Mobile Robotics and Olfaction Lab

Objective

The focus of our attention is on perception systems for mobile robots. Our goal is to advance the theoretical and practical foundations that allow mobile robots to operate in an unconstrained, dynamic environment. The approaches that we develop address real-world needs and are typically characterized by fusion of different sensor modalities. Where possible, the results of our research work are timely integrated in industrial demonstrators.

Research Focus

Our research is organized along two major strands in the areas of mobile robotics and artificial olfaction.

Mobile Robotics

Our research in Mobile Robotics is aimed at autonomous and safe long-term operation in real world scenarios. Industrial relevance and technology transfer is facilitated through collaborative projects with industrial partners in the area of professional service robots for autonomous transportation ("logistics robots"). In our collaborative projects we develop robotic forklifts in warehouses, robotic wheel loaders on asphalt production sites, underground mining vehicles, service robots in airports and robotic systems to unload containers.
Key projects: AIR, Semantic Robots, SPENCER, RobLog (ended), SAUNA (ended), ALLO (ended), SAVIE (ended), ALL-4-eHAM (ended), MALTA (ended).

Artificial and Mobile Robot Olfaction

Artificial Olfaction is the science of gas sensing with artificial sensor systems. We study in particular open sampling systems where the gas sensors are directly exposed to the environment. Open sampling systems are opposed to common laboratory setups, which use sophisticated sampling systems to keep parameters such as air flow, temperature, humidity and concentration of the chemical compound constant over a prolonged time. For most real-world applications this is not possible. We address the corresponding challenges and aim to further develop systems known as "electronic nose" (e-nose) towards a "mobile nose" (m-nose). By combining artificial olfaction and mobile robotics we study the foundations for Mobile Robot Olfaction. Application domains of interest include gas sensor networks and mobile robots for surveillance of landfill sites, monitoring of air pollution and gas leak detection and localization.
Key projects: SmokeBot, Gasbot (ended), Diadem (ended), Dustbot (ended).

Research Themes

Our research can be described by three partially overlapping research themes.

Rich 3D Perception

In this theme we consider algorithms to create a consistent world model from 3D data augmented with additional information (these additional dimensions can include for example colour, reflectivity, temperature, semantic information, confidence, patterns of motion, social behaviours). In particular, we address fusion of visual and range information, efficient representations, 6DOF scan registration, change detection and loop closing in 3D and rich 3D data. Examples are shown in the slide on the right.

Robot Vision

Work in the Robot Vision theme concerns appearance-based approaches to localization, topological mapping and visual SLAM. The basic modalities investigated are perspective and omni-directional cameras and 3D laser range-finders. Examples are shown in the slide on the right.

Mobile Robot Olfaction

This theme is concerned with different aspects of airborne chemical sensing with mobile robots and sensor networks in unconstrained environments. In particular, we address gas discrimination and quantification with open sampling systems, statistical gas distribution modelling and gas source localization.

Applications

Inspection Robots and Sensor Networks

We study gas-sensitive robots as dedicated inspection robots for e.g. support of disaster response or as mobile nodes in sensor networks for surveillance and monitoring. Our contributions relate to all research schemes mentioned above, mainly gas discrimination and quantification with open sampling systems, distribution modelling, gas source localization, sensor planning as well as work on general perception for inspection robots (fusion with vision, 3D and thermal sensing). Examples are shown in the slide on the right.

Professional Service Robots for Autonomous Transportation

The integration of robotic solutions into industrial vehicles depends on the ability to achieve safe autonomous operation in dynamic, shared environments. Related to this central goal, we collaborate with numerous industrial partners and strive to integrate our research work timely in industrial demonstrators. Our relevant research addresses localization, navigation, material handling (mobile manipulation), task and motion planning, obstacle avoidance and human-robot interaction in semi-structured, dynamic environments. Examples are shown in the slide on the right.

People

The Mobile Robotics and Olfaction Lab is one of two research groups within the Centre of Applied Autonomous Sensor Systems (AASS). We are currently 27 highly motivated researchers (15 Ph.D. students, 12 senior researchers) from 15 different countries. Further details can be found under the item "People" in the menu on the left side of this page.

Industrial Partners

National: Atlas Copco, Fotonic, Kollmorgen Automation AB, Linde Material Handling, NCC, Volvo CE and Volvo Trucks.

International: Berthold Vollers GmbH (Germany), Qubiqa A/S (Denmark), BlueBotics Inc. (Switzerland), KLM Royal Dutch Airlines (The Netherlands), and Clearpath Robotics.

Key Collaborative Projects

We are currently working in four collaborative projects (ordered by starting date):

• AIR - Action and Intention Recognition in Human Interaction with Autonomous Systems:
  Apr 1, 2015 - Mar 31, 2019; funded by KKS (SIDUS).
• SmokeBot - Mobile Robots with Novel Environmental Sensors for Inspection of Disaster Sites with Low Visibility:
  Jan 1, 2015 - Jun 30, 2018; funded by the European Comission (EU H2020 RIA).
• Semantic Robots:
  Oct 1, 2014 - Sep 30, 2020; funded by KKS (Profile).
• SPENCER - Social Situation-aware Perception and Action for Cognitive Robots:
  Apr 1, 2013 - Mar 31, 2016; funded by the European Comission (EU 7FP IP).
• SAVIE - Safe Autonomous Vehicles for Industrial Environments:
  Mar 1, 2011 - Feb 28, 2014; funded by KKS and Robotdalen.
• RobLog - Cognitive Robot for Automation of Logistic Processes:
  Feb 1, 2011 - Jan 31, 2015; funded by the European Comission (EU 7FP IP).
• SAUNA - Leading Edge Research in Safe Autonomous Navigation:
  Jan 1, 2011 - Dec 31, 2013; funded by KKS.
• Gasbot - Monitoring of Landfill Sites with a Gas-Sensitive Mobile Robot:
  Jan 1, 2011 - Dec 31, 2013; funded by Robotdalen.
• ALL-4-eHAM - Autonomous Wheel Loaders For Efficient Handling of Heterogeneous Materials:
  Apr 1, 2009 - Mar 31, 2012; funded by KKS, Vinnova and Robotdalen.
• HANDLE - Developmental Pathway Towards Autonomy and Dexterity in Robot In-Hand Manipulation:
  Feb 1, 2009 - Jan 31, 2013; funded by the European Comission (EU 7FP IP).
• Diadem - Distributed Information Acquisition and Decision-Making for Environmental Management:
  Sep 1, 2008 - May 31, 2011; funded by the European Comission (EU 7FP STREP).
• MALTA - Multiple Autonomous Forklifts for Loading and Transportation Applications:
  Jan 1, 2008 - Dec 31, 2010; funded by KKS and Robotdalen.
• Dustbot - Networked and Cooperating Robots for Urban Hygiene:
  Dec 1, 2006 - Jan 30, 2010; funded by the funded by the European Comission (EU 6FP STREP).

Good Use Declaration

Regarding the intended applications that we target, we feel indebted to the Uppsala Code of Ethics for Scientists. Our aim is ultimately to free humans from dull and dangerous tasks (as phrased by Norbert Wiener: "the human use of human beings") and to understand perceptual, biological and physical processes through the help of robots. We are aware that our results may have also other, less beneficial, applications and therefore declare that it is strictly prohibited to use or to develop, in a direct or indirect way, any of our scientific contributions by any army or armed group in the world, for military purposes and for any other use which is against human rights or the environment.

Lab Leader

Achim J. Lilienthal