Autonomous Reconfiguration of a Multi-Modal Mobile Robot

This paper presents an approach for a reconfigurable multi-modal mobile robot operating in an indoor environment, based on a probabilistic framework. The modalities are composed of a path planning method, a reactive motion strategy, and an emergency stop. While the mobile robot is achieving its mission to reach its goal, a Hidden Markov Model is used to estimate the most appropriate mode on-line, based on two types of information: context (using mainly information known a priori) and monitoring (evaluating aspects of the current situation that cannot be known in advance). The robot uses the modality that is considered as the most appropriate, switching between one and another as appropriate. We show in experiments that this approach can enable failure mitigation, while maintaining safety and robustness.