Keynote Lectures
Speaker: Prof. Seth Hutchinson, University of Illinois at Urbana-Champaign, USA
Topic: Visual Servo Control: The First Quarter Century
Abstract:
Visual servo control, a fusion of computer vision, robotics and control, is a maturing method for controlling robots using real-time vision feedback. It has now been approximately twenty-five years since the seminal visual servo control papers were published. During this period, several major, and well understood, approaches have evolved and have been demonstrated in laboratories around the world. Most of these can be classified as either position-based or image-based, depending on whether camera pose or image features are used in the control law. Each approach has well-documented performance problems.
In this talk, after a brief description of traditional methods and their shortcomings, I will describe two methods that overcome these performance problems. With the first approach, the control system is partitioned along its spatial degrees of freedom. Rotation about and translation along the optical axis are controlled by a specifically designed controller, and the remaining degrees of freedom are controlled with a traditional image-based method. With the second approach, a switched control system selects either an image-based or position-based controller at each time instant, using a state-based switching scheme. The performances of both of these approaches are demonstrated by a variety of simulated and experimental results.
Speaker: Prof. Goro Obinata, EcoTopia Science Institute, Nagoya Univesity, Japan
Topic: Human centered robotics
Abstract:
Robotics technologies can be applied not only to design assistive devices for impaired human functions but to analyze human movements. The analogy between neuro-musculo-skeletal system of human bodies and humanoid robots helps us to analyze human movements and to design exo-skeleton active devices for walking of disabled. The talk presents simulation-based methods for designing exo-skeleton devices and control schemes of rehabilitation robots. The simulation and experimental results show the effectiveness of the proposed methods.
Speaker: Prof. Pier Paolo Porta, Università di Parma, Italy
Topic: Efficient sensing for autonomous driving
Abstract:
VisLab is active in the field of intelligent perception systems since more than 15 years. Applied research on autonomous driving together with the realization of several prototypes brought VisLab to reach world milestones of vehicular robotics. The talk presents the key aspects of vision technology applied to the automotive domain. In particular the performances of a stereo system compared to most common approaches will be highlighted.
Topic: Visual Servo Control: The First Quarter Century
Abstract:
Visual servo control, a fusion of computer vision, robotics and control, is a maturing method for controlling robots using real-time vision feedback. It has now been approximately twenty-five years since the seminal visual servo control papers were published. During this period, several major, and well understood, approaches have evolved and have been demonstrated in laboratories around the world. Most of these can be classified as either position-based or image-based, depending on whether camera pose or image features are used in the control law. Each approach has well-documented performance problems.
In this talk, after a brief description of traditional methods and their shortcomings, I will describe two methods that overcome these performance problems. With the first approach, the control system is partitioned along its spatial degrees of freedom. Rotation about and translation along the optical axis are controlled by a specifically designed controller, and the remaining degrees of freedom are controlled with a traditional image-based method. With the second approach, a switched control system selects either an image-based or position-based controller at each time instant, using a state-based switching scheme. The performances of both of these approaches are demonstrated by a variety of simulated and experimental results.
Speaker: Prof. Goro Obinata, EcoTopia Science Institute, Nagoya Univesity, Japan
Topic: Human centered robotics
Abstract:
Robotics technologies can be applied not only to design assistive devices for impaired human functions but to analyze human movements. The analogy between neuro-musculo-skeletal system of human bodies and humanoid robots helps us to analyze human movements and to design exo-skeleton active devices for walking of disabled. The talk presents simulation-based methods for designing exo-skeleton devices and control schemes of rehabilitation robots. The simulation and experimental results show the effectiveness of the proposed methods.
Speaker: Prof. Pier Paolo Porta, Università di Parma, Italy
Topic: Efficient sensing for autonomous driving
Abstract:
VisLab is active in the field of intelligent perception systems since more than 15 years. Applied research on autonomous driving together with the realization of several prototypes brought VisLab to reach world milestones of vehicular robotics. The talk presents the key aspects of vision technology applied to the automotive domain. In particular the performances of a stereo system compared to most common approaches will be highlighted.