|
Maxim A. Batalin |
||||
|
Research |
|||||
|
|
Development of a JavaClient for Player/Stage/Gazebo environments Javaclient allows development of applications for Player/Stage using the elegancy and power of the Java programming language. The client implements all interfaces described in the Player manual, plus several various additions. |
||||
|
|
|||||
|
|
Monitoring Spatiotemporal Phenomena (top) Monitoring of environmental phenomena with embedded networked sensing confronts the challenges of both unpredictable variability in the spatial distribution of phenomena, coupled with demands for a high spatial sampling rate in three dimensions. For example, low distortion mapping of critical solar radiation properties in forest environments may require two-dimensional spatial sampling rates of greater than 10 samples/m^2 over transects exceeding 1000 m^2. Clearly, adequate sampling coverage of such a transect requires an impractically large number of sensing nodes. A new approach, Networked Infomechanical System (NIMS), has been introduced to combine autonomous-articulated and static sensor nodes enabling sufficient spatiotemporal sampling density over large transects to meet a general set of environmental mapping demands. Relevant publications: SenSys04, IROS05, FTDS04 Video: NIMS
|
||||
  |
|||||
|
|
|||||
|
|
|||||
|
Coverage and Exploration (top) We developed and performed theoretical analysis of a novel algorithm termed Least Recently Visited (LRV). LRV efficiently solves the problems of coverage, exploration and sensor network deployment and repair at the same time. The basic premise behind the algorithm is that the robot carries network nodes as a payload, and in the process of moving around, emplaces the nodes into the environment based on certain local criteria. In turn, the nodes emit navigation directions for the robot as it goes by. Nodes recommend directions least recently visited by the robot, hence the name LRV. We formally established the following two properties: 1. LRV is complete on graphs, and 2. LRV is optimal on trees. We also established some experimental conjectures for LRV on regular square lattice graphs and compared its performance empirically to other graph exploration algorithms. Relevant publications: TS03, ICRA05, ICRA03 Animations: traditional coverage, LRV |
||||
|
|
|||||
 |
Sensor Network Deployment, Maintenance and Repair (top) Algorithms that we have developed to assist Mobile Robots in coverage and exploration, navigation and task allocation can/are also used for sensor network deployment, maintenance and repair. For example, LRV allows the robot to cover and explore the environment, while deploying the sensor network. If a part of the network requires redeployment or maintenance, LRV implicitly allows to address this problem. Using algorithms like DINTA, on the other hand, allows sensor network to explicitly perform maintenance and repair. |
||||
|
|
|||||
|
Mobile
Robot Navigation
(top)
We designed an algorithm for robot navigation using a sensor network embedded in the environment (by LRV, for example). Sensor nodes act as signposts for the robot to follow, thus obviating the need for a map or localization on the part of the robot. Navigation directions are computed within the network (not on the robot) using value iteration. Using small low-power radios, the robot communicates with nodes in the network locally, and makes navigation decisions based on which node it is near. An algorithm based on processing of radio signal strength data was developed so the robot could successfully decide which node neighborhood it belonged to. Extensive experiments with a robot and a sensor network confirm the validity of the approach. The robot was able to successfully navigate for over 1km during experimental trials. Relevant publications: TS03, ICRA04_NAV Videos: all videos refer to the map of the environment (Intel Research, Hillsboro, Oregon), with 9 predeployed sensor nodes. Every node knows it's immediate neighbors. Robot does not have a map of the environment, GPS, IMU or compass. Robot does not perform neither localization nor mapping. Environment is not static (people walking, office equipment (chairs, trash cans, etc) is constantly moved, etc.): |
||||
| Robot navigating node 9 to 5 | Robot navigating node 5 to 1 | ||||
|
|
|||||
 |
Multi-Robot
Task Allocation
(top)
We developed DINTA, Distributed In-network Task Allocation - a novel paradigm for multi-robot task allocation (MRTA) where tasks are allocated implicitly to robots by a pre-deployed, static sensor network. Experimental results with a simulated alarm scenario show that our approach is able to compute solutions to the MRTA problem in a distributed fashion. We also developed DINTA-MF, an improved version of DINTA, which allows explicit assignment of robots to tasks. DINTA-MF is based on greedy algorithms and hence provides the best possible solution to an online task allocation problem, which we consider. |
||||
|
|
|||||
