A recurrent neural network model for generation of humanlike reaching
movements
Yuta Tsuzuki and Naomichi Ogihara
Depar tment of M echanical Engineering, Facult y of S cience and Technology, Keio Universit y, Yokohama, Japan
ABSTR AC T
We constructed a recurrent neural network model that can generate human reaching motion. Given a target position, the neural network model is capable of producing muscular activation signals that move the hand to the target endpoint, while solving the problem of musculoskeletal redundancy by dynamic relaxation of the energy functions embedded in the network. The proposed neural network model was integrated with a two-dimensional three-link eight muscle musculoskeletal model of the human arm to simulate arm reaching movements in the horizontal and sagittal planes. Our results demonstrate that the model is capable of generating natural arm movements that have spatiotemporal features, such as a slightly curved hand path and the characteristic bell-shaped velocity profile, that are similar to those of actual human movements. Some aspects of the proposed computational
framework might be utilized in the central nervous system for generation of reaching movements.
KEY WORDS
Musculoskeletal system; redundanc y ; dynamics; muscle synergy ; motor co nt ro l
Anthropomorphic musculoskeletal 10 degrees-of-freedom robot arm driven by
pneumatic artificial muscles
Arne Hitzmann , Hiroaki Masuda, Shuhei Ikemoto and Koh Hosoda
Graduate S chool of Engineering S cience, Osak a Universit y, Toyonak a, Japan
ABSTR AC T
This paper describes the construction and design decisions of an anthropomorphic musculoskeletal robot arm actuated by pneumatic artificial muscles. This robot was designed to allow humaninspired compliant movements without the need to replicate the human body-structure in detail. This resulted in an mechanically simple design while preserving the motoric characteristics of a human. Besides the constructional details of the robot we will present two experiments to show the robots abilities regarding to its dexterity and compliance.
KEY WORDS
Musculoskeletal ro bot-arm; M cK ibben pneumatic ar tificial muscle; construc tive approach
Compliant universal grippers as adaptive feet in legged robots
S. Hauser a, M. Mutlu a,b, P. Banzeta and A.J. Ijspeert a
aBioRob, School of Engineering, EPFL, Lausanne, Switzerland; bVislab, Institute of Systems and Robotics, IST, Lisbon, Portugal
ABSTR AC T
This work investigates the usage of compliant universal grippers as a novel foot design for legged locomotion. The method of jamming of granular media in the universal grippers is characterized by having two distinct states: a soft, fluid-like state which in locomotion can be used to damp impact forces and enable passive shape adaptation especially on rough terrain, and a hard, solid-like state that is more suited to transmit propulsion forces.We propose a system that actively uses and switches between both states of a foot design based on granular jamming and detail the implementation on a quadruped robotic platform. The mechanism is inspired by the stiffness varying function of the tarsal bones in a human foot, and our aim is to understand how the change of foot stiffness can be used to improve the locomotion performance of legged robots. Using the same open loop trot gait in all experiments, it is shown that a fast state transition enables the robot to profit from both states, leading to more uniform foot placement patterns also on rough terrain compared to other tested feet. This results in overall faster gaits and even enables the robot to climb steeper inclined surfaces.
KEY WORDS
Adaptive feet; jamming; universal gripper; locomotion; legged robots
Effects of passive and active joint compliance in quadrupedal locomotion
M. Mutlu a,b, S. Hauser a, A. Bernardino b and A. J. Ijspeert a
aBIOROB EPFL, Lausanne, Switzerland; bVislab IST, Lisbon, Portugal
ABSTR AC T
Compliance of the body has a crucial role on locomotion performance. The levels and the distribution of compliance should be well tuned to obtain efficient gait. The leg stiffness changes significantly even during different phases of a single gait cycle. This paper presents an experimental study on different passive and active limb compliance configurations. Each configuration is tested on flat, rough and inclined-rough surfaces, to analyze locomotion performance in diverse conditions. As the active compliance mechanism, Tegotae-based control is selected. Even though active compliance is not its primary use, we show that the Tegotae rule presents intriguing features that have potential to boost gait performance in various scenarios.
KEY WORDS
Locomotion; compliance; Tegotae; stiffness; passive compliance; active compliance
Spontaneous gait transition to high-speed galloping by reconciliation between
body support and propulsion
A. Fukuharaa, D. Owakib, T. Kanoa, R. Kobayashic and A. Ishiguroa
aResearch Institute of Electric and Communication, Tohoku University, Sendai, Japan; bDepartment of Robotics, Graduate School of Engineering, Tohoku University, Sendai, Japan; cGraduate School of Science, Hiroshima University, Hiroshima, Japan
ABSTR AC T
Quadrupeds change their gait patterns in response to locomotion speed to achieve low cost of transport over a wide range of speeds. Understanding the underlying control mechanism is essential to establish a design principle for legged robots that can adaptively generate energy-efficient locomotion patterns. Even decerebrate cats exhibit spontaneous gait transition, suggesting that adaptive gait patterns are generated via decentralized control systems, i.e. central pattern generators and reflexes. Several studies address this issue; however, the essential control mechanism that enables spontaneous transition from low- to high-speed gait is still poorly understood. To address this issue, this work reconsiders the interlimb coordination mechanism by focusing on two fundamental roles of limbs: body support and propulsion. To verify the proposed model, 2D simulations and 3D hardware experiments were conducted. The results indicate that the proposed model enables the robot to spontaneously exhibit gait transition to high-speed galloping and to achieve faster and more energy-efficient locomotion than a bounding gait in 3D hardware experiments.
KEY WORDS
Quadruped robot; interlimb coordination; local sensory feedback; central pattern generator
Synergistic control of a multi-segments vertebral column robot based on
tensegrity for postural balance
Artem Melnyka and Alexandre Pittib
aHéphaïstos Project, Université Côte d’Azur, INRIA, France; bLaboratoire ETIS, Université Paris Seine, Université de Cergy-Pontoise, CNRS UMR, ENSEA, Cergy-Pontoise, France
ABSTR AC T
We present a neuronal architecture to control a compliant robotic model of the human vertebral column for postural balance. The robotic structure is designed using the principle of tensegrity that ensures to be lightweight, auto-replicative with multi-degrees of freedom, flexible and also robust to perturbations. We model the central pattern generators of the spinal cords with a network of
nonlinear Kuramoto oscillators coupled internally and externally to the structure and error-driven by a proportional derivative (PD) controller using an accelerometer for feedback. This coupling between the two controllers is original and we show it serves to generate controlled rhythmical patterns. We observe for certain coupling parameters some intervals of synchronization and
of resonance of the neural units to the tensile structure to permit smooth control and balance. We show that the top-down PD control of the oscillators flexibly absorbs external shocks proportionally to the perturbation and converges to steady state behaviors. We discuss then about our neural architecture to model motor synergies for compliance control and also about tensegrity structures for soft robotics. The 3D printed model is provided as well as a movie at the address https://sites.google.com/site/embodiedai/current-research/tensegrityrobots.
KEY WORDS
Motor synergies; central pattern generators; tensegrity; vertebral column; postural balance; phase synchronization; soft robotics; feedback
resonance; biological robotics
