From RRTs to the Path to Minimalism

Abstract :

This talk will survey work from my research group over the past three decades, while emphasizing a spectrum that ranges from robots with complete, perfect models to robots with little or no memory or computational abilities.  At one extreme, strong geometric information is sensed and encoded, leading to problems such as classical motion planning.  This part of the talk covers rapidly exploring random trees
(RRTs), including a recent enhancement called bang-bang RRTs.  Then the talk progresses toward an egocentric or situated view of robot development that takes into account its space of possible environments
and specific tasks.  How much does a robot need to sense and remember to successfully interact with its environment?  This question is fundamental to robotics and distinguishes it from other fields such as
computer science or control theory.  If machine learning is the goal, then the question becomes what are the minimal, ideal models that could possibly be learned?  Thus, emphasis in this part is placed on determining the minimal amount of information necessary to solve tasks, thereby giving the robot the smallest possible `brain'.  On the path to minimalism, weak geometric information is considered in the form of combinatorial or relational sensing and filtering.  Eventually, topological and set-based models are considered at the minimalist extreme.


Bio:

Steven M. LaValle is Professor of Computer Science and Engineering, in Particular Robotics and Virtual Reality, at the University of Oulu since 2018.  Since 2001, he has also been a professor in the Department of
Computer Science at the University of Illinois.  He has previously held positions at Stanford University and Iowa State University.  His research interests include robotics, virtual and augmented reality, sensing, planning algorithms, computational geometry, and control theory.  In research, he is mostly known for his introduction of the Rapidly exploring Random Tree (RRT) algorithm, which is widely used in robotics and other engineering fields.  In industry, he was an early founder and chief scientist of Oculus VR, acquired by Facebook in 2014, where he developed patented tracking technology for consumer virtual reality and led a team of perceptual psychologists to provide principled approaches to virtual reality system calibration, health and safety, and the design of comfortable user experiences.  From 2016 to 2017 he was Vice President and Chief Scientist of VR/AR/MR at Huawei Technologies, Ltd.  He has authored the books Planning Algorithms, Sensing and Filtering, and Virtual Reality.  He currently leads an Advanced Grant project from the European Research Council on the Foundations of Perception Engineering.