Time-Optimized Contextual Information Flow on Unmanned Vehicles

Abstract

Nowadays, the domain of robotics experiences a significant growth. We focus on Unmanned Vehicles intended for the air, sea and ground (UxV). Such devices are typically equipped with numerous sensors that detect contextual parameters from the broader environment, e.g., obstacles, temperature. Sensors report their findings (telemetry) to other systems, e.g., back-end systems, that further process the captured information while the UxV receives control inputs, such as navigation commands from other systems, e.g., commanding stations. We investigate a framework that monitors network condition parameters including signal strength and prioritizes the transmission of control messages and telemetry. This framework relies on the Theory of Optimal Stopping to assess in realtime the trade-off between the delivery of the messages and the network quality statistics and optimally schedules critical information delivery to back-end systems.

To Transmit or Not to Transmit

“…However, the mobile devices are moving based on a grid at the floor to predefined paths. In [25], researchers apply Optimal Stopping Theory based on Change Detection only in-network statistics. This method is only applied to pause the generation of telemetry messages.…”

“…We performed 100 runs of 10 mins duration each, where each run involves sampling for more than N = 100 observations for every sensor integrated on UGV. The comparative assessment is based on four different policies of decision making: (i) the no-policy model, (ii) the heuristic threshold-based model, in which the transmission of messages is paused when QNI falls below a threshold, (iii) TOCP model based on [25], which applies a change detection policy triggering the 'pause' mode operation (the passive mode lasts for Th and then it is activated again) and (iv) the hybrid TOCP-DRP model applied on both UGV and GCS. The performance metrics are QNI measured, Packet Error Rate (PER), based on packets sent and packets lost, and the end-to-end message latency.…”

Multi-layer IoT resource management

“…Η διαχείριση των διαλόγων τηλεμετρίας και ελέγχου σχεδιάστηκε σύμφωνα με τις αρχές βέλτιστης παύσης (Optimal Stopping Theory -OST) ως πρόβλημα άπειρου ορίζοντα (infinite horizon). O προτεινόμενος μηχανισμός αυτός δημοσιεύτηκε στο συνέδριο ΙΕΕΕ WiMob 2018 [44] . Πρόσθετα, το σύστημα λήψης αποφάσεων ενισχύθηκε με ένα μηχανισμό αυτόματης ενεργοποίησης της μετάδοσης των μηνυμάτων παρακολουθώντας την ποιότητα του δικτύου.…”

“…We performed 100 runs of 10 mins duration each, where each run involves sampling for more than N = 100 observations for every sensor integrated on UGV. The comparative assessment is based on four different policies of decision making: (i) the no-policy model, (ii) the heuristic threshold-based model, in which the transmission of messages is paused when QNI falls below a threshold, (iii) TOCP model based on [44], which applies a change detection policy triggering the 'pause' mode operation (the passive mode lasts for T h and then it is activated again) and (iv) the hybrid TOCP-DRP model applied on both UGV and GCS. The performance metrics are QNI measured, Packet Error Rate (PER), based on packets sent and packets lost, and the end-to-end message latency.…”

“…Figure 4.11 plots the QNI performance of the four policies. We can observe that in mission M1, two areas of poor connectivity exist in time-steps [35][36][37][38][39][40][41][42][43][44][45] and [75][76][77][78][79][80][81][82][83][84][85][86][87][88][89][90]. The no-policy, the threshold-based policy and TOCP policy reach QNI values less than 50%, while our TOCP-DRP policy has a mean value close to 68%.…”