Latest Past Events

Sensing and perception for humanoid robots

Online meeting through WebEx system

Presented by Dr. Lorenzo Natale Humanoid Sensing and Perception laboratory Italian Institute of Technology Genova, Italy Sign up for the event now Abstract Robots can actively interact with the environment and humans using their sensory system to learn about objects and their properties. To extract structured information, however, the robot needs to be endowed with appropriate sensors, fast learning algorithms, and exploratory behavior that guide the interaction with the world. In this talk I will revise the research activities of the Humanoid Sensing and Perception laboratory at the Italian Institute of Technology. I will briefly revise past work on the use of visual and tactile feedback to explore objects and control the interaction between the hand and the objects. I will then present our recent work on behavior modelling using behavior trees, and the study of fast algorithms for learning visual segmentation and object tracking. Presenter biography Lorenzo Natale is Tenured Senior Researcher at the Italian Institute of Technology and coordinator of the Center for Robotics and Intelligent Systems. He received his degree in Electronic Engineering (with honours) and Ph.D. in Robotics from the University of Genoa. He was later postdoctoral researcher at the MIT Computer Science and Artificial Intelligence Laboratory. He was invited professor at the University of Genova where he taught the courses of Natural and Artificial Systems and Antropomorphic Robotics for students of the Bioengineering curriculum. Since 2020 he is visiting Professor at the University of Manchester. Lorenzo Natale has contributed to the development of various humanoid platforms. He was one of the main contributors to the design and development of the iCub platform and he has been leading the development of the iCub software architecture and the YARP middleware. His research interests range from vision and tactile sensing to software architectures for robotics. He has been principal investigator and co-principal investigator in several EU funded projects. He was general chair of IEEE ARSO 2018 and served as Program Chair of ICDL-Epirob 2014 and HAI 2017. He is Specialty Chief Editor for the Humanoid Robotics Section of Frontiers in Robotics and AI, associate editor for IEEE-Transactions on Robotics and IEEE Robotics and Automation Letters. He is Ellis fellow and Core Faculty of the Ellis Genoa Unit.

E3MoP: Multi-layer Real-time Efficient Motion Planning for Mobile Robots

Online meeting through WebEx system

Presented by Dr. Xuebo Zhang Department of Intelligent Science Nankai University, China Sign up for the event now Abstract As one of the most fundamental research topics in robotics, high-performance motion planning is still challenging in many applications because it needs to consider many constraints as well as many performance indexes simultaneously, such as computational efficiency, motion efficiency, safety issues, smoothness, uncertain environmental factors, robot kinematic and dynamic constraints, and so on. In this talk, I will discuss our recently developed motion planning approach called E3MoP, a three-layer efficient motion planning framework consisting of global path planning, local path planning and velocity planning. For global planning, I will talk about a new heuristic-guided approach to increase the computational efficiency with lower memory consumption. For local planning, a decoupling framework consisting of local path planning and velocity planning, will be discussed. A sparse optimization approach to generate a safe and smooth local path will be presented, and then a real-time, complete and time-optimal velocity planning approach that was proposed to generate the most efficient trajectory along the preplanned path with rigorous mathematical proofs. Such a hierarchical motion planning framework has been experimentally verified, and comparative results showed its remarkable improvements in terms of computational efficiency, motion efficiency, and the trajectory flexibility to help robot navigation in challenging environments. Presenter biography Dr. Xuebo Zhang received the B.Eng. degree in Automation from Tianjin University in 2006, China, and the Ph. D. degree in Control Theory and Control Engineering from Nankai University in 2011, China. From July 2011, he joined the Institute of Robotics and Automatic Information Systems (IRAIS), Nankai University, China. Currently, he is a full professor and the head of Department of Intelligent Science. His research interests include planning and control of autonomous robotic and mechatronic systems with focus on time-optimal planning and visual servo control; intelligent perception including robot vision, visual sensor networks, SLAM, etc. Prof. Zhang is the PI of more than 20 projects across both academic and industrial fields. He is a Technical Editor of the IEEE/ASME Transactions on Mechatronics and the Associate Editor for ASME Journal of Dynamic Systems, Measurement and Control.  

A task space motion planning algorithm for nonholonomic systems based on Lie-algebraic evaluation of intermediate configurations

Online meeting through WebEx system

Presented by Arkadiusz Mielczarek Department of Cybernetics and Robotics Wrocław University of Science and Technology Sign up for the event now   Abstract The vast majority of motion planning methods for nonholonomic systems (which include, but are not limited to, wheeled mobile robots) are well-established in the configuration space. However, this space is often not optimal for practical tasks such as collision avoidance. It is common to describe obstacles in a space that is a projection of a nonholonomic system's configuration space, e.g. (x,y) coordinates in the case of wheeled mobile robots. During the presentation, a modified version of the Lie-algebraic motion planning method for a nonholonomic system with an output function will be introduced. Planning in the task space (usually a subspace of the configuration space) provides more opportunities for optimization in the null space. To exploit this fact, an easy-computable algorithm for an intermediate configuration evaluation will be presented along with a comparison of its results with the energy cost of motion. Finally, a multi-step trajectory planning algorithm that optimizes the energy of motion using the aforementioned evaluation will be discussed. Presenter biography Arkadiusz Mielczarek is a PhD student in the Department of Cybernetics and Robotics of the Wrocław University of Science and Technology. He received his MSc degree in control theory and robotics in 2016 from the same university. His research interests include nonholonomic motion planning, nonlinear control theory and signal processing (mainly in bio-medical applications).