Anya Petrovskaya, PhD
Research Consultant, Computer Science Department
In December 2015, I have co-founded Eonite Perception --- a startup focused on advanced 3D perception, mapping, and tracking.
· In June 2014, I have been named Best Associate Editor at ICRA 2014.
· In December 2012, my thesis work has been honored with a Best Ph.D. Dissertation Award by IEEE Intelligent Transportation Systems Society (ITSS).
3D Perception for AR/VR. CS294 Lecture, Stanford University, USA. May 24, 2016.
Sub-Millimeter Accurate Mapping and Tracking for Robots, Drones, and AR/VR. At Industry Forum, ICRA 2016, Stockholm, Sweeden. May 19, 2016.
The Smart Robot Revolution. Live Chat orginized by IEEE WIE, Stanford University, USA, February 2014.
Abstract: In the past, robots have been confined to manufacturing applications in strictly controlled environments. However, this is about to change. We are entering an era, when robots will become plentiful in our everyday lives. What makes the new robots different from robots of the past are their brains and their ability to perceive our environments. Join this chat to learn how recent advances in Robotics and AI are leading to new industry and consumer applications that will change the world. Robotics expert, Dr. Anna Petrovskaya, will discuss her experiences with autonomous cars, robotic perception, and the many promising start-ups that have sprung up to bring about the smart robot revolution. [more] [video]
Reliable perception is crucial for robots operating in uncertain human environments. To enable reliable robotic perception, we developed a guaranteed inference algorithm called Guaranteed Recursive Adaptive Bounding (GRAB). Unlike most modern inference methods, GRAB algorithm guarantees that all optimal solutions will be found. In addition , it dramatically outperforms state-of-the-art. In experiments, GRAB lead to 100% safe decision making, provided 1mm robot localization accuracy based on laser sensors, and resulted in reliable 6DOF object pose estimation based on tactile data.
Humans are capable of performing many tasks relying just on the sense of touch. To enable robots to do the same, we explore robotic perception via contact. [more]
STAIR stands for STanford AI Robot project. Its goal is to build a single robot that combines techniques from all areas of AI to carry out a wide range of day-to-day tasks. My work focuses on teaching the robot to navigate hallways and open doors. [more]
Autonomous Urban Driving
Knowledge Base of Tactile Sensors
In this ongoing project, our goal is to build a complete knowledge base of tactile sensing technologies. [more]
Links to groups I work with:
Gates Building 1A, Room 112, Stanford, CA 94305
anya at cs.stanford.edu
Awareness of Road Scene Participants for Autonomous Driving. A. Petrovskaya, M. Perrollaz, L. Oliveira, L. Spinello, R. Triebel, A. Makris, J.-D. Yoder, C. Laugier, U. Nunes, and P. Bessiere. In Handbook of Intelligent Vehicles, pp. 1383-1432, Springer 2012. [pdf] [SpringerLink] [cite]
Towards Dependable Robotic Perception. Anna Petrovskaya. PhD Thesis, Computer Science Department, Stanford University, June 2011. [pdf]
· Mobile Manipulation Workshop (MMW 2010) at RSS in Zaragoza, Spain, June 2010
· Dependable Robots in Human Environments Workshop (DRHE 2010) in Toulouse, France, June 2010. This version is titled “Towards Dependable Perception: Guaranteed Inference for Global Localization”.
Model Based Vehicle Detection and Tracking for Autonomous Urban Driving. Anna Petrovskaya and Sebastian Thrun. Autonomous Robots Journal, vol. 26(2-3), pp. 123--139, April 2009. [pdf] [Springer] [more]
Tactile Sensors. Sherri Billimoria, Nandini Mukherjee, Anna Petrovskaya and Oussama Khatib. Project report. Stanford University, 2008. [pdf]
Junior: The Stanford Entry in the Urban Challenge. M. Montemerlo, J. Becker, S. Bhat, H. Dahlkamp, D. Dolgov, S. Ettinger, D. Haehnel, T. Hilden, G. Hoffmann, B. Huhnke, D. Johnston, S. Klumpp, D. Langer, A. Levandowski, J. Levinson, J. Marcil, , D. Orenstein, J. Paefgen, I. Penny, A. Petrovskaya, M. Pflueger, G. Stanek, D. Stavens, A. Vogt, and S. Thrun. Field and Service Robot Journal 2008. [pdf] [more]
Identifying Physical Properties of Deformable Objects by Using Particle Filters. Steve Burion, Francois Conti, Anna Petrovskaya and Oussama Khatib. International Conference in Robotics and Automation (ICRA), Pasadena, USA, May 2008.
Touch Based Perception for Object Manipulation. Anna Petrovskaya, Oussama Khatib, Sebastian Thrun, and Andrew Y. Ng. Robotics Science and Systems Conference (RSS), Robot Manipulation Workshop, Atlanta, GA, 2007. [pdf]
Probabilistic Estimation of Whole Body Contacts for Multi-Contact Robot Control. Anna Petrovskaya, Jaeheung Park, Oussama Khatib. IEEE International Conference on Robotics and Automation (ICRA), Rome, Italy, 2007. [pdf]
Probabilistic Mobile Manipulation in Dynamic Environments, with Application to Opening Doors. Anna Petrovskaya and Andrew Y. Ng. International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, 2007. [pdf]
Bayesian Estimation for Autonomous Object Manipulation Based on Tactile Sensors. Anna Petrovskaya, Oussama Khatib, Sebastian Thrun, and Andrew Y. Ng. IEEE International Conference on Robotics and Automation (ICRA), Orlando, Florida, 2006. [pdf] Also poster version from WiML06 [ppt]
At ICRA 2006, Orlando, Florida