The rise of robots and robotics has proved to be a benefaction to humankind in different aspects. Robotics evolved from a simple button, has seen massive development over the years. Consequently, it has become an integral part of human life as robots are used for a wide range of applications ranging from indoor uses to interplanetary missions. Recently, the use of social robots, in commercial indoor spaces to offer help or social interaction with people, has been quite popular. As such, taking the increasing use of social robots into consideration, many works have been carried out to develop the robots to make them capable of acting like humans. The notion behind this development is the need for robots to offer services without being asked. Social robots should think more like humans and suggest possible and suitable actions by analyzing the environment where they are. Belief–desire–intention (BDI) is one of the most popular models for developing rational agents based on how humans act based on the information derived from an environment. As such, this work defines a foundation architecture to integrate a BDI framework into a social robot to add “act like a human” feature for proactive behaviors. The work validates the proposed architecture by developing a vision-based proactive action using the PROFETA BDI framework in an indoor social robot, Waldo, operated by the robot operating system (ROS).
Rapid estimates of the risk from potential wildfires are necessary for operational management and mitigation efforts. Computational models can provide risk metrics, but are typically deterministic and may neglect uncertainties inherent in factors driving the fire. Modeling these uncertainties can more accurately predict risks associated with a particular wildfire, but requires a large number of simulations with a corresponding increase in required computational time. Surrogate models provide a means to rapidly estimate the outcome of a particular model based on implicit uncertainties within the model and are very computationally efficient. In this paper, we detail the development of a surrogate model for the growth of a wildfire based on initial meteorological conditions: temperature, relative humidity, and wind speed. Multiple simulated fires under different conditions are used to develop the surrogate model based on the relationship between the area burnt by the fire and each meteorological variable. The results from nine bio-regions in Tasmania show that the surrogate model can closely represent the change in the size of a wildfire over time. The model could be used for a rapid initial estimate of likely fire risk for operational wildfire management.
1 February 2022 in Environmental Modelling & Software