I'm trying to think, but nothing happens! [robotics]
Brian Carlisle · 2002
Summary form only given as follows. Much of the recent research in robotics has focused on improving the speed and control of robots. Today's robots blindly follow orders that have been prepared in advance. In order to make further progress in the acceptance of robots on the factory floor and in new applications such as surgery or service, robots must be able to sense and reason about their environment. We need to devote research to reasoning about geometry and processes. We need better ways of acquiring models than laborious programming in CAD systems. We need methods to represent errors and plan recoveries. These capabilities will be necessary for the autonomous robots of tomorrow.