J. del R. Mill'an and A. Arleo, "Neural network learning of variable grid-based maps for the autonomous navigation of robots," in Proc. IEEE Int. Symposium on Comp. Intelligence in Robotics and Automation, 1997, pp. 40--45. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Efficient Occupancy Grids for Variable Resolution Map Building - Dedieu, Millán (Correct)
....So the latter may use a resolution adapted to its purpose, leaving out fine details to be handled by the reactive controller. Email: feric.dedieu, jose.millang jrc.it The basic concept supporting each aspect of this work is the variable resolution adaptive strategy, built on previous work [Mill an Arleo, 97] Different scales being adequate for different tasks, they should be able to cooperate harmoniously. This paper presents two parts of the whole system we are developing. The first one is a new method for integrating metric information into local occupancy grids that makes them more appropriate ....
....distributed sensory processing. The sensory resources that have been developed so far are: the immediate sensory readings, a local occupancy grid, a local dominant wall orientation, and a local grid of obstacle edges. As a result, this new method makes fewer assumptions than our previous work [Mill an Arleo, 97] and it is considerably faster to process than any previous occupancy grid used for map building. Indeed, it takes just 5 ms to update all four sensory resources on a Sparc Ultra 1 Sun workstation, using non optimised C code. The second part reported is the local map representation used to ....
[Article contains additional citation context not shown here]
J. del R. Mill'an and A. Arleo (1997). Neural network learning of variable grid-based maps for the autonomous navigation of robots. Proc. of the IEEE Int. Symposium on Computational Intelligence in Robotics and Automation, 40--45.
Efficient Learning of Variable-Resolution Cognitive.. - Arleo.. (1999) (2 citations) Self-citation (Del Mill'an Arleo) (Correct)
....the frontal 180 degrees of the robot and two sensors face backward. b) Schematic top view of the robot. line that is sufficiently close and has the same orientation. In order to illustrate the performance of our approach in a more complex environment, we also report results obtained in simulation [23]. The Nomad 200 simulator models the robot s motion system (i.e. translation, steering, and turret rotation) and the robot s sensor system (i.e. tactile, infrared, and sonar) adequately. Uncertainty of the motion control is modeled by keeping track of two positions of the simulated robot, ....
J. del R. Mill'an and A. Arleo, "Neural network learning of variable grid-based maps for the autonomous navigation of robots," in Proc. IEEE Int. Symposium on Comp. Intelligence in Robotics and Automation, 1997, pp. 40--45.
Efficient Learning of Variable-Resolution Cognitive Maps.. - Arleo, Millán, Floreano (1999) (2 citations) Self-citation (Del Mill'an Arleo) (Correct)
....many differences between the two robots, especially their sensor capabilities and sensor configurations, made it interesting to test our method on both of them. 3. 1 Experiments with the Nomad 200 We have tested our approach with TESEO (the physical Nomad 200 robot) and with a simulated version [8]. This section reports experimental results obtained in simulation. Figure 10 shows the environment used for carrying out the experiments. It simulates a real environment of about 14:5 10:5 meters. For the neural sensor interpretation, we use a local grid G of 28 28 cells, each covering an area ....
J. del R. Mill'an and A. Arleo. Neural network learning of variable grid-based maps for the autonomous navigation of robots. In Proceedings of the IEEE Int. Symposium on Computational Intelligence in Robotics and Automation, pages 40--45, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC