Robotics research has made impressive progress in the past five decades. Various robots have become a part of our daily life. Industrial robots are performing boring and cumbersome tasks on our behalf, toy robots have become good buddies of children, surgical robots have extended surgeons’ dexterity and accessibility, and mobile robots and flying robots explore unknown environments for us.
However, robots are still far away from our expectations, due to the limitations on systematic reliability, robustness, environmental adaptability, intelligence and so on. How can we address these problems and allow robots to bring more convenience to our lives? If we look back, the classical system modeling approaches laid down the solid foundation for modern robotics, and probabilistic robotics greatly extended the application of robotic systems through improving environmental adaptability and systematic robustness. And now, with the deeper understanding of biological systems and neuro systems, more and more neurorobotic and biologically inspired solutions are further improving robot performance and are extending the application of robots. It is clear that the appearance of these techniques will bring another big leap in robotics research. In this topic, we will especially focus on the neural and bio-inspired solutions to the control problem, which is the key and fundamental problem in robotics.
This topic is to disseminate the new findings in the robotics community and the neuroscience community, in order to promote cross-disciplinary communication and fusion. We hope this topic will serve as a platform that facilitates the communication between neuroscience researchers and robotics researchers, and inspires the marriage of the neural and bio-inspired processing research and the robotics research. We strongly believe such research can greatly improve the precision and reliability of robotic systems and promote research of the robot control problem.
The areas of interests include but are not limited to:
• Locomotion and Manipulator Control
• Medical Robot and Control
• Sensing, signal processing, and decision making of robots.
• Neural networks (feed-forward, recurrent, and deep) for robot data processing
• Bionic robots and bio-inspired robot control
• Intelligent modeling of robotic systems
Robotics research has made impressive progress in the past five decades. Various robots have become a part of our daily life. Industrial robots are performing boring and cumbersome tasks on our behalf, toy robots have become good buddies of children, surgical robots have extended surgeons’ dexterity and accessibility, and mobile robots and flying robots explore unknown environments for us.
However, robots are still far away from our expectations, due to the limitations on systematic reliability, robustness, environmental adaptability, intelligence and so on. How can we address these problems and allow robots to bring more convenience to our lives? If we look back, the classical system modeling approaches laid down the solid foundation for modern robotics, and probabilistic robotics greatly extended the application of robotic systems through improving environmental adaptability and systematic robustness. And now, with the deeper understanding of biological systems and neuro systems, more and more neurorobotic and biologically inspired solutions are further improving robot performance and are extending the application of robots. It is clear that the appearance of these techniques will bring another big leap in robotics research. In this topic, we will especially focus on the neural and bio-inspired solutions to the control problem, which is the key and fundamental problem in robotics.
This topic is to disseminate the new findings in the robotics community and the neuroscience community, in order to promote cross-disciplinary communication and fusion. We hope this topic will serve as a platform that facilitates the communication between neuroscience researchers and robotics researchers, and inspires the marriage of the neural and bio-inspired processing research and the robotics research. We strongly believe such research can greatly improve the precision and reliability of robotic systems and promote research of the robot control problem.
The areas of interests include but are not limited to:
• Locomotion and Manipulator Control
• Medical Robot and Control
• Sensing, signal processing, and decision making of robots.
• Neural networks (feed-forward, recurrent, and deep) for robot data processing
• Bionic robots and bio-inspired robot control
• Intelligent modeling of robotic systems