A decision mechanism, method, module and robot configured to determine at least one future activity of the robot

摘要

The present invention refers to a decision mechanism, configured to decide on at least one prospective action of a robot from set of actions by: computing a prior probabilistic representation of a prior environment state; updating said prior probabilistic representation with targets of a new observation on reducing at least one uncertainty in a posterior probabilistic representation of a posterior environment state to be reached after an appliance of said at least one prospective action, said posterior probabilistic representation resulting from said updating; determining an information gain between said prior probabilistic representation and said posterior probabilistic representation by use of at least one information theoretic measure; evaluating said at least one prospective action by adding costs of executing said at least one prospective action to said information gain. The present invention provides an improved action planning for robots and can be implemented in various robots investigating scenes for their actions.