Florent Lamiraux

Email: Florent.Lamiraux@laas.fr
Address: LAAS-CNRS
7, avenue du Colonel Roche
31077 Toulouse Cedex 4
Tel: 05.61.33.64.54
Fax: 05.61.33.69.69
Assistant: 05 61 33 64 69 (Delphine Fourcade)

Short Résumé

Oct. 2009 Directeur de Recherche CNRS-LAAS, Toulouse, France

Humanoid Robots (motion planning and control)

Dec. 2007 - Sept. 2009 Chargé de Recherche CNRS/AIST Joint Robotics Laboratory, Tsukuba, Japan

Humanoid Robots (motion planning and control)

Sept. 1999 - Dec. 2007 Chargé de Recherche CNRS-LAAS, Toulouse, France

Humanoid Robots (motion planning and control) Motion Planning and Control for Nonholonomic Robots

Oct. 97 - Sept. 99 Postdoctoral Research Associate at Rice University.

Path Planning for Deformable Objects

Sept. 94 - Sept. 97 Ph-D in the Robotics and Artificial Intelligence group at LAAS-CNRS,

Toulouse, France. Motion Planning and Control for a Mobile Robot with Trailer

1993-94 Advanced Studies Degree (DEA) in Computer Science at ENSEEIHT

in Toulouse.

1991-93 Ecole Polytechnique Paris.

Publications

All the publications are avaiblable here (with pdf files if available).

Research Areas and Interests

Manipulation planning

When an robot manipulates objects, the motions of the objects are subject to constraints:

  • objects grasped by the robot move with the robot,
  • objects not grasped by the robot stay static in a stable position.

These constraints raises scientific issues that we try to address by designing dedicated algorithms.

Robot programming

Programming industrial robots to perform repetitive tasks is time-consuming. Based on our knowledge in manipulation planning, we have developed

  • software that handle the manipulation constraints evoked above, and
  • a graphical user interface that enable a programmer to define the manipulation constraints relative to a problem.
Definition of a manipulation problem. Definition of grasps and resolution. Pre-grasp position to ease motion planning The full sequence. The robot grasp each of 8 parts, move them to the caroussel where they are processed, put them back to the initially empty tray, and finally stacks the empty tray on top of the full tray.

Humanoid Robot Motion Planning

The goal of this research topic is to make humanoid robots able to perform every-day tasks in environments designed for human beings. Our research work focus on geometric motion planning, taking into account kinematic and dynamic constraints.

  • Motion Planning

We conduct research aiming at making a humanoid robot able to perform a large range of motions in order to achieve various tasks in in-door environments, for instance,

  • walking in a cluttered environment,
  • grasping an object,
  • going through a door,
  • opening or closing a window...

Our approach consists in augmenting object models with the information useful to manipulate these object. See [Dalibard et al 2010] for details.

HRP-2 waking through a door... ...cluttered by an obstacle... ...through a sliding door Toyota Partner walking through a door
  • Whole-Body motion planning

hpp-gik is a software SDK that implements task-based inverse kinematics. The sofware is released under license LGPL and can be found on github. To use this SDK, it is recommended to download the tutorial The movie below shows a simple motion produced by hpp-gik including whole-body stepping and upper-body tasks.

Navigation for nonholonomic mobile robots

The goal of this research topic is to develop algorithms that will make articulated and kinematically constrained vehicles like trailer-truck systems navigate autonomously in partially known environments. The main challenge is to execute motions that can be very close to the obstacles of the environment. Our research work focus on two aspects of the problem.

  • Motion planning in cluttered environments,
  • Motion control in dynamic environments.

Mobile Robot Hilare 2 towing a trailer

A path computed by Move3D

Talks and Lectures

Talks

Lectures