A selective attention-based contextual perception approach for a humanoid robot

A humanoid robot is always flooded by sensed information when sensing the environment, and it usually needs significant time to compute and process the sensed information. In this paper, a selective attention-based contextual perception approach was proposed for humanoid robots to sense the environment with high efficiency. First, the connotation of attention window (AW) is extended to make a more general and abstract definition of AW, and its four kinds of operations and state transformations are also discussed. Second, the attention control policies are described, which integrate intensionguided perceptual objects selection and distractor inhibition, and can deal with emergent issues. Distractor inhibition is used to filter unrelated information. Last, attention policies are viewed as the robot’s perceptual modes, which can control and adjust the perception efficiency. The experimental results show that the presented approach can promote the perceptual efficiency significantly, and the perceptual cost can be effectively controlled through adopting different attention policies.

A selective attention-based contextual perception approach for a humanoid robot

A humanoid robot is always flooded by sensed information when sensing the environment, and it usually needs significant time to compute and process the sensed information. In this paper, a selective attention-based contextual perception approach was proposed for humanoid robots to sense the environment with high efficiency. First, the connotation of attention window (AW) is extended to make a more general and abstract definition of AW, and its four kinds of operations and state transformations are also discussed. Second, the attention control policies are described, which integrate intension-guided perceptual objects selection and distractor inhibition, and can deal with emergent issues. Distractor inhibition is used to filter unrelated information. Last, attention policies are viewed as the robot’s perceptual modes, which can control and adjust the perception efficiency. The experimental results show that the presented approach can promote the perceptual efficiency significantly, and the perceptual cost can be effectively controlled through adopting different attention policies. This work was supported by the National Natural Science Foundation of China (No.60375031) and the Nature Science Foundation of Guangdong Province (No.36552). Yanrong JIANG was born in Hunan Province, China, in 1976. He received the B.S. and M.S. degree from South China University of Technology, Guangzhou, in 1999 and 2002 respectively. He is currently a Ph.D. candidate of School of Computer Science and Engineering, South China University of Technology. His research interests include humannoid robot, machine intelligence. Nanfeng XIAO was born in Jiangxi Province, China, in 1962. He received his B.S. degree from Huazhong University of Science and Technology at Automatic Control and Computer Engineering Department in 1982, and M.S. degree from Northeastern University in Department of Automation in 1989. He received the Ph.D degree in Robotics from Yokohama National University, Japan, in 2001. From 2001 to 2002, he was a senior visiting scholar in Deakin University, Australia. He is now a professor and supervisor of Ph.D candidates at School of Computer Science and Engineering, South China University of Technology, China. His research interests include humanoid robot, intelligent control, computer vision, etc.