TUM-Robotics Talks is an initiative of the Munich Institute of Robotics and Machine Intelligence (MIRMI) where international experts and pioneers in the field of Robotics and Machine Intelligence present their research.
Rabab Benotsmane (University of Miskolc) and Majid Khadiv (Technical University of Munich) talk on Collaborative Robot Arms and Legged Locomotion at TUM-MIRMI
Talk 1: Exploring the Design and Development Challenges of Collaborative Robot Arms
Prof. Rabab Benotsmane (University of Miskolc / Hungary)
Talk 2: Optimal control and learning for legged locomotion
Prof. Majid Khadiv (Technical University of Munich / Germany)
TUM-Robotics Talks | 29. Nov 2023, 17:00 – 19:00 CET | Location: M001, Georg-Brauchle-Ring 60-62, 80992 Munich, Germany. See map
Prof. Rabab Benotsmane
Exploring the Design and Development Challenges of Collaborative Robot Arms
Abstract: Collaborative robot arms, or 'cobots' are significantly making a great impact on increasing the productivity, and the flexibility to create cooperation-friendly workspaces. At present, cobot systems are being widely used in various industrial sectors beside the traditional robots, which lead us to think “if the industrial market had already produced millions of traditional industrial robots, is it possible to upgrade them to be smarter and cooperative ?”. This presentation explores the potential of upgrading the traditional industrial robots to collaborative robots (cobots). We will discuss the basic requirements of cobot arm system, including the advanced sensors and AI/ML techniques to make this transformation possible. The last part of the presentation will be an open, friendly discussion to exchange the knowledge to the different related fields. Join us for an easy-to-understand exploration of making robots and humans work together again in the daily life.
Short Bio: Rabab Benotsmane is an assistant professor in the Institute of Automation and Info-Communication at the University of Miskolc, Hungary. Her field is Modeling, Control and Trajectory Optimisation of Dynamic Systems (Autonomous Vehicles – Serial Robots). She earned the PhD degree in Robotics in 2021, where the research focused on Collaborating Robots Arm Using AI Techniques. Since 2021, she has been actively engaged in teaching and research at the Institute of Automation and Info-Communication, where she led courses on Automation, Robotics, and Embedded Systems. Furthermore, she actively participates in diverse projects related to the gas and oil industry, drone navigation, and AI/ML related to the healthcare. She served as a session chair, organisation committee member and editor in IEEE ICCC’23 (International Carpathian Control Conference). She has published more than 20 peer-reviewed journal articles and conference papers in these domains.
Prof. Majid Khadiv
Optimal control and learning for legged locomotion
Abstract: Planning motions for loco-manipulation systems is extremely complicated due to their highly nonlinear dynamics, under-actuation and inherent instability, as well as the hybrid nature of contact interaction. The two dominant approaches to control legged robots in multi-contact scenarios are optimal control (OC) and reinforcement learning (RL). In this talk, I will present my recent research efforts on devising a general framework based on OC and RL to efficiently control legged systems. I will also discuss my perspectives on how to generalize this framework toward realizing a fully autonomous humanoid robot.
Short Bio: Majid Khadiv is an assistant professor in the school of Computation, Information and Technology (CIT) at the Technical University of Munich (TUM), Germany. He leads the chair of "AI Planning in Dynamics Environment" at TUM and is also a member of the Munich Institute of Robotics and Machine Intelligence (MIRMI). Prior to joining TUM, he was a research scientist at the Empirical Inference department at the Max Planck Institute for Intelligent systems (Director: Prof Bernhard Schölkopf). Before that he was a postdoctoral researcher in the Machines in Motion, a joint laboratory between New York University and Max Planck Institute (Director: Prof. Ludovic Righetti). Since the start of his PhD in 2012, he has been performing research on motion planning, control and learning for legged robots ranging from quadrupeds, lower-limb exoskeleton up to humanoid robots. He has published 23 peer-reviewed journal articles and more than 21 peer-reviewed conference papers in these domains. He is currently an associate editor of the International Journal of Robotics Research (IJRR) and has served for several years as associate editor in major robotics conferences (ICRA, IROS, Humanoids).