Affiliation:
1. Department of Mechano-Informatics, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan
Abstract
Robots of the future will act in the real world. To realize robots with the common sense to do this will, it is generally believed, require massively parallel processing. This is a problem for those of us who want to do experiments with robots in the real world today—it is hard to build active, limber, situated robots when they have to carry along heavy brains. Our answer is “remote-brained robots.” A remote-brained robot is designed to have the brain and body separate, both conceptually and physically. It allows us to tie artificial intelligence (AI) with massive parallelism directly to the real world, enabling the verification of high-level AI techniques, which could previously only be used in simulation. Once the brain is placed remotely from the body, it encourages us to investigate many important research topics of embodied agents working in the real world. This paper describes such platform for future robotics and principal experiments done on the platform.
Subject
Applied Mathematics,Artificial Intelligence,Electrical and Electronic Engineering,Mechanical Engineering,Modelling and Simulation,Software
Reference4 articles.
1. Koike, H., and Tanaka, H. 1989. Parallel inference engine pie64 . bit: Parallel Computer Architecture 21(4).
2. Matsui, T., and Inaba, M. 1990. EusLisp: An object-based implementation of Lisp . Journal of Information Processing 13(3): 327–338 .
3. Sugano, S., Tanaka, Y., Ohoka, T., and Kato, I. 1985. Autonomic limb control of the information processing robot . Journal of Robotics Society of Japan 3(4): 81–95 .
4. Vision and navigation for the Carnegie-Mellon Navlab
Cited by
37 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献