Evolution of Neural Controllers for Robot Navigation in Human Environments | Science Publications

Journal of Computer Science

Genci Capi¹  Hideki Toda¹ 

关键词: Robot navigation;    vision;    neural networks;    evolutionary algorithm;   

DOI  :  10.3844/jcssp.2010.837.843

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: In this study, we presented a novel vision-based learning approach for autonomous robot navigation. Approach: In our method, we converted the captured image in a binary one, which after the partition is used as the input of the neural controller. Results: The neural control system, which maps the visual information to motor commands, is evolved online using real robots. Conclusion/Recommendations: We showed that evolved neural networks performed well in indoor human environments. Furthermore, we compared the performance of neural controllers with an algorithmic vision based control method.

【 授权许可】

Unknown