RSS Workshop on

Robust Task and Motion Planning

Key Facts

Workshop Date
Sunday, June 23, 2019 @ RSS 2019
Workshop Location
078 00 014, Georges-Koehler-Allee, University of Freiburg, Freiburg, Germany
Submission Deadline
May 28, 2019 (AoE)
Acceptance Notification
June 01, 2019
Neil T. Dantam, Ye Zhao, Lydia E. Kavraki
  1. Description
  2. Invited Speakers
  3. Schedule
  4. Accepted Posters


This workshop will address a growing need in Task and Motion Planning (TMP) to tackle the uncertainty, non-determinism, and complex dynamics of real-world environments. TMP is an active research topic with related work proceeding in the robotics, AI, controls, and formal methods communities. The varying focus and assumptions between different communities has produced a proliferation of approaches addressing different aspects of the problem space. This workshop will bring together researchers from these different communities to discuss the challenges and contrasting approaches for robust TMP. We hope to build on past RSS workshops on formal methods and benchmarks for TMP to now identify connections among robust TMP approaches and to better define the scenarios and motivating problems on which the community should focus.


This workshop is intended for researchers in robotics, AI planning, motion planning, and controls who are interested in improving the autonomy of robots for complex, real-world tasks such as mobile manipulation.

The two main target audiences for the workshop are: (1) members actively researching new methods, future trends and open questions in task and motion planning (2) people who are interested in learning about the current state-of-the-art in order to incorporate these methods into their own projects. We strongly encourage the participation of graduate students.

This workshop follows the previous workshops on Task and Motion Planning at RSS 2016, RSS 2017, and RSS 2017, from the same organizers. Past workshops received excellent participation with approximately 50 attendees, 10 presented posters, and engaging group discussions. During the previous workshops, numerous questions were raised regarding handling uncertainty and operating in real-world environments. This workshop aims to address these needs with specific focus on robust TMP for real-world uncertainty and complex dynamics.


Invited Speakers

Tomás Lozano-Pérez (MIT, USA)

Title: Learning Methods for Combined Task and Motion Planning

Tomas Lozano-Perez Bio: Tomas Lozano-Perez is currently the School of Engineering Professor in Teaching Excellence at the Massachusetts Institute of Technology (MIT), USA, where he is a member of the Computer Science and Artificial Intelligence Laboratory. He has been Associate Director of the Artificial Intelligence Laboratory and Associate Head for Computer Science of MIT's Department of Electrical Engineering and Computer Science. He was a recipient of the 2011 IEEE Robotics Pioneer Award and a 1985 Presidential Young Investigator Award. He is a Fellow of the AAAI, a Fellow of the ACM, and a Fellow of the IEEE. His research has been in robotics (configuration-space a pproach to motion planning), computer vision (interpretation-tree approach to object recognition), machine learning (multiple-instance learning), medical imaging (computer-assisted surgery) and computational chemistry (drug activity prediction and protein structure determination from NMR & X-ray data). His current research is aimed at integrating task, motion and decision-theoretic planning for robotic manipulation.

Taskin Padir (Northeastern University, USA)

Taskin Padir

Title: Motion Planning for Humanoids for Task Completion in Constrained Environments

Bio: Taskin Padir is an Associate Professor of Electrical and Computer Engineering at Northeastern University. His research interests involve humanoid robots, dexterous manipulation, model-based robot design, human-supervised robot autonomy, and medical cyber-physical systems. He was won the Kalenian Award for Entrepreneurial Spirit, the HEART: Humans Empowered with Assistive Robot Technologies award, and the Romeo L. Moruzzi Young Faculty Award for Innovation in Undergraduate Education.

Volkan Patoğlu (Sabancı University, Turkey)

Title: A Hybrid Planning Approach to Robot Construction Problems

Volkan Patoğlu

Bio: Volkan Patoğlu is an Associate Professor of Mechatronics at Sabancı University. His research is in the area of physical human-machine interaction, in particular, design and control of force feedback robotic systems with applications to rehabilitation and skill training. His research extends to cognitive robotics. Dr. Patoglu has been honored with Career Award by the Scientific and Technological Research Council of Turkey (2008), Meritorious Service Award by IEEE Transactions of Haptics (2011 and 2018), Best Application Paper Award by IEEE/RSJ International Conference on Intelligent Robots and Systems (2013), Best Conference Paper Nomination by IEEE International Conference on Robotics and Automation (2015), and Young Scientist Award by Science Academy (2015). He received his Ph.D. from the University of Michigan and worked as a post doctoral research fellow at the University of Michigan and as a post doctoral research associate at Rice University.

Luis Sentis (UT Austin, USA)

Title: Whole-Body Control for Dynamic Locomotion and Asymmetric Exoskeletons

Luis Sentis

Bio: Luis Sentis is an Associate Professor in the Department of Aerospace Engineering at the University of Texas at Austin and a contractor for NASA Johnson Space Center. He leads the Human Centered Robotics Laboratory, an experimental laboratory focusing on control and embodiment of humanoid robots. He was the UT Austin's Lead for DARPA's Robotics Challenge with NASA Johnson Space Center where he helped to design and test the Valkyrie humanoid robot. His research has been funded by NASA, the Office of Naval Research, NSF, DARPA, and private companies. He was awarded the NASA Elite Team Award for his contributions to NASA’s Johnson Space Center Software Robotics and Simulation Division, and is also co-founder and scientific advisor of Apptronik Systems Inc., a company focusing on human-centered robotic augmentation systems and educational robotic laboratories.

Elisa Tosello (University of Padova, Italy)

Title: A Cloud-based approach for Task And Motion Planning: combining Deep Reinforcement Learning and Knowledge Bases

Elisa Tosello

Bio: Elisa Tosello is a Post-Doc and Contract Professor in the Department of Information Engineering at the University of Padova. She received her Ph.D. (2017), M.Sc. (2012), and B.Sc. (2009) in Computer Engineering at the University of Padova. Her research focuses on the Hardware and Software reuse for the resolution of the Motion Planning problem for multi-Degrees of Freedom robots. She focuses her attention on the resolution of the Navigation Among Movable Obstacles and Task and Motion Planning problem.

Marc Toussaint (University of Stuttgart / Max Plank Institute, Germany)

Title: Logic-Geometric Programming -- what are limits and challenges?

Marc Toussaint

Bio: Marc Toussaint is a professor for Machine Learning & Robotics at the University of Stuttgart and a Max Planck Fellow at the Max Planck Institute for Intelligent Systems. His research focuses on the combination of decision theory and machine learning, motivated by applications in robotics. The goals are learning systems able to reason about their own state of knowledge (e.g., in a Bayesian way), to decide which actions might yield the most informative future data, and to make these systems learn even better and eventually solve problems. His work takes the form of Reinforcement Learning, Planning, and Active Learning in probabilistic relational domains. Furthermore, a growing focus of his lab is real-world robotic systems and joint symbolic and geometric planning, including trajectory optimization and optimal control methods.



09:00-09:15 Workshop Introduction
Dynamics Session
09:15-9:45 Luis Sentis: Whole-Body Control for Dynamic Locomotion and Asymmetric Exoskeletons
09:45-10:15 Volkan Patoğlu: A Hybrid Planning Approach to Robot Construction Problems
10:15-10:30 Dynamics Discussion
10:30-11:00 Coffee Break
Manipulation Session
11:00-11:30 Tomás Lozano-Pérez: Learning Methods for Combined Task and Motion Planning
11:30-12:00 Taskin Padir: Motion Planning for Humanoids for Task Completion in Constrained Environment
12:00-12:15 Manipulation Discussion
12:15-13:45 Group Lunch and Discussion
Learning and Optimization Session
13:45-14:15 Elisa Tosello: A Cloud-based approach for Task And Motion Planning: combining Deep Reinforcement Learning and Knowledge Bases
14:15-14:45 Marc Toussaint: Logic-Geometric Programming -- what are limits and challenges?
14:45-15:00 Learning and Optimization Discussion
15:00-15:30 Coffee Break
Poster Session
15:30-16:00 Poster Lightning Talks
16:00-16:45 Poster Presentations
16:45-17:15 Panel Discussion and Wrap-Up