Development of u niversal vacuum gripper for w all-climbing r obot
Masahiro F ujitaa, Suguru Ikedab, Toshiaki Fujimotoa, Toshihiko Shimizub, Shuhei Ikemotoc and
Takeshi Miyamotob
aGraduate School information Sciences, Tohoku University, Sendai-shi, Japan; bDepartment of Mechanical Engineering, Kobe City College of Technology, kobe-shi, Japan; cGraduate School of Engineering Science, Osaka University, Osaka, Japan
ABSTRACT
Task performed at a height, such as wall inspections are one of the dangerous tasks for humans. Thus, robotic technology for safety inspection is required. This research focuses on developing robots to climb vertical walls with flat and uneven surfaces, e.g. concrete, tile and riveted structure. To have wall-climbing capability, climbing robots use vacuum pads, claws, magnets, intermolecular force, and adhesive. However, each of these approaches has disadvantages. To achieve wall climbing on an uneven surface without scratching and staining, we have developed a novel vacuum pad named the Universal Vacuum Gripper (UVG), which is based on the Universal Gripper (UG). The UG is a robot hand using jamming transition of coffee powder inside a balloon to grip uneven material. The UVG is a vacuum pad with a deformable skirt based on the UG. If the skirt shape is deformed in accordance with the contact surface, air leaks can be avoided. Moreover, the deformed skirt can be stiffened, thereby working as a gripper. Here, we evaluate the proposed gripper, having both grasping and adhesion force. We also develop a wall-climbing robot with UVGs, and evaluate its performance on uneven surfaces under real-world conditions.
KEYWORDS
Universal vacuum gripper; wall-climbing robot; vacuum pad; uneven surface; jamming transition
Bilateral remote teaching and autonomous task execution w ith task progress
feedback
Yasuhiro Ishiguro, Wataru Takano and Y oshihiko Nakamura
Department of Mechano-Informatics, U niversity of Tokyo, 7-3-1 Bunkyo-ku, Hongo, Tokyo, J apan
ABSTRACT
This paper d escribes an approach to estimating the p rogress in a task executed by a humanoid r o b o t a n d t o s y n t h e s i z i n g m o t i o n b a s e d o n t h e cu r r e n t p r o g r e s s s t h a t t h e r o b o t c a n a c h i e v e t h e t a s k . Th e r o b o t o b s e r v e s a h u m a n p e r f o r m i n g w h o l e b o d y m o t i o n f o r a s p e c i fi c t a s k , an d e n c o d e s t h e s e m o t i o n s i n t o a h i d d e n Ma r k o v m o d e l ( H M M ) . Th e c u r r e n t o b s e r v a t i o n is co m p a r e d wi t h t h e m o t i o n g e n e r a t e d b y t h e H M M , a n d t h e t a s k p r o g r e s s ca n b e e s t i m a t e d d u r i n g t h e r o b o t p e r f o r m i n g t h e m o t i o n . T h e r o b o t s u b s e q u e n t l y u s e s t h e es t i m a t e o f t h e t a s k p r o g r e s s t o g e n e r a t e a m o t i o n a p p r o p r i a t e t o t h e cu r r e n t s i t u a t i o n wi t h t h e f e e d b a c k r u l e . W e c o n s t r u c t e d a b i l a t e r a l r e m o t e co n t r o l system with humanoid r obot HRP-4 and haptic device Novint Falcon, and we m ade t he humanoid r o b o t p u s h a b u t t o n . T e n t r i a l m o t i o n s o f p u s h i n g a b u t t o n we r e r e c o r d e d f o r t h e t r a i n i n g d a t a . W e t e s t e d o u r p r o p o s e d a p p r o a c h o n t h e au t o n o m o u s e x e c u t i o n o f t h e p u s h i n g m o t i o n b y t h e h u m a n o i d r o b o t , an d c o n fi r m e d t h e eff e c t i v e n e s s o f o u r t a s k p r o g r e s s f e e d b a c k m e t h o d .
KEYWORDS
H u m a n o i d r o b o t ; b i l a t e r a l c o n t r o l ; t e l e o p e r a t i o n ; hidden Markov model; a u t o n o m o u s
Optimal design of a stair-climbing mobile robot with flp mechanism
Pengzhan Liu a,b , Jianzhong Wanga, Xin Wanga,b and Peng Zhaoa,b
astate Key Laboratory of explosion science and technology, beijing institute oftechnology, beijing, china; bschool of Mechatronical engineering, beijing institute of technology, beijing, china
ABSTRACT
Stairs overcoming is a primary challenge for mobile robots moving in human environments, and the contradiction between the portability and the adaptability of stair climbing robot is not well resolved. In this paper, we present an optimal design of a flp-type mobile robot in order to improve the adaptability as well as stability while climbing stairs. The kinematic constraints on the flp mechanism are derived to prevent undesired interferences among stairs, wheels and main body during climbing stairs. The objective function is proposed according to the traction demand of the robot during stair-climbing motion for the fist time and the value of the objective function is calculated though kinetic analysis. The Taguchi method is using as the optimization tool because of its simplicity and cost-effctiveness both in formulating an objective function and in satisfying multiple constraints simultaneously. The performance of the robot under the optimal parameters is verifid through simulations and experiments.
KEYWORDS
Flip-type robot; climbing stair; taguchi method; kinetic analysis
Probabilistic movement primitives under u nknown system dynamics
Alexandros Paraschosa, Elmar Rueckerta, Jan Petersa,b and Gerhard Neumannc
aIntelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany; bRobot Learning Group, Max Planck Institute for Intelligent Systems, Tuebingen, Germany; cLincoln Centre for Autonomous Systems (LCAS), University of Lincoln, Lincoln, UK
ABSTRACT
Physical interaction requires robots to accurately follow kinematic trajectories while modulating the interaction forces to accomplish tasks and to be safe to the environment. However, current approaches rely on accurate physical models oriterative learning approaches.We present a versatile approach for physical interaction tasks, based on Movement Primitives (MPs) that can learn physical interactiont asks so lely by demonstrations,with out explicitly modeling the robot or the environment. We base our approach on the Probabilistic Movement Primitive s(ProMPs),which utilizes the variance of the demonstrations to provide better generalization of the encoded skill, combines kills ,and derive a controller that follows exactly the encoded trajectory distribution. However, the ProMP controller requires the system dynamics to be known. We present a reformulation of the ProMPs that allows
accurate reproduction of the skill without modeling the system dynamics and, further, we extent our approach to incorporate external sensors, as for example, force/torque sensors. Our approach learns physical interaction tasks solely from demonstrations and online adapts the movement to force–torque sensor input. We derive a variable-stiffness controller in closed form that reproduces the trajectory distribution and the interaction for cespresentin the demonstrations.We evaluate our approach in simulated and real-robot tasks.
KEYWORDS
Movement primitive; robot learning; learning from demonstration
