Conference Paper

Chasing an elusive target with a mobile robot

INRIA, Montbonnot
DOI: 10.1109/IROS.2001.977172 Conference: Intelligent Robots and Systems, 2001. Proceedings. 2001 IEEE/RSJ International Conference on, Volume: 3
Source: IEEE Xplore

ABSTRACT This paper describes how a mobile robot (a six-wheeled Koala
equipped with a PAL pan-tilt camera) can chase an elusive target (a
remote controlled toy car) in a unknown and unconstrained environment.
First, the paper demonstrates the efficiency, simplicity, and adequacy
of Bayesian robot programming to quickly develop such applications.
Next, it illustrates that a high information compression ratio may be
obtained by some pertinent sensory-motor decoupling

  • [Show abstract] [Hide abstract]
    ABSTRACT: The objective of this research is to operate a radio-controlled car (RC car) by using Thai voice commands. The research was conducted by sending a user's voice commands to a computer machine, and then the computer converted the voice commands into digital signal. After that, the digital signal was converted into a radio wave commands. Finally, an RC car operated based on the radio wave commands. The experiment was conducted on the RC car with five Thai voice commands, which were: 1) Stop, 2) Forward, 3) Backward, 4) Turn Left, and 5) Turn Right. The experimental precisions are 98.2%, 93.0% and 44.2% in a quiet room, an office room and a noisy room, respectively.
  • [Show abstract] [Hide abstract]
    ABSTRACT: For a ground target tracking system using an unmanned helicopter, an estimator is proposed in this paper to estimate the states of the target in the world coordinate. With the goal to reduce the estimation errors caused by the noises from on-board sensors, the static features in two successive images are first utilized to calculate the image variation induced by the camera movement, which is then fused with the on-board sensors to estimate the states of the dynamic target. Specifically, the KLT feature tracking algorithm is adopted to track the target and the static features respectively between successive images, then the image information, together with the velocities of the helicopter and the camera, is employed to calculate the target's velocity in the image plane due to the motion of the camera. Based on this information, the velocity of the target is finally obtained by the utilization of the mapping between the world coordinate and the image plane. Simulation and experiment results are provided to validate the performance of the presented state estimation method.
  • [Show abstract] [Hide abstract]
    ABSTRACT: To analyze the characteristic of an onboard pan-tilt control system to enable an unmanned aerial vehicle (UAV) to Track a ground target, and to verify the stability of the tracking controller and to test the performance of the controller, an experiment platform for pan-tilt control of a small scale autonomous helicopter is designed and then implemented. The system consists of four components including the model of the helicopter, pan-tilt camera, onboard equipment and ground control center. Moreover, the control software is developed by using C++ based on the Visual Studio environment, where multi-threading technique is adopted to make the modules independent of each other. The system not only reliably reflects the dynamics of a practical pan-tilt control system of a small scale autonomous helicopter, but also provides friendly user interface which brings much convenience to implemented and then tested various control strategies. Finally, all the function modules are tested in the ground and air condition respectively, and the obtained experiment results demonstrates the reliability of the system.