Capture, recognition and imitation of antropomorphic motion
|Title||Capture, recognition and imitation of antropomorphic motion|
|Publication Type||Conference Paper|
|Year of Publication||2012|
|Authors||Hak, S, Mansard, N, Ramos, O, Saab, L, Stasse, O|
|Conference Name||IEEE/RAS Int. Conf. on Robotics and Automation (ICRA)|
|Keywords||Whole body control|
We present an overview of our current research works in generation, recognition and editing of anthropomorphic motion using a unified framework: the stack of tasks. It is based on the task function formalism classically used for motion generation. A task function maps the joint space of a robot to a dedicated space which is usually linked to the sensors of the robot: the task space. The task spaces are suitable to perform motion analysis and task recognition because the tasks are described in those spaces. The generation is originally based on inverse kinematics but can be generalized to produce full-dynamic motions. The tasks are defined by a task space, a reference behavior and a task Jacobian. The reference behaviors are originated from human trajectories. Specific tasks are then integrated to retarget and edit the reference motion in order to respect the dynamic constraints, the limits of the robot and the general aspect. In the next section, we quickly introduce the stack of tasks framework. Then we present our methods to perform task recognition, dynamic retargeting and editing based on that framework.