In this talk, how to design the locomotion system of a biped robot that can move flexibly and robustly in the real world is discussed. The robot should perceive how the world and the robot itself are and determine how to behave in real-time even from uncertain, incomplete, noisy and unpredictable sensory information.
Area 1 - Simulation Tools and Platforms
The overall system should not form a sequential architecture, where each process waits for complete information from the former process, as employed in the conventional systems, but "the subsumption architecture", where a homeostatic controller works in the lower layer and upper layer subsumes it. This is not easy since each process including navigation, mapping and perception has to be implemented in a successive way, i.
Some key technologies to build up such a system are presented. He is interested in the modeling and control of electro-mechanical systems with applications to medical robotics. Medical robotic systems strive to make surgical interventions less invasive, less risky for both patients and clinicians, more efficient, and capable of achieving better patient outcomes. Increasing the targeting accuracy during robot-assisted minimally invasive surgical procedures requires the integration of pre-operative plans and intra-operative control.
In this talk, I will discuss how wirelessly controlled agents might offer advantages in terms of reduced invasiveness and untethered access to deep-seated regions within the human body. On that account, this talk covers the closed-loop control of microparticles, miniaturised hydrogel grippers, microjets, and magnetosperms. His research fields deal with the design, modeling, signal estimation and control techniques for piezoelectric systems with applications on microrobotics and automation at small scale.
How robots learn to see
The paper 'Complete open loop control of hysteretic, creeped and oscillating piezoelectric cantilever' was among the 5 most cited papers of the IEEE Transactions on Automation Science and Engineering of the year. In , he received the Big-On-Small award which is to recognize a young professional with excellent performance and international visibility in the topics of manipulation, automation and robotics at small scales. Piezoelectric materials have strong recognition in the development of actuators, systems and microrobots devoted to work at small scale.
This recognition is thanks to their high resolution down to nanometer , high bandwidth in excess of the kiloHertz , high force density for certain piezomaterials, ease of integration driven by electricity , and physical reversibility usable for sensors or for actuators. In counterpart, piezoelectric systems exhibit low deformation classically 0. These behaviors drastically damage or degrade the final tasks to be executed, such as precise positioning, imaging or manipulation. This talk describes first my works on the developments of piezoelectric systems that account for these limitations during the design.
Then, I present their modeling for control purpose in order to reach certain severe performances when working at small scale. Because measurement is essential in control, I finally present some measurement and estimation techniques among which self-sensing approach is one of the feature for piezoelectric systems. In the meantime I will highlight how measurement is still a great challenge in automation at small scale due to the lack of convenient sensors.
Control with sensors minimization in piezoelectric systems working at small scale. In this talk, the challenge in controlling piezoelectric systems working at small scale is discussed. Their control and automation suffer from the lack of convenient and embedded sensors to complete the real-time measurement and feedback. The first part of the talk deals with an alternative feedback control architecture based on the piezoelectric self-sensing approach.
This approach permits a real-time and fully embedded measurement, or almost.
Bin-Picking: New Approaches for a Classical Problem (Studies in Systems #44) (Hardcover)
In the second part, open-loop or feedforward control architecture for piezoelectric systems is presented. The advantage of this approach is its full integration and its low cost, though robustness could be compromised in some case. Robotics have played important roles in biomedical applications owing to its advantages in precision, stability, dexterity and productivity. This talk will give two specific examples to demonstrate the above two types of robotic system in biomedical applications, i.
Lastly, the prospects of the micro-nano robotic systems will be discussed. His research interests include cognitive robotics, computer vision, and machine learning.
Robots need to perceive their environment to act in a goal-directed way. While mapping the environment geometry is a necessary prerequisite for many mobile robot applications, understanding the semantics of the environment will enable novel applications, which require more advanced cognitive abilities. In the talk, I will report on methods that we developed for learning tasks like the categorization of surfaces, the detection, recognition, and pose estimation of objects, and the transfer of manipulation skills to novel objects. We demonstrated the utility of semantic environment perception with cognitive robots in multiple challenging application domains, including domestic service, space exploration, search and rescue, and bin picking.
Picking objects from cluttered piles is a challenging task with great application potential, e. A key prerequisite for cluttered bin picking is the understanding of complex manipulation scenes. In the talk, I will report on efficient methods that we developed for learning tasks like semantic segmentation, object detection, pose estimation of objects, and the transfer of manipulation skills to novel objects.
Before joining Northeastern, Dr. Amato was a Research Scientist at Aptima, Inc.
He has published papers in leading artificial intelligence and robotics conferences including winning a best paper prize at AAMAS and being nominated for the best paper at RSS He also successfully co-organized several tutorials on team decision making and co-authored a book on the same subject. His research focuses on decision making under uncertainty in multi-agent and multi-robot systems. He obtained the Ph. Piaggio" at the Faculty of Engineering, in January She has been Assistant Professor from to She has been Visiting Scholar at M.
Show More. He teaches and conducts research in the fields of autonomous and embedded systems, robotics and artificial intelligence. In this function, he was in involved in the development of the EU flagship projects and was ab author of the report "European Challenges and Flagships ". In , he co-founded "fortiss", the Munich Institute for Software, which has since been transformed into a state institute of Bavaria.
His focus there is on modeling, simulation and optimization for infrastructure, both in methodical development and in the construction of practical systems. Brain-Derived Products : it links brain research to information technology by using scientific results e. Virtualised Brain Research : it links information technology to brain research by designing new tools for brain researchers, with which they can design experiments and then carry them out in simulation.
We envision that the unique integration of the above three paths will lead to widespread mutually beneficial fertilization and research acceleration through the two-way inspiration of the involved disciplines. Zhijun Li received the Ph. China, in In this talk, we present kinds of wearable robots to achieve many activities of daily living ADL.
The developed service robots include upper limb exoskeleton, lower limb exoskeleton, intelligent robotic wheelchairs, wheeled inverted transportation, and interactive tour guide operation robot, and neural prosthesis, bionic hands, etc. The various advanced control approaches including skill transfer technique, intelligent control, bio-feedback control have been proposed and verified in these developed platforms. The development of robotic systems capable of sharing with humans the load of heavy tasks has been one of the primary objectives in robotics research.
At present, in order to fulfill such an objective, a strong interest in the robotics community is collected by the so-called wearable robots, a class of robotics systems that are worn and directly controlled by the human operator. Prostheses, powered orthoses, and exoskeletons are described for upper limb, lower limb, and whole body structures.
- [PDF Download] Bin-Picking: New Approaches for a Classical Problem [Download] Online.
- Bin-Picking | rasleopapo.tk!
- Distinguished Lecturers by TC - IEEE Robotics and Automation Society.
He received his Ph. His research covers control theory and its applications to robotic systems. Su has authored or coauthored over journal publications in robotics, mechatronics and control that have resulted in over 10, citations. Su has delivered over 80 invited talks, including plenary conference presentations and seminars.
He was a recipient of several best conference paper awards. He has also served for many conferences as an organizing committee member. Therefore, it is essential that the developed exoskeletons could exhibit biological behavior and performance. Considering human joints, one of the important features is the physical properties of the musculotendinous and their resultant impedance.
However, the impedance profiles of the human joints vary substantially during motion. Therefore, exoskeletons should accordingly respond and adapt to these impedance profiles. This talk presents methods to develop adaptive impedance control of exoskeletons using biological signals. Then, an impedance algorithm is proposed transferring stiffness from human operator through the surface electromyography sEMG signals, being utilized to design the optimal reference impedance model. In order to verify the proposed approach, the actual implementation has been performed using a real robotic exoskeleton and a human operator.
With the advances in robot control RC systems, the relationship between humans and robots has thus become increasingly intimate, and many human-robot collaboration systems have been developed. However, it is hard for a disabled person to operate a robot because of the loss of motion capacity or reduced sensing ability. The target objects are detected by a vision system and then displayed to the user in a video that shows them fused with flicking diamonds. Through the analysis of the invoked electroencephalograph EEG signals, a brain computer interface BCI is developed to infer the exact object that is required by the user.
These results are then transferred to the shared control system, which is enabled by visual servoing VS techniques to achieve accurate object manipulation.