The goal of this workshop is to highlight recent advances in Task And Motion Planning, as well as in ontology frameworks and Cloud engines for robotic applications, and to explore new methods for leveraging knowledge for an efficient combination of the planning levels. We expect participating researchers to identify and address important challenges, techniques, and benchmarks necessary for combining task and motion planning in the frame of cloud robotics. A lively discussion will be organized at the end of sessions to foster interaction among participants in order to outline a set of main targets for future international cooperation on the workshop topics.



Challenging robotic problems, like complex manipulation task in cluttered environments or navigation among movable obstacles, require a smart combination of task and motion planning (TAMP) capabilities. Different approaches work in this direction, usually focused on specific problems and scenarios, although efforts are being done to achieve more general, scalable and complete solutions. On the other hand, the use of knowledge in terms of ontologies, as well as the use of cloud computing, provides autonomy and can greatly enhance these planning capabilities. Since great efforts are being done to propose frameworks and standards to represent and use knowledge in both of them, the combination of task and motion planning in the frame of cloud robotics is a good direction towards making robots smarter and more autonomous.

Workshop’s topics can include, but are not limited to, the following:

  • Generality, Scalability and Completeness of TAMP
  • TAMP Challenges
  • TAMP Benchmarking
  • Interaction between Task and Motion Layers
  • Software Services for TAMP
  • Advanced Software Tools for TAMP and Cloud Robotics
  • Knowledge-based Planning for Autonomous Robots
  • Web Services for Autonomous Robots
  • Architectures of Cloud Robotics Systems
  • Cloud Engines for Robotics
  • Human-Robot Interfaces for Cloud Robotics Systems
  • Ontology Standards for Robotics
  • Ontology Frameworks for Robotic Tasks
  • Cloud Computing Techniques for Autonomous Robots

Papers are solicited in all areas of the topics described above. Submission that include experimental results in simulation and/or with real robots are particularly welcome. Papers with descriptions of work in progress or preliminary results are also welcome to be submitted as shorter papers to be presented as posters.
Papers will be reviewed by at least two reviewers. Papers must be submitted to EasyChair: . Papers must be formatted using the standard IEEE style files provided for the IEEE RAS Conferences described in The page limit is 6 pages plus one page for references for full papers, and up to 4 pages for posters.  All accepted papers and posters will be included in a DVD with an ISBN number, distributed to the workshop attendees.


Neil T. Dantam

Performance and Evaluation of Task and Motion Planning

ABSTRACT Task and Motion Planning is being simultaneously investigated across the robotics, planning, and formal methods communities. This variety in perspectives has produced a variety of techniques with different capabilities and performance traits. Identifying the key combinatorial and geometric features that make planning challenging enables us to directly relate different planning approaches. Finally, there is significant potential to improve the performance of task and motion planning by incorporating learning and parallel or cloud computing to construct heuristics, generalizations, and scalable planning systems.

BIO Neil T. Dantam is an Assistant Professor of Computer Science at the Colorado School of Mines.
Neil's research focuses on robot planning and control. He has developed methods to combine discrete and geometric planning, improve Cartesian control, and analyze discrete robot policies. In addition, he has worked on practical aspects of robot manipulation and software design to ensure that new theoretical techniques can be validated in the physical world.
Previously, Neil Dantam was a Postdoctoral Research Associate in Computer Science at Rice University working with Prof. Lydia Kavraki and Prof. Swarat Chaudhuri. Neil received a Ph.D. in Robotics from Georgia Tech, advised by Prof. Mike Stilman, and B.S. degrees in Computer Science and Mechanical Engineering from Purdue University. He has worked at iRobot Research, MIT Lincoln Laboratory, and Raytheon. Neil received the Georgia Tech President's Fellowship, the Georgia Tech/SAIC paper award, an American Control Conference '12 presentation award, and was a Best Paper and Mike Stilman Award finalist at HUMANOIDS '14.

Howard Li

Motion Planning for Autonomous Robotics

ABSTRACT Robots usually are related to situations involving hazardous environments, repetitive and menial tasks. Autonomous robots can be used in many areas, such as surveillance, mine hunting, automatic inspection of power plants and refineries, disposal of hazardous materials and ocean exploration. There is a growing demand and interest in the sensing, perception, motion planning, navigation and control of autonomous robotics. In this talk, we will discuss various aspects of autonomous robotics. Motion planning strategies for autonomous robotics will be presented.

BIO Howard Li (PEng, PhD, IEEE Senior Member, IEEE 1872.2 Standard for Autonomous Robotics Working Group Chair) is a professor in the Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, New Brunswick, Canada. He is a registered professional engineer in the Province of Ontario, Canada. He obtained his Ph.D. from the University of Waterloo, Waterloo, Ontario, Canada. In addition, he received training in Team Based Project Management in the School of Business, Queen’s University, Kingston, Ontario. He has conducted research at the University of New Brunswick, Canada, Ecole Polytechnique Federale de Lausanne, Switzerland, University of Pavia, Italy, University of Waterloo, Canada, and University of Guelph, Canada. Before joining UNB, he was employed by Atlantis Systems International in the development of training systems for the F/A-18 Hornet fighter aircraft for the Boeing company, Canadian Forces, Royal Australian Air Force, and training systems for Royal Danish Air Force. He has developed control software and hardware for unmanned ground vehicles, unmanned aerial vehicles, autonomous underwater vehicles, and mobile robots for Defence Research and Development Canada and Applied AI Systems Inc. for both domestic and military applications. Dr. Li’s research interests are unmanned aerial vehicles, unmanned ground vehicles, autonomous underwater vehicles, motion planning, Simultaneous Localization And Mapping (SLAM), mechatronics, control systems, robotics, multi-agent systems, and artificial intelligence.