In the near future robotic devices will be integrated in our daily lives. They would have to be equipped with social intelligence so they can move and act in a way that humans consider to be safe, reliable and in compliance with the unwritten rules of acceptable social behaviors linked to a given context. Instead of having stored computer-based models of surrounding environments (deliberative systems), behavior-based robots (BBR) are guided by their users through smart cooperation and interaction. For instance, there is no programming in the robot of what a crop field, cleaning floor or transporting goods looks like, or what kind of surface the robot is moving on, all the information is gleaned from the input of the robot's sensors. The robot uses that information to react to the changes in its environment. Even more, BBR must know when and how to engage a user in guiding it; robots that play with children, assists elderly or approaches people in air-ports for helping them on their way, must watch human movements, interpret what their intentions are and act accordingly. The paper gives an introduction of various BBR and their relation with sensors, presents a technique for representing behaviors and hierarchical behavior-based architectures, as a uniform time scale state representation. Behavior-based controller as a structured network of interacting behaviors for such ro-bots is discussed related to Danish BBR projects. The paper concludes by addressing success criteria for the development of BBR, including aspects to transform social contexts into behavioral control models and to plan a behavioral strategy and make it adaptive. Validation of ideas is made in an experiment with a group of LEGO mobile robots using a range of sensors and negotiating their roles in different environments, which possesses skills and can offer services.
Social Robot; Intelligent Robot; Behavior-Based Robotics; Behavior-Based Control