ROBTK: An intelligent robot to transport objects

• Wallyson O. das Mecês IFPA
• Edson M. da Costa UFRA
• Jailton W. Tavares IFPA
• Patrícia P. Diniz IFPA
• Renato H. Torres IFṔA

DOI: https://doi.org/10.5753/encompif.2019.6344

Resumo

Studies show that every year the number of accidents and medical care expenses increase due to the work accident. In the context of transporting objects, many activities are still carried out by human labor which in many cases may be subject to disasters due to the high number of hours worked or due to unhealthy activities. Taking into account the presented scenario, this work aims to introduce the robot ROBTK an intelligent robot to transport objects. We developed robot intelligence building a convolutional neural network (CNN) to perform object classification. The tests performed showed that both the intelli- gence and the mechanics designed are efficient.

Referências

Correll, N., Bekris, K. E., Berenson, D., Brock, O., Causo, A., and and, K. H. (2018).

Analysis and observations from the first amazon picking challenge. IEEE Transactions on Automation Science and Engineering, 15:172–188. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. http: //www.deeplearningbook.org.

Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., and Chen, T. (2018). Recent advances in convolutional neural networks. Pattern Recognition, 77:354–377.

LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436– 444.

Smartlab (2016). Observat´orio nacional de seguranc¸a do trabalho. https:// observatoriosst.mpt.mp.br.