Pennochio - Mapping Motion Capture onto a Humanoid Robot in Real Time

نویسنده

  • Anthony Arena
چکیده

The objective of this project is to use motion capture to track the motions of a human subject, above the waist, and then map these motions onto a humanoid robot in real-time, essentially making the robot a puppet and the human the puppeteer. This puppeteer will control the robot while wearing a virtual reality rig that allows the puppeteer to see what the robot sees. The robot that will be used is the PR2 from Willow Garage [3] and the motion capture system was initially designed to be the VICON system [9]. However, given possible difficulties in usefulness of a system based on such an expensive system with such limited access, thought has been given to developing the system (either exclusively or in parallel) for use with more commercial motion capture systems like the Sony Playstation Move and the Microsoft Xbox Kinect. Through the course of the project the Kinect has revealed itself to be the more logical choice and so has replaced the VICON system as the method for motion capture. The PR2 can raise and lower its height, turn and tilt its head, and has arms that fully mimic a human arm. Because most motion capture relies on manual correction after gathering data, the most difficult task will be forming an algorithm or method for motion capture that avoids ambiguity among the capture points and can also be easily be mapped onto the robot in real-time without significant delay. Although the main objective is to achieve an effective mapping from the user’s head, torso and arms onto the robot in, it is also hoped that an effective system can be designed to control the robot’s motion in the (x,y) plane and also to eventually design a system using a mechanical device to grasp and interact with objects.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Combined Controllers that Follow Imperfect Input Motions for Humanoid Robots

Humanoid robots have the potential to become a part of everyday life as their hardware and software challenges are being solved. In this paper we present a system that gets as input a motion trajectory in the form of motion capture data, and produces a controller that controls a humanoid robot in real-time to achieve a motion trajectory that is similar to the input motion data. The controller e...

متن کامل

Real Time 3D Vision for Humanoid Robots

Recent advances in humanoid robotics, such as the introduction of Honda’s Asimo robot, have brought humanoids to the forefront of robotics research. We propose to mount the CanestaVision EP camera onto a humanoid robot. The 3D sensing capabilities of the camera will enable significant improvements in the core behaviors of obstacle detection (which is important for reliable walking) and grasp pl...

متن کامل

Automatic Generation of Kinematic Models for the Conversion of Human Motion Capture Data into Humanoid Robot Motion

Human motion capture is a promising technique for the generation of humanoid robot motions. To convert human motion into humanoid robot motion, we need to relate the humanoid robot kinematics to the kinematics of a human performer. In this paper we propose an automatic approach for scaling of humanoid robot kinematic parameters to the kinematic parameters of a human performer. The kinematic mod...

متن کامل

Humanoid Robots Imitation of Human Motion Using Off-line and Real-time Adaptation Techniques

This paper describes Off-Line and Real time motion conversion approaches for imitating the motion of a human being using a humanoid robot. In both cases, the human motion is measured with marker points captured by the 3D motion capture system Vicon. A similar physical morphology between the shape of the robot and the human is assumed. This paper also demonstrates that the input measurements of ...

متن کامل

Visual Motion Capturing for Kinematic Model Estimation of a Humanoid Robot

Controlling a tendon-driven robot like the humanoid Ecce is a difficult task, even more so when its kinematics and its pose are not known precisely. In this paper, we present a visual motion capture system to allow both real-time measurements of robot joint angles and model estimation of its kinematics. Unlike other humanoid robots, Ecce (see Fig. 1A) is completely molded by hand and its joints...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011