertainty as an evolutionary tool – the vision of Francesco Ferro, CEO of PAL Robotics
Read More

Uncertainty as an evolutionary tool – the vision of Francesco Ferro, CEO of PAL Robotics

In this edition of Humans of PAL, we’re thrilled to spotlight Francesco Ferro, the driving force behind PAL Robotics’ journey…
Luca Marchionni on pioneering legged and humanoid robots at PAL Robotics
Read More

Luca Marchionni on pioneering legged and humanoid robots at PAL Robotics

Luca Marchionni, CTO and Head of the legged business unit at PAL Robotics, has played a critical role in steering…
Cheap, robust, safe and accepted
Read More

Cheap, robust, safe and accepted

By Luca Marchionni, CTO of PAL Robotics The media has been calling 2024 “the year of the humanoid robots,” and…