Light-Sensitive Displays
Abstract: Nobel prize winner M. G. Lippmann described his dream of an ideal display as a “window into the world.” “While the current most perfect photographic print only shows one aspect of reality, reduced to a single image fixed in a plane, the direct view of reality offers, as we know, infinitely more variety.” Changing [...]
Acquiring and Transferring Generalizable Vision-based Robot Skills
Abstract: In recent years, there have been great advances in policy learning for goal-oriented agents. However, there are still major challenges brought by real-world constraints for teaching highly generalizable and versatile robot policies in a cost efficient and safe manner. In this talk, I will argue that instead of aiming to teach large motion repertoires [...]
Carnegie Mellon University
Robot Learning in Homes – Improving Generalization and Reducing Dataset Bias
Abstract: Data-driven approaches to solving robotic tasks have gained a lot of traction in recent years. However, most existing policies are trained on large-scale datasets collected in curated lab settings. If we aim to deploy these models in unstructured visual environments like people’s homes, they will be unable to cope with the mismatch in data [...]
Learning to localize and anonymize objects with indirect supervision
Abstract: Computer vision has made great strides for problems that can be learned with direct supervision, in which the goal can be precisely defined (e.g., drawing a box that tightly-fits an object). However, direct supervision is often not only costly, but also challenging to obtain when the goal is more ambiguous. In this talk, I [...]
What People See in a Robot: A New Look at Human-Like Appearance
Abstract: A long-standing question in HRI is what effects a robot’s human-like appearance has on various psychological responses. A substantial literature has demonstrated such effects on liking, trust, ascribed intelligence, and so on. Much of this work has relied on a construct of uni-dimensional low to high human-likeness. I introduce evidence for an alternative view according to which [...]
Safe Learning in Robotics
Abstract: A great deal of research in recent years has focused on robot learning. In many applications, guarantees that specifications are satisfied throughout the learning process are paramount. For the safety specification, we present a controller synthesis technique based on the computation of reachable sets, using optimal control and game theory. In the first part [...]
Carnegie Mellon University
Online, Interactive User Guidance for High-dimensional, Constrained Motion Planning
Abstract: We consider the problem of planning a collision-free path for a high-dimensional robot. Specifically, we suggest a planning framework where a motion-planning algorithm can obtain guidance from a user. In contrast to existing approaches that try to speed up planning by incorporating experiences or demonstrations ahead of planning, we suggest to seek user guidance [...]