Defining a Navigation Goal for Social Robots to Approach People
Murillo Rehder Batista, Marcos Vinicius Cruz, Guilherme Bittencourt Nunes, Josué J. G. Ramos
- 发表年份
- 2023
- 引用次数
- 1
摘要
The task of a mobile robot receptionist includes knowing how to approach a person to start an interaction on a socially acceptable manner. For this, the robot must know where to position itself to approach the person and plan a trajectory. Although this position is usually right in the front of the person, the presence of other people close to the approaching target, especially if this person is potentially interacting with him, can be seen as inappropriate. Considering there are solid approaches for path planning in literature, this paper describes the elaboration and implementation of a goal definition for a socially acceptable approaching behavior. The goal position is obtained from a virtual cost grid that considers an ideal approaching position, the distance to be traveled, the obstacles and social spaces to infer an adequate approaching position. This paper deals with defining this goal position in an adaptive manner and is compared to a standard movement towards an ideal position. This approach is then applied on a real robot for a proof of concept experiment. Results show that the approach is effective to define approaching goals and hint at potential future enhancements.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002