59 documents found, page 1 of 6
End-to-end approach for autonomous driving: a supervised learning method using ...
Ribeiro, Inês A.; Ribeiro, Tiago; Lopes, Gil; Ribeiro, A. FernandoThis paper presents a solution for an autonomously driven vehicle (a robotic car) based on artificial intelligence using a supervised learning method. A scaled-down robotic car containing only one camera as a sensor was developed to participate in the RoboCup Portuguese Open Autonomous Driving League competition. This study is based solely on the development of this robotic car, and the results presented are on...
Dynamic control of a hexapod robot using compliant contact force models
Canedo, João; Coelho, Joana; Marques, Filipe; Dias, Bruno; Lopes, Gil; Ribeiro, A. Fernando; Flores, Paulo[Excerpt] The design of autonomous hexapod robots for rescue or exploratory missions aims to achieve high-performing and efficient locomotion, which must be able to adapt to complex environments with variable terrain topology. In this sense, the contact forces developed during the interaction between the robot’s feet and the ground can cause undesirable trajectory deviations and increase the torso instability d...
Dynamic modeling and simulation of the omnidirectional locomotion of a mobile m...
Gonçalves, Fernando; Ribeiro, Tiago; Ribeiro, A. Fernando; Lopes, Gil; Flores, PauloOmnidirectional wheeled locomotion is often utilized by robots intended to work in indoor environments due to its high manoeuvrability in confined spaces. CHARMIE, a human-inspired mobile manipulator that aims to assist patients with mobility limitations, employs four Swedish wheels supported by an independent suspension to navigate through domestic environments. Multibody dynamics is one of the main tools whic...
Large-scale tactile detection system based on supervised learning for service r...
Cunha, Fábio; Ribeiro, Tiago; Lopes, Gil; Ribeiro, A. FernandoIn this work, a large-scale tactile detection system is proposed, whose development is based on a soft structure using Machine Learning and Computer Vision algorithms to map the surface of a forearm sleeve. The current application has a cylindrical design, whose dimensions intend to be like a human forearm or bicep. The model was developed assuming that deformations occur only at one section at a time. The goal...
Development and implementation of a new approach for posture control of a hexap...
Coelho, Joana Sofia Falcato Pereira Lima; Dias, Bruno; Lopes, Gil; Ribeiro, A. Fernando; Flores, PauloThe adaptability of hexapods for various locomotion tasks, especially in rescue and exploration missions, drives their application. Unlike controlled environments, these robots need to navigate ever-changing terrains, where ground irregularities impact foothold positions and origin shifts in contact forces. This dynamic interaction leads to varying hexapod postures, affecting overall system stability. This stud...
Multibody model of the human-inspired robot CHARMIE
Gonçalves, Fernando; Ribeiro, Tiago; Ribeiro, A. Fernando; Lopes, Gil; Flores, PauloThe rapid ageing of the worldwide population raises pressing concerns related to ensuring proper healthcare and quality of life for older adults. A human-like mobile domestic robot, named CHARMIE, is being produced to aid in these situations by performing household chores, thus increasing the autonomy of persons with mobility limitations. The present work provides a valuable contribution to the development of C...
Reactive locomotion of a hexapod for navigation across irregular ground
Coelho, Joana; Dias, Bruno; Lopes, Gil; Ribeiro, A. Fernando; Flores, PauloIn controlled environments, the hexapod limbs actuation can be controlled as a closed system. However, the increase of the terrain complexity implies an adaptation of their trajectory based on the robot interactions with the environment. Thus, the implementation of terrain data to the legs actuation potentially improves the hexapod quasi-static stability in these scenarios. This paper presents an adaptive contr...
Parallel, angular and perpendicular parking for self-driving cars using deep re...
Sousa, Bruno; Ribeiro, Tiago; Coelho, Joana; Lopes, Gil; Ribeiro, A. FernandoThe progress in creating a fully autonomous selfdriving car has steadily increased in recent decades. Consequently, autonomous parking has been a well-researched field since every driving trip must end with a parking manoeuvre. In recent years, with the current successes in reinforcement learning, the concept of applying it to solve the autonomous parking problem has been more and more explored. A vehicle equip...
Combining YOLO and deep reinforcement learning for autonomous driving in public...
Andrade, Nuno; Ribeiro, Tiago; Coelho, Joana; Lopes, Gil; Ribeiro, A. FernandoAutonomous driving is emerging as a useful practical application of Artificial Intelligence (AI) algorithms regarding both supervised learning and reinforcement learning methods. AI is a well-known solution for some autonomous driving problems but it is not yet established and fully researched for facing real world problems regarding specific situations human drivers face every day, such as temporary roadworks ...
Dynamic modeling of a human-inspired robot based on a Newton-Euler approach
Gonçalves, Fernando; Ribeiro, Tiago A.; Ribeiro, A. Fernando; Lopes, Gil; Flores, PauloThis work deals with the modeling process of a new three dimensional human-like robot for an inverse dynamic analysis. This robot intends to be utilized by caregivers to assist persons with reduced mobility (such as the elderly). The model under analysis is composed by 24 rigid bodies: 3 to represent the robot’s base and locomotion, 4 for the lower limbs and torso, 7 for each arm, and 3 for the head. The result...