POMDPs for Robotic Arm Search and Reach to Known Objects
This addresses the challenge of object search and reach for robotic arms in applications like offices, though it appears incremental as it applies existing POMDP methods to a specific domain.
The paper tackles the problem of robotic arms searching for and reaching known objects under uncertainty by using POMDPs to plan optimized search processes, aiming to approach optimality for this task.
We propose an approach based on probabilistic models, in particular POMDPs, to plan optimized search processes of known objects by intelligent eye in hand robotic arms. Searching and reaching for a known object (a pen, a book, or a hammer) in one's office is an operation that humans perform frequently in their daily activities. There is no reason why intelligent robotic arms would not encounter this problem frequently in the various applications in which they are expected to serve. The problem suffers from uncertainties coming both from the lack of information about the position of the object, from noisy sensors, imperfect models of the target object, of imperfect models of the environment, and from approximations in computations. The use of probabilistic models helps us to mitigate at least a few of these challenges, approaching optimality for this important task.