Deep Learning Vision System for Quadruped Robot Gait Pattern Regulation

نویسندگان

چکیده

Robots with bio-inspired locomotion systems, such as quadruped robots, have recently attracted significant scientific interest, especially those designed to tackle missions in unstructured terrains, search-and-rescue robotics. On the other hand, artificial intelligence systems allowed for improvement and adaptation of capabilities these robots based on specific imitating natural behavior animals. The main contribution this work is a method adjust adaptive gait patterns overcome terrains using ARTU-R (A1 Rescue Task UPM Robot) robot central pattern generator (CPG), automatic identification terrain characterization its obstacles (number, size, position superability analysis) through convolutional neural networks regulation. To develop method, study dog was carried out, validation adjustment simulation model ROS-Gazebo subsequent transfer real robot. Outdoor tests were out evaluate validate efficiency proposed terms percentage success overcoming stretches well kinematic dynamic variables results show that has an over 93% (identification terrain, segmentation obstacle characterization) 91% terrains. This also compared against developments state-of-the-art benchmark models.

برای دانلود باید عضویت طلایی داشته باشید

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

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Free Gait Pattern Generator for the Quadruped Walking Robot ALDURO

The purpose of this paper is to give a short overview of the ongoing work of the combined four-legged and wheeled walking machine ALDURO with special consideration to gait generation in unstructured terrain.

متن کامل

Combination of Transverse-Trot Gait Pattern for Quadruped Walking Robot

This paper presents a combination of transverse and trot walking pattern technique for hexa-quad robot after transformation to optimize the multi-legged robot operation and walking performances. Due to the limitation on the stability of hexapod robot, the combination of hexa-quad walking sequence is proposed to stabilize the quadruped configuration and walking modes. Quadruped robot configurati...

متن کامل

Adaptive gait pattern control of a quadruped locomotion robot

The authors have proposed a control system of a quadruped locomotion robot by using nonlinear oscillators. It is composed of a leg motion controller and a gait pattern controller. The leg motion controller drives the actuators of the legs by using local feedback control. The gait pattern controller involves nonlinear oscillators with mutual interactions. In this paper, capability of adaptation ...

متن کامل

Locomotion Gait Optimization for a Quadruped Robot

Legged robot gait generation is a challenging task that involves the control of a large number of degrees of freedom (DOF’s) within a mechanical structure that varies during locomotion. A large number of motion parameters have to be considered in order to obtain a stable, natural and efficient locomotion. Legged robot locomotion applies nonlinear dynamical equations of high order with a multidi...

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

ژورنال

عنوان ژورنال: Biomimetics

سال: 2023

ISSN: ['2313-7673']

DOI: https://doi.org/10.3390/biomimetics8030289