Affiliation:
1. MIT Artificial Intelligence Laboratory, 545 Technology Square, Cambridge, MA 02139, USA
Abstract
Most animals have significant behavioral expertise built in without having to explicitly learn it all from scratch. This expertise is a product of evolution of the organism; it can be viewed as a very long-term form of learning which provides a structured system within which individuals might learn more specialized skills or abilities. This paper suggests one possible mechanism for analagous robot evolution by describing a carefully designed series of networks, each one being a strict augmentation of the previous one, which control a six-legged walking machine capable of walking over rough terrain and following a person passively sensed in the infrared spectrum. As the completely decentralized networks are augmented, the robot's performance and behavior repertoire demonstrably improve. The rationale for such demonstrations is that they may provide a hint as to the requirements for automatically building massive networks to carry out complex sensory-motor tasks. The experiments with an actual robot ensure that an essence of reality is maintained and that no critical disabling problems have been ignored.
Subject
Cognitive Neuroscience,Arts and Humanities (miscellaneous)
Cited by
257 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
1. DeepCPG Policies for Robot Locomotion;IEEE Transactions on Cognitive and Developmental Systems;2023-12
2. Examples of Issues with Chatbots Over the Last Few Years;Synthesis Lectures on Engineering, Science, and Technology;2023-11-03
3. Theoretical investigation of an array of Josephson junction neuron circuits actuating a mechanical leg and the array in mimicking a multi-legged locomotion;Pramana;2023-08-29
4. The Detection of Hexapod Robot Based on Arduino Environment;2023 International Conference on Computers, Information Processing and Advanced Education (CIPAE);2023-08-26
5. Transitions in cognitive evolution;Proceedings of the Royal Society B: Biological Sciences;2023-07-05