Author name cluster

DeWitt Latimer IV

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

ICRA Conference 2004 Conference Paper

Sensor Space Planning with Applications to Construction Environments

Edward Latimer
DeWitt Latimer IV
Rajiv Saxena
Catherine Lyons
L. Michaux-Smith
Scott Thayer

Outlined is a new approach to sensor space planning and its application to the construction industry. The software planning tool described here generates sensor placements automatically for use in assessing deviations in construction environments. The first step is to separate construction information goals into clusters, simplifying the planning space in order to reduce computational complexity. For each cluster, the planner generates the space of potential sensor placements for a set of information goals and selects a minimal set of subspaces to take advantage of views that can achieve multiple goals simultaneously. Sensing locations are chosen that maximize the probability of achieving each goal and a path is generated to minimize the transit cost between the various sensing locations within each cluster. Finally, paths are generated that minimize the transit cost between clusters. This method is demonstrated on a desktop computer and shown to support LIDAR information goal sensor planning within a construction site.

Details

ICRA Conference 2002 Conference Paper

Towards Sensor Based Coverage with Robot Teams

DeWitt Latimer IV
Siddhartha S. Srinivasa
Vincent Lee-Shue
Samuel Sonne
Howie Choset
Aaron P. Hurst

We introduce an algorithm to cover an unknown space with a homogeneous team of circular mobile robots. Our approach is based on a single robot coverage algorithm, a boustrophedon approach, which divides the target two-dimensional space into regions called cells, each of which can be covered with simple back and forth motions. Single robot coverage is then achieved by ensuring that the robot visits each cell. The new multi-robot coverage algorithm uses the same planar cell-based approach as the single robot approach, but also prescribes the methods by which multiple robots cover a cell, teams are allocated among cells, and sub-teams of robots share information in a minimalistic manner. The advantage of this method is that planning occurs in a two dimensional configuration space for a team of n robots, bypassing the need to plan in a 2n dimensional configuration space. The approach is semi-decentralized: robot teams cover the space independent of each other, but robots within a team communicate state and share information.

Details