2013 Homepage

RSS2013 2nd Workshop on Resource-Efficient Integration of Perception, Control, and Navigation for Micro Air Vehicles (MAVs)

Motivation and Objectives

The wide availability of small and cheap flying platforms (e.g. quadrotors) in combination with advances in embedded systems, high density batteries and lightweight sensors has made small UAS very attractive for a wide range of applications like area surveillance, asset inspection, mapping or search and rescue. The compact size and small weight also make them easier to deploy, both due to their high portability and because obtaining an operational permit is typically easier for such systems.

A disadvantage of using compact, low-power sensors is often their slower speed and lower accuracy making them unsuitable for direct capture and control of high dynamic motion. On the other hand, the inherent instability of some systems (e.g. helicopters or quadrotors), their limited on-board resources and payload, their multi-DOF design and the uncertain and dynamic environment they operate in, present unique challenges both in achieving robust low level control and in implementing higher level functions, like navigation, exploration or object tracking. These challenges can be exacerbated in search and rescue missions where the lack of communications infrastructure and the need for beyond-line-of-sight flying creates the need for operating at a higher degree of autonomy.

The perceptual evaluation of high dynamic motion can be improved through fusion of proprioceptive (e.g. inertial) and exteroceptive (e.g. vision) sensors, through the use of internal environment representations and/or through the coordinated use of multiple platforms. Perception and action need to be strongly coupled to allow long-term stabilization in the face of challenging platform dynamics, external disturbances, sensor uncertainty and on-board failures. The same is true between perception and navigation/planning to achieve both the necessary reactive behaviors (e.g. for obstacle avoidance or for formation keeping), as well as the execution of goal-oriented tasks.

The goal of the workshop is to collect current state-of-the art solutions to the aforementioned issues. Our key interests lie in the latest developments in the area of robust integration of perception with control and planning of the highly dynamic motion of resource-limited flying platforms. We are also interested in new developments in the field of internal environment representation and collaborative approaches in perception and exploration.

After the great success of the last RSS workshop, we aim to bring together again researchers working on aspects of sensor data processing and fusion for robust navigation of flying platforms. The goal is to provide an opportunity to compare and discuss the current state-of-the-art approaches and solutions to the aforementioned problems. We encourage video and live presentations of the approaches during the conference. We aim to organize a panel at the end of the workshop to discuss current challenges in the field and to foster collaborations between the research groups.

Important Dates

  • Extended abstracts due: May 3, 2013
  • Notification of acceptance: May 17, 2013
  • Final submission: May 31, 2013

Workshop Topics

Subjects of interest include, but are not limited to:

  • Robust and accurate perception from limited sensing on light-weight, resource-limited systems (e.g. fusion approaches with an emphasis on error-tolerance and extension of the dynamic range observable)
  • Planning and control approaches for highly dynamic systems to cope with the disadvantages of limited sensing on small platforms
  • Interaction between internal representation and low-/high-level control for scalable action generation under degrading perceptive conditions
  • Integration of perception with action/reaction approaches towards improved performance and safety in small unmanned systems
  • Collaborative multi-system approaches to perception and perception/action solutions for planning and control of unmanned systems with limited sensing.
  • Novel sensor designs and sensing strategies integrated into resource-limited mobile autonomous systems.


Darius Burschka
Sensordata-Fusion and Telerobotics, MVP
Technische Universität München
Michael Suppa
Institute of Robotics and Mechatronics
German Aerospace Center
Roland Siegwart
Autonomous Systems Lab
ETH Zürich
Korbinian Schmid
Institute of Robotics and Mechatronics
German Aerospace Center
Markus Achtelik
Autonomous Systems Lab