Softbank Robotics Europe

Aldebaran Robotics

Centre National De La Recherche Scientifique

Institut National De Recherche En Informatique Et En Automatique

Inria Institut National De Recherche En Informatique Et En Automatique

David Gouaillier

Vincent Clerc

Sébastien Dalibard

Damien Chablat

Cyrille Collette

Pierre-Brice Wieber

Jory Lafaye

Giulio Cerruti

Sebastien Dalibard

A hand intended to equip a humanoid robot, the hand includes a palm and at least one finger extending along a first axis, the hand being capable of picking up an object, the finger comprising a first phalanx linked to the palm by a first motorized pivot link and a second phalanx consecutive to the first phalanx linked to the first phalanx by a second pivot link. The finger comprises a first mechanism linking the palm to the second phalanx configured such that the rotation of the first phalanx about the second axis causes the second phalanx to rotate about the third axis, and a second mechanism linking the palm to each of the phalanges configured to actuate the finger in such a way that the finger wraps around the object to be picked up, and the second mechanism is configured to deform the first mechanism.

Hand intended to equip a humanoid robot

A computer-implemented method of determining a collision between an object and a robot, comprises monitoring one or more articular parts of the robot by measuring the parameters associated with the real displacements of the one or more articular parts; comparing the measured parameters with the expected parameters associated with the corresponding commanded displacements; and determining the probability of a collision with an object. Described developments comprise the exclusion of system failures, the identification of the collided object by computer vision or by communicating with the object, the execution of one or more actions such as a safety mode, the identification of systematic discrepancies in performed comparisons, the grouping of articular parts belonging to a same articular chain, and the mutual surveillance of robots. The use of capacitive sensors, bumper sensors and magnetic rotary encoders is disclosed.

Collision detection

A humanoid robot with a body joined to an omnidirectional mobile ground base, and equipped with: a body position sensor and a base position sensor to provide measures, actuators comprising at least 3 wheels located in the omnidirectional mobile base, extractors for converting the measures into useful data, a controller to calculate position, velocity and acceleration commands from the useful data using a robot model and pre-ordered position and velocity references, means for converting the commands into instructions for the actuators, wherein the robot model is a double point-mass model, and wherein the commands are based on a linear model predictive control law with a discretized time according to a sampling time period and a number of predicted samples, and expressed as a quadratic optimization formulation with: a weighted sum of objectives and a set of predefined linear constraints.

Omnidirectional wheeled humanoid robot based on a linear predictive position and velocity controller

A jointed robot capable to move on a surface is provided. It is known to limit to a predefined fixed value the torque that the motors of the joints of the robot can develop. A rigidity coefficient corresponding to the limit torque is calculated by solving a dynamic equilibrium model of the robot. The contact points of the characteristic effectors are determined by a selection from a list of potential effectors, notably as a function of a criterion of distance from a virtual ground plane. The contact forces for said effectors are calculated by optimal resolution of the equilibrium equations. Finally the torques applied in the dynamic equilibrium model of the robot and the coefficients of corresponding rigidity are calculated.

Robot with joints of variable rigidity and method for calculating said optimized rigidity

The invention relates to a humanoid robot endowed with particular capabilities for managing falls. The risks of falling limit the development of the mass-market use of humanoid robots. In the prior art, the modalities for detecting falls are not well suited to the case of very dynamic robots since the center of mass is very often outside their support polygons. The modalities for managing falls are also poorly suited to robots which must be economical in their computation resources. According to the invention, the conventional support polygon is supplemented with effectors for which it is determined that they are sufficiently close to the ground. Protection strategies are implemented, chosen from a set of strategies defined by a classification of the angles of fall.

Growing community of inventors

St Jean de Boiseau, France

David Gouaillier