[robocup-worldwide] [CFP] Last CFP for ICRA 18 Third Workshop on Machine Learning in Planning and Control of Robot Mot&ion (MLPC) (deadline extended)

Tsz-Chiu Au chiu at unist.ac.kr
Wed Mar 21 00:58:58 EDT 2018


FINAL CALL FOR PAPERS (Deadline extended)


Third Machine Learning in Planning and Control of Robot Motion Workshop at

IEEE International Conference on Robotics and Automation (ICRA) 2018

Monday, 21-May-2018

Brisbane, Australia

http://www.cs.unm.edu/amprg/Workshops/MLPC18/index.html



New paper submission deadline: *** March 25, 2018 ***



=====================================================================

ABSTRACT:

Modern robots are expected to perform complex tasks in changing environments. Nonlinear dynamic, model uncertainty, and high-dimensional configuration spaces make planning and executing the motions required for these tasks is difficult. Recent success has been made through the integration of planning and control methods with tools from machine learning.  For example, clustering, reinforcement learning, and intelligent heuristics have adaptively solved planning problems in complex spaces, have automatically identified appropriate trajectories for robots with complex dynamics, and have reduced the amount of time required for planning motions.

After the success of the First Workshop (http://www.cs.unm.edu/amprg/mlpc14Workshop) and Second Workshop (http://kormushev.com/MLPC-2015) in Machine Learning in the Planning and Control of Robot Motion at IROS 2014 in Chicago and IROS 2015 in Hamburg, it is the goal of this workshop to continue to explore methods and advancements afforded by the integration of machine learning for the planning and control of robot motion. The objectives of this workshop are to:

- Develop a community of researchers working on machine learning methods in complementary fields of motion planning and controls
- Discuss current state of the art and future directions of intelligent motion planning and controls
- Provide for collaboration opportunities


MOTIVATION AND OBJECTIVES:

To meet the objectives, the workshop will:

- Include high-quality keynote talks by the leaders of the fields.
- Solicit extended abstracts and short papers (2-4 pages) contributions of the state of the art, and preliminary research results. We aim at accepting approximately 12 short papers and several extended abstracts.
- Organize the workshop with ample time for informal meeting and networking, including group lunch and dinner.
- Conclude the day with an interactive panel discussion and dialogue between the invited speakers, contributed authors, and audience on the next challenges in the field on machine learning for motion planning and control.


LIST OF TOPICS (included, but not limited to):

Because machine learning methods are often heuristic, issues such as safety and performance are critical.  Also, learning-based questions such as problem learnability, knowledge transfer among robots, knowledge generalization, long-term autonomy, task formulation, demonstration, role of simulation, and methods for feature selection define problem solvability. The topics include:

- Task representation and classification
- Planning for complex and high dimensional environments
- Smart sampling techniques for motion planning
- Learning feature selection
- Methods for incorporating learning into planning
- Reinforcement learning for robotics and dynamical systems
- Transfer of learning and motion plans, knowledge and experience sharing among the agents
- Policy selection: exploration versus exploitation, methods for safe exploration
- Methods for creating motion plans that meet dynamical constraints
- Task planning and learning under uncertainty and disturbance
- Motion planning for system stability
- Adaptable heuristics for efficient motion plans
- Motion generalization - methods that learn subset of motion and produce plans with higher range of motions
- Motion planning for multi-agent systems and fleets


INTENDED AUDIENCE:

- Motion planners with interests in learning and planning for changing agents, environment, or both
- Reinforcement learning and machine learning communities that develop novel learning methods for autonomous agents
- Multi-agent researchers
- Controls community focused on controlling physical systems
- Robotics community


=====================================================================

SOCIAL MEDIA:

Like us on Facebook: https://www.facebook.com/mlpcworkshop
Follow us on Twitter: https://twitter.com/MLPC18
Please feel free to contact the workshop committee at mlpc18\AT\googlegroups.com

=====================================================================

ORGANIZERS:

Aleksandra Faust, Google Brain, faust\AT\google.com
Tsz-Chiu Au, Ulsan National Institute of Science and Technology, chiu\AT\unist.ac.kr	
Hao-Tien (Lewis) Chiang, University of New Mexico, lewispro\AT\unm.edu
James Davidson, Google Brain, jcdavidson\AT\google.com
Hanna Kurniawati, University of Queensland, hannakur\AT\uq.edu.au
Lydia Tapia, University of New Mexico, tapia\AT\cs.unm.edu




More information about the robocup-worldwide mailing list