One of the challenges of task planning is to find out what causes the planning failure and how to handle the failure intelligently. This paper shows how to achieve this. The idea is inspired by the connected graph: each verticle represents a set of compatible \textit{states}, and each edge represents an \textit{action}. For any given initial states and goals, we construct virtual actions to ensure that we always get a plan via task planning. This paper shows how to introduce virtual action to extend action models to make the graph to be connected: i) explicitly defines static predicate (type, permanent properties, etc) or dynamic predicate (state); ii) constructs a full virtual action or a semi-virtual action for each state; iii) finds the cause of the planning failure through a progressive planning approach. The implementation was evaluated in three typical scenarios.

A new breed of robot mimics bats by using sound alone to find its way around. The four-wheeled Robat, developed by Israeli researchers, uses an echo-based sonar system to navigate and map its surroundings. A speaker sends out ultrasonic signals which bounce back off of objects and are picked up by two ultra-sensitive microphones. Experts behind the autonomous technology say it could be used during rescue operations in areas that are too dangerous for humans to reach. The Tel Aviv University team showed that Robat can pick its way through an obstacle course using sonar alone.

New robots can learn old tricks. Bats use sound to navigate their surroundings in the dark and now a robot called Robat can do the same. Robat is a four-wheeled autonomous robot, equipped with a speaker to mimic a bat's mouth, and two microphones, positioned on the left and right, to mimic a bat's ears. As it moves around, Robat's speakers produce a high-frequency chirp every half a metre. It can then identify the position of obstacles by calculating the delay between making this sound and the echo returning, and any differences between the two microphones.