Situational Reasoning for Road Driving in an Urban Environment

Robot navigation in urban environments requires situational reasoning. Given the complexity of the environment and the behavior specified by traffic rules, it is necessary to recognize the current situation to impose the correct traffic rules. In an attempt to manage the complexity of the situational reasoning subsystem, this paper describes a finite state machine model to govern the situational reasoning process. The logic state machine and its interaction with the planning system are discussed. The approach was implemented on Alice, Team Caltech’s entry into the 2007 DARPA Urban Challenge. Results from the qualifying rounds are discussed. The approach is validated and the shortcomings of the implementation are identified.