The National Academy of Sciences is holding a symposium with its annual meeting to discuss robot technology.
According to its web site, "As robot technology advances, we are approaching the day when robots will be deployed prevalently in uncontrolled, unpredictable environments: the proverbial 'real world.' As this happens, it will be essential for these robots to be able to adapt autonomously to their changing environment. This session will present three examples of machine learning on physical robots: Peter Stone of the University of Texas at Austin will present a machine-learning approach to legged locomotion, with all training done on the physical robots; Brian Scassellati of Yale University will present research on humanoid robots that learn to use normal social cues to interact with people; and Ayanna Howard of the Georgia Institute of Technology will present research that focuses on space robotics, in which robust operations must occur in environments that are unknown, unexpected, and uncertain.
For interesting reading about robot technology, go to the BBC's The World and Science Daily.