2023 - Collaborative Robotics Workshop
What: Workshop - 3 talks from experts in the area of collaborative robotics and physical human robot interaction
When: 10:45am - 1pm
Where: G205, Karlovo náměstí 13, Praha 2
10:45 - 11:30: Bakir Lacevic, Associate Professor, Faculty of Electrical Engineering, University of Sarajevo, Bosnia and Herzegovina
Title: Sampling-based motion planning for robotic manipulators: distance-based approach
Abstract: The original sampling-based algorithms (e.g., PRM, RRT), with a variety of follow-ups, typically use collision checking to validate local paths up to a given resolution. Free local paths are assembled into a graph capturing the connectivity of free configuration space to find collision-free paths. In general, distance/proximity query implies a computational surplus compared to a Boolean collision check. However, distance information can be used to infer about the free volumes of C-space, which may serve as generators of arbitrarily many local paths that are collision-free by design. A method to quickly explore C-spaces of robotic manipulators and thus facilitate motion planning is described. The method is based on a geometrical structure called generalized bur. It is a star-like tree, rooted at a given point in free C-space, and with an arbitrary number of guaranteed collision-free edges computed using distance information from the workspace and simple forward kinematics. Generalized bur captures large portions of free C-space, enabling accelerated exploration. When plugged in a suitable RRT-like planning algorithm, generalized burs enable significant performance improvements with respect to competing algorithms. Of particular interest are human-centric environments where humans/obstacles move and thus render the problem of motion planning remarkably challenging.
11:30-12:15: Michael Hofbaur, Professor for modular Robotics @ University of Klagenfurt Department of Smart Systems Technologies, Austria
Title: Safe Autonomous Machines
Abstract: Robots or automated machines in general are becoming more and more important for a wide spectrum of applications where these machines operate within the vicinity of humans. Being safe for humans and the environment is thus of paramount importance. Working in non-deterministic environments, however, requires a high level of awareness that goes beyond the capacity of classic automation. So, in addition to being physically safe, it is helpful if these machines have a high-level of self- and environmental awareness and, as a long-term goal being able to anticipate risk and act accordingly. The talk will highlight this overall vision for safe and autonomous machines and detail individual aspects of safety, self-diagnosis and intelligent control.
12:15 - 13:00: Andrea Maria Zanchettin, Associate Professor at Politecnico di Milano, Italy
Title: Collaborative robots - From safe to intelligent co-workers
Abstract: Future manufacturing paradigms will require flexibility and cognitive capabilities to respond to the increasing need for mass customisation. Production environments will be populated by humans and robots. Despite the advancements in technology, today’s collaborative robots are primarily only able to safely stop in case of unintended contacts or collisions with humans, without being able to effectively collaborate with them. This talk will address the problem of synchronising human and robot activities and proposes a formal control architecture to govern the execution of collaborative application, requiring some degree of coordination between the human and the robot, while guaranteeing safety.
