Abstract

As robot are starting to emerge in human everyday environments, it becomes necessary to find ways, in which they can interact and engage seamlessly in the human environments. Open-ended human environments, such as pedestrian streets, shopping centres, hospital corridors, airports etc., are places where robots will start to emerge. Hence, being able to plan motion in these dynamic environments is an important skill for future generations of robots. To be accepted in our everyday human environments, the robots must be able to move naturally, and such that it is both safe, natural and comfortable for the humans in the environment. Imagine a service robot driving around in an airport. The objective of the service robot is: to drive around among the people in the environment; identify people who need assistance; approach them in an appropriate way; interact with the person to help with the needs of the person. This could be showing the way to a gate, providing departure information, checking reservations, giving information about local transportation, etc. This chapter describes algorithms that handle the motion and navigation related problems of this scenario. To enable robots with capabilities for safe and natural motion in human environments like in the above described scenario, there are a number of abilities that the robot must possess. First the robot must be able to sense and find the position of the people in the environment. Also, it is necessary to obtain information about orientation and velocity of each person. Then the robot must be able to find out if a person needs assistance, i.e. the robot needs to establish the intentions of the people. Knowing the motion state and the intention state of the person, this can be used to generate motion, which is adapted according to the person and the situation. But in a crowded human environment, it is not only necessary for the robot to be able to move safe and naturally around one person, but also able to navigate through the environment from one place to another. So in brief, the robot must be able to:

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.