About Us


As a technology transfer center, the CATIE organisation has a broad set of skills and strong ties with laboratories and high tech startups. The robotic team will benefit from the multidisciplinary environment it lives in.

The team aims at exploring service robotics from an application-driven perspective.

One of the team’s goal is to participate in the RoboCup @Home competition. The RoboCup competition is a way to objectively measure progress, expose it to a broad audience and gather an international community. At a local scope, creating a robotic team is also a way of uniting people from various scientific horizons towards a very pragmatic, tangible goal.

Near future

The team is in the process of acquiring an off-the-shelf robotic platform. The goal is to have a robot up and running to participate in service robotics competitions as soon as 2019.
Human consideration in AI will be one of the research topics of the team to ensure human acceptability of the robot. The robot will be modified with custom hardware solutions developed by the team.
An internship will start in April 2018 and will be followed by a PHD thesis in to explore, invent and implement hardware acceleration techniques as a way, among others, to enhance the capabilities of service robots.

The team will be backed up by master degree students from the Institut National Polytechnique de Bordeaux (INP).



Unit manager


Team leader


Communication manager


Embedded computer vision


Remi Fabre, Quentin Rouxel, Gregoire Passault, Steve N'Guyen and Olivier Ly:

Dynaban, an Open-Source Alternative Firmware for Dynamixel Servo-Motors. In Symposium RoboCup 2016: Robot World Cup XX

[Abstract] In this paper, we present an alternative open-source firmware for the Dynamixel MX-64 servo-motor. We discuss software features to fully exploit the hardware capabilities of the device. In order to enhance the default controller, a friction model and an electric model of the motor are embedded into the firmware. The parameters of the model are found using a black-box optimization algorithm. A feed-forward method is proposed to follow position, speed and torque trajectories.
The approach is tested with a highly dynamic kick movement on our humanoid soccer robot Sigmaban whose torque trajectories are computed using a classic rigid body inverse dynamics. The comparison between the default control strategy and the proposed one shows significant improvements in terms of accuracy, delay and repeatability.

Download pdf


Open-source alternative firmware for Dynamixel servos

Source Github


- Our media section is still in the works -