Monte Carlo localization: efficient position estimation for mobile robots
AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Robust Monte Carlo localization for mobile robots
Artificial Intelligence
Neural virtual sensors for terrain adaptation of walking machines
Journal of Robotic Systems
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Generating continuous free crab gaits for quadruped robots on irregular terrain
IEEE Transactions on Robotics
Accurate tracking of legged robots on natural terrain
Autonomous Robots
Robotics and Autonomous Systems
Hi-index | 0.00 |
Knowledge of a robot's position with an accuracy of within a few centimeters is required for potential applications for legged robots, such as humanitarian de-mining tasks. Individual sensors are unable to provide such accuracy. Thus information from various sources must be used to accomplish the tasks. Following this trend, this paper describes the method developed for estimating the position of legged robots in outdoor environments. The proposed method factors in the specific features of legged robots and combines dead-reckoning estimation with data provided by a Differential Global Positioning System through an extended Kalman filter algorithm. This localization system permits accurate trajectory tracking of legged robots during critical activities such as humanitarian de-mining tasks. Preliminary experiments carried out with the SILO4 system have shown adequate performance using this localization system.