Adaptive Autonomous Robot Teams for Situational Awareness

Erdinc Altug, Aveek Das, Jongwoo Kim, Jim Keller, Vijay Kumar, Guilherme Pereira, John Spletzer, CJ Taylor

This project is focused on the critical technologies required to realize a network-centric force of heterogeneous platforms that is strategically responsive, lethal, survivable and sustainable, as envisioned by the DoD Future Combat Systems project. The key ideas in our project include:

• A comprehensive model and framework integrating communications, perception, and execution, which allow a small team of robots to behave as a seamless, distributed robot whose task is to provide situational awareness and to facilitate the war fighter’s mission execution.

• The automated acquisition of perceptual information for situational awareness, the integration of perceptual models and information from heterogeneous robots and sensors, and their synthesis into a coherent picture for enhanced situational awareness and presentation to a human user.

• A suite of new reactive group behaviors for a team of air and ground based robots that are communications sensitive, ensuring reliable communications through coordinated motion consistent with the overall mission's objectives.

• A new paradigm and algorithms for team planning mechanisms in support of air and ground operations geared towards maximizing communications capabilities in adverse conditions while on the move.

• A new framework for ad hoc networking in which robots use sensory information and relative position information to adapt network topology to the constraints of the task.

• New, fully integrated mission specification capabilities for parsing the tasks of overall mission objectives and mapping them onto a heterogeneous group of robotic platforms.

The effort will result in the first completely integrated team of UAVs and UGVs, in which the team and the network will adapt to the needs and commands of a remotely located warfighter, while simultaneously providing situational awareness. In addition, our research will constitute the first systematic approach to integrate communication with other system requirements. This project will develop and integrate key technologies (control, communication, perception, and adaptation) to demonstrate new capabilities in network-centric warfare.

In order to realize this vision, we are developing truly intelligent robotic communication and sensory nodes that will be able to:

• Acquire and maintain knowledge of the terrain to maximize communication pathways while maximizing mission effectiveness;
  
• Integrate heterogeneous air-ground assets in support of continuous operations over varying terrain;
  
• Behave adaptively in response to communication variation and alterations in suitably defined quality of service communication metrics;
  
• Learn how to improve their communications performance over time, consistent with terrain, foliage, and mission requirements;
  
• Provide user interaction through mixed initiative task interfaces to preserve and enhance connectivity and throughput at run-time;
  
• Be effectively evaluated via formal models of control, communication and perception; and
  
• Use path-referenced behaviors for recovery and fault-tolerance with respect to maintaining connectivity and robust performance of the network.

Our research goals are to:

• Establish the overall paradigm, a modeling framework, and the software architecture to enable a new vision for network centric warfare
  
• Develop small team communication-sensitive behaviors, which allow robots to perform alongside humans as full team members
  
• Enable the team to learn and adapt to changing terrain conditions that may impact communication network performance and localization information (e.g., GPS, line of sight sensing, etc.)
  
• Develop computationally distributed strategies to provide an unprecedented level of situational awareness. A central theme will be to realize the full potential of combining air and ground assets using a small team of UAVs and UGVs.

The project will culminate with a demonstration of the performance of the integrated team of UAVs, UGV’s, and a human leader in a reconnaissance type mission.