UAV Capability Management using Agent Supervisory Control

The key to mission performance is the capability of a UAV operator to command and monitor automation as well as his ability to coordinate its actions towards achieving the current task. In order to reproduce such capabilities onboard an unmanned aircraft to a certain extent, we present an approach to introduce an Artificial Cognitive Unit (ACU), acting as an onboard agent supervisor. The ACU commands and controls all onboard automation and acts as a single mission management system subordinate to the human supervisor. For this purpose the term “Agent Supervisory Control” is introduced. In this context onboard automation represents UAV capabilities that can be deployed by the agent supervisor to achieve tasks issued by the operator. These capabilities are managed by the ACU according to their availability, to task and to system constraints. The implementation of the cognitive agent and its automation components, integrated into a UAV system architecture is described. The system has been tested in real-flight experiments and results on in-mission planning and decision making are presented.

[1]  Axel Schulte,et al.  Intent-Based UAV Mission Management Using an Adaptive Mixed-Initiative Operator Assistant System , 2013 .

[2]  Charles E. Billings,et al.  Aviation Automation: The Search for A Human-centered Approach , 1996 .

[3]  Peter Stütz,et al.  Airborne sensor and perception management: Experiments and Results for surveillance UAS , 2013 .

[4]  Qidan Zhu,et al.  Robot Path Planning Based on Artificial Potential Field Approach with Simulated Annealing , 2006, Sixth International Conference on Intelligent Systems Design and Applications.

[5]  Christopher D. Wickens,et al.  A model for types and levels of human interaction with automation , 2000, IEEE Trans. Syst. Man Cybern. Part A.

[6]  Sebastian Clauss,et al.  Design and Evaluation of a UAS combining Cognitive Automation and Optimal Control , 2012, Infotech@Aerospace.

[7]  Mark A. Neerincx,et al.  Modelling Cognitive and Affective Load for the Design of Human-Machine Collaboration , 2007, HCI.

[8]  A. Schulte,et al.  Cognitive UAV resource management allowing task-based mission execution under data link limitations , 2012, 2012 IEEE/AIAA 31st Digital Avionics Systems Conference (DASC).

[9]  Axel Schulte,et al.  UAV Autonomy Research - Challenges and Advantages of a Fully Distributed System Architecture , 2012 .

[10]  Axel Schulte,et al.  Task-based Guidance of Multiple UAV Using Cognitive Automation , 2011 .

[11]  Raja Parasuraman,et al.  Human-Automation Interaction , 2005 .

[12]  Axel Schulte,et al.  System-Ergonomic Design of Cognitive Automation: Dual-Mode Cognitive Design of Vehicle Guidance and Control Work Systems , 2010, Studies in Computational Intelligence.

[13]  Axel Schulte,et al.  The Electronic Camera Gimbal , 2013 .

[14]  Ariel Felner,et al.  Theta*: Any-Angle Path Planning on Grids , 2007, AAAI.

[15]  Axel Schulte,et al.  Design considerations for COSA2 , 2011, 2011 IEEE Symposium on Intelligent Agent (IA).

[16]  Peter A. Hancock,et al.  Human-Centered Design of Unmanned Aerial Vehicles , 2003 .

[17]  Axel Schulte,et al.  Knowledge Configured Vehicle - A layered artificial cognition based approach to decoupling high-level UAV mission tasking from vehicle implementation properties , 2011 .