Diagnosis architecture reconfiguration for a networked mobile robot

Insaf Sassi (1) , Alexia Gouin (1) , Jean-Marc Thiriet (1)

1 GIPSA-SAIGA - GIPSA - Signal et Automatique pour la surveillance, le diagnostic et la biomécanique

Wireless networked robots are mobile systems communicating to a control station via a wireless network. These robots move in a distributed infrastructure while receiving orders from control stations to reach their target. A distributed and collaborative diagnosis architecture is a good solution to monitor and diagnose the different components behavior of such distributed system due to the unreliability of wireless networks. Modular Bayesian Network (MBN), as a distributed Bayesian Network, can manage causal uncertain factors (stochastic failures dependencies) and infer information coming from different environments and from devices having memory and calculation limitations. MBN was proposed in our previous work for distributed and collaborative diagnosis. However, the robots can receive orders to switch to autonomous operating mode or to a good performing network (a new control station) to avoid system performance degradation. The robot is no more connected to the station of origin. The diagnosis strategy must consequently be updated. This paper proposes a procedure to reconfigure the diagnosis architecture and the MBN when the mobile robot changes its operating mode i.e, switching from embedded controller to distant controller.

Domaines: Sciences de l'ingénieur [physics]

Insaf Sassi, Alexia Gouin, Jean-Marc Thiriet. Diagnosis architecture reconfiguration for a networked mobile robot. ESREL 2017 - 27th European Safety and Reliability Conference, Jun 2017, Portorož, Slovenia. ⟨10.1201/9781315210469-373⟩. ⟨hal-01558498⟩