The aim of this project is to integrate social behaviors into the RoboComp navigation agent. Mobile robots that encounter people on a regular basis must react to them in some way or the other. Traditional robot control algorithms for path planning and obstacle avoidance treat all sensor readings identically, as foreign objects that must be avoided. However, for a mobile robot that operates around people, these traditional algorithms may not follow the social norms. Even simple conventions like move to the right when a person is encountered might not be honored by these algorithms. However, people would want to, or rather tend to perceive robots-particularly assistive robots, as human like. So catering to this need social behavior will be implemented via certain cost functions.

Organization

Student

Yohan M R

Mentors

  • Pedro Núñez Trujillo
close

2017