Mining robotics: Application of computer vision to the automation of a roadheader

Michel Devy (1) , Jean-José Orteu (2) , J.L. Fuentes-Cantillana (3) , J.C. Catalina (3) , A. Rodriguez (3) , D. Dumahu (4) , P. Villeneuve de Janti (5, 4)

1 LAAS-RIS - Équipe Robotique et InteractionS
2 LAAS - Laboratoire d'analyse et d'architecture des systèmes
3 AITEMIN
4 INERIS - Institut National de l'Environnement Industriel et des Risques
5 LPNHE - Laboratoire de Physique Nucléaire et de Hautes Énergies

Automation of mining operations involves the use of sensing, remote monitoring and control systems in order to confront a variety of situations and environmental conditions. The need of profitability of a mine sometimes requires that selective cutting be performed in order to separate rich ore from waste at the cutting stage. Basically, the problems to be solved are those of modelling an uncontrolled, changing mine environment and programming the machine to cut a pattern accordingly. We present in this paper how image segmentation and classification, 3-D scene perception and path planning can cooperate to solve such a complex problem as selective cutting.

Domaines: Automatique / Robotique; Traitement du signal et de l'image [eess.SP]

Michel Devy, Jean-José Orteu, J.L. Fuentes-Cantillana, J.C. Catalina, A. Rodriguez, et al.. Mining robotics: Application of computer vision to the automation of a roadheader. Robotics and Autonomous Systems, 1993, 11 (2), pp.65- 74. ⟨10.1016/0921-8890(93)90010-A⟩. ⟨hal-01716473⟩