(Georgia Institute of Technology, 2013-05)
Levihn, Martin; Scholz, Jonathan; Stilman, Mike
In this paper we present a decision theoretic
planner for the problem of Navigation Among Movable Obstacles (NAMO) operating under conditions faced by real
robotic systems. While planners for the NAMO domain exist,
they typically assume a deterministic environment or rely on
discretization of the configuration and action spaces, preventing
their use in practice. In contrast, we propose a planner that
operates in real-world conditions such as uncertainty about the
parameters of workspace objects and continuous configuration
and action (control) spaces.
To achieve robust NAMO planning despite these conditions,
we introduce a novel integration of Monte Carlo simulation
with an abstract MDP construction. We present theoretical and
empirical arguments for time complexity linear in the number
of obstacles as well as a detailed implementation and examples
from a dynamic simulation environment.
(Georgia Institute of Technology, 2012-06)
Levihn, Martin; Scholz, Jonathan; Stilman, Mike
In this paper we present the first decision theoretic planner for the problem
of Navigation Among Movable Obstacles (NAMO). While efficient planners
for NAMO exist, they are challenging to implement in practice due to the inherent
uncertainty in both perception and control of real robots. Generalizing existing
NAMO planners to nondeterministic domains is particularly difficult due to the sensitivity
of MDP methods to task dimensionality. Our work addresses this challenge
by combining ideas from Hierarchical Reinforcement Learning with Monte Carlo
Tree Search, and results in an algorithm that can be used for fast online planning
in uncertain environments. We evaluate our algorithm in simulation, and provide
a theoretical argument for our results which suggest linear time complexity in the
number of obstacles for typical environments.
(Georgia Institute of Technology, 2010-12)
Scholz, Jonathan; Stilman, Mike
Robots that operate in natural human environments
must be capable of handling uncertain dynamics and
underspecified goals. Current solutions for robot motion planning
are split between graph-search methods, such as RRT
and PRM which offer solutions to high-dimensional problems,
and Reinforcement Learning methods, which relieve the need to
specify explicit goals and action dynamics. This paper addresses
the gap between these methods by presenting a task-space
probabilistic planner which solves general manipulation tasks
posed as optimization criteria. Our approach is validated in
simulation and on a 7-DOF robot arm that executes several
tabletop manipulation tasks. First, this paper formalizes the
problem of planning in underspecified domains. It then describes
the algorithms necessary for applying this approach to
planar manipulation tasks. Finally it validates the algorithms
on a series of sample tasks that have distinct objectives, multiple
objects with different shapes/dynamics, and even obstacles that
interfere with object motion.