Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation
نویسندگان
چکیده
In this paper, we present a novel methodology to obtain imitative and innovative postural movements in a humanoid based on human demonstrations in a di®erent kinematic scale. We collected motion data from a group of human participants standing up from a chair. Modeling the human as an actuated 3-link kinematic chain, and by de ̄ning a multi-objective reward function of zero moment point and joint torques to represent the stability and e®ort, we computed reward pro ̄les for each demonstration. Since individual reward pro ̄les show variability across demonstrating trials, the underlying state transition probabilities were modeled using a Markov chain. Based on the argument that the reward pro ̄les of the robot should show the same temporal structure of those of the human, we used di®erential evolution to compute a trajectory that ̄ts all humanoid constraints and minimizes the di®erence between the robot reward pro ̄le and the predicted pro ̄le if the robot imitates the human. Therefore, robotic imitation involves developing a policy that results in a temporal reward structure, matching that of a group of human demonstrators across an array of demonstrations. Skill innovation was achieved by optimizing a signed reward error after imitation was achieved. Experimental results using the humanoid HOAP-3 are shown.
منابع مشابه
Learning Full-Body Motions from Monocular Vision in Real-Time: Dynamic Imitation in a Humanoid Robot
Learning Full-Body Motions from Monocular Vision in Real-Time: Dynamic Imitation in a Humanoid Robot
متن کاملFlexible Foot/Ankle Based on PKM with Force/Torque Sensor for Humanoid Robot
This paper describes the development of a novel humanoid robot foot/ankle based on an orientation Parallel Kinematic Mechanism for intelligent and flexible control. With three identical Universal-Prismatic-Spherical prismatic-actuated limbs and a central Universal-Revolute passive limb, the PKM can perform three degrees of freedom rotation motions. In order to enable the humanoid robot safely t...
متن کاملReal-time full body motion imitation on the COMAN humanoid robot
On-line full body imitation with a humanoid robot standing on its own two feet requires simultaneously maintaining the balance and imitating the motion of the demonstrator. In this paper we present a method that allows real-time motion imitation while maintaining stability, based on prioritized task control. We also describe a method of modified prioritized kinematic control that constrains the...
متن کاملLearning to Walk through Imitation
Programming a humanoid robot to walk is a challenging problem in robotics. Traditional approaches rely heavily on prior knowledge of the robot's physical parameters to devise sophisticated control algorithms for generating a stable gait. In this paper, we provide, to our knowledge, the first demonstration that a humanoid robot can learn to walk directly by imitating a human gait obtained from m...
متن کاملLearning Nonparametric Models for Probabilistic Imitation
Learning by imitation represents an important mechanism for rapid acquisition of new behaviors in humans and robots. A critical requirement for learning by imitation is the ability to handle uncertainty arising from the observation process as well as the imitator’s own dynamics and interactions with the environment. In this paper, we present a new probabilistic method for inferring imitative ac...
متن کاملذخیره 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 ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- I. J. Humanoid Robotics
دوره 11 شماره
صفحات -
تاریخ انتشار 2014