[robotics-worldwide] [journals] Autonomous Robots - Special Issue on "Constrained decision making in robotics: models, algorithms, and applications"
scarpin at ucmerced.edu
Wed Jul 2 17:38:16 PDT 2014
The Autonomous Robots journal invites papers for a special issue
on “Constrained decision-making in robotics: models, algorithms,
As the complexity of robotic tasks grows, robotic decision makers
increasingly face the problem of trading off different objectives (for
example, safety versus speed, or, in a reinforcement learning framework,
balancing exploration versus exploitation for fast convergence). A natural
framework for this class of problems is constrained decision-making,
whereby a decision maker seeks to optimize a given cost function (often
stochastic) while keeping other costs (usually involving risk assessments)
below given bounds. Aspects of this framework have been addressed in
isolation by the operations research and finance communities (for example,
algorithms for constrained Markov decision processes and modeling of
risk preferences), but the application of such a framework to the robotics
domain is relatively new, fueled by application as diverse as safe
autonomous driving, collision avoidance for unmanned aerial vehicles,
and risk-aware learning for autonomous robots.
Accordingly, this special issue aims at presenting the state of the art on
the fast growing field of constrained decision-making in robotics.
Specifically, it focuses on models, algorithms, and applications to solve
constrained decision and planning problems for single and multiple
robot systems. We invite submissions of original research papers addressing
constrained decision making problems with an emphasis on theories and
frameworks validated on robotic systems operating in the physical world.
Topics of interest include, but are not limited to:
- Modeling of constraints (in particular, risk) for robotic applications;
- Algorithms for risk-aware decision making and learning for robotic systems, with a
focus on online computation;
- Chance-constrained robotic motion planning;
- Hierarchical constrained decision making;
- Applications of Constrained MDPs and Constrained POMDPs to robot planning;
- Applications: ground, underwater, aerial, and space robots;
- Benchmarks and performance metrics for constrained decision-making problems;
- Verification and validation techniques for constrained decision-making problems.
Stefano Carpin, University of California, Merced
Marco Pavone, Stanford University
October 15, 2014: Submission deadline
January 15, 2015: First reviews completed
February 15, 2015: Revised papers due
March 30, 2015: Final decision
Manuscript must be submitted to http://AURO.edmgr.com.
Stefano Carpin, PhD
School of Engineering
University of California, Merced
More information about the robotics-worldwide