IEEE Kingston section in collaboration with Queen’s University Mining Systems Laboratory is pleased to announce a special seminar series by six members of the Centre for Autonomous Sensor Systems(AASS), Örebro University, Sweden from October 8-10 at Queen’s and RMC.
Oct 8, 10:30 AM, Queen’s Goodwin 221B
Dr. Federico Pecora
Closed Loop Control of Multiple Autonomous Vehicles
Abstract: A growing interest in the industrial sector for autonomous ground vehicles has prompted significant investment in fleet management systems. Desirable properties of such systems are the ability to accommodate externally imposed temporal and spatial requirements on-line, and guaranteeing adherence to these reqruiementseven in the presence of contingencies. In this talk I will provide an overview of the results achieved in the Safe Autonomous Navigation Project (SAUNA), a nationally funded Swedish project aimed at tackling the problems above. The key intuition behind the SAUNA approach is to view virtually all aspects of vehicle motion as pruning invalid trajectories from a common representation of the trajectories of the entire fleet. This allows to achieve a tight integration between decision processes at different levels of abstraction, including vehicle coordination and motion planning, as well as execution and control level processes. The talk will include a live demo with simulated forklifts in ROS/Gazebo in collaboration with Henrik Andreasson (AASS, Örebro University).
Biography: Dr. Federico Pecora is a Senior Lecturer at the Center for Applied Autonomous Sensor Systems (AASS) at Örebro University, Sweden. His interests lie at the intersection of Artificial Intelligence and Robotics, with a focus constraint reasoning algorithms, planning, scheduling, meta-CSP techniques for integrated reasoning, distributed constraint reasoning, and planning/scheduling for multi-agent systems. He has primarily applied these techniques in two broad application areas: service robots/sensor systems for use in domestic environments; and decision support tools for industrial scenarios with large autonomous vehicles.
Oct 9, 11:00 AM, RMC Currie Hall
Dr. Todor Stoyanov
Mapping, Localization and Perception for Industrial Robots
Abstract: In this talk I will summarize some of the recent scientific advances at our group in the areas of mapping, localization and perception in industrial environments. In the first part of the talk, I will focus on the Normal Distributions Transform and explain how it has been applied to the domains of scan registration, mapping, localization and navigation. The algorithms discussed in this talk will be put into context of industrial ground vehicles in semi-structured environments. In the second part, I will discuss perception in the context of the RobLog project, which aims at autonomous container unloading.
Biography: Dr. Todor Stoyanov is a postdoctoral researcher at the the Mobile Robotics and Olfaction Lab at AASS, Örebro university, Sweden. He received his PhD from Örebro University (’12) and his Masters (’08) from Jacobs University Bremen, Germany. His main research interests are in perception and safe autonomous navigation for ground mobile robots.
Oct 9, 2:00 PM, RMC Currie Hall
Dr. Henrik Andreasson
Material Handling using Autonomous Forklifts
Abstract: In this presentation, I will talk about our previous and current projects involving transporting goods autonomously in warehouses. The main topics covered are in navigation aspects – mapping / localization in dynamic indoor environments, load handling, existing industrial solutions (AGV’s) and their limitations and sensor requirements for autonomous operation. In addition an active safety system for robust human detection for industrial sites will be presented.
Biography: Dr. Henrik Andreasson holds a lecturer position at AASS, Örebro University, Sweden. His main interest includes, aspects of long term navigation in real-world environments, 3d perception, robot vision, human detection. Henrik Andreasson obtained his Ph. D. from Örebro University in 2008 and his M.Sc. at Royal Institute of Technology, Stockholm, Sweden in 2001.
Oct 10, 9:30 AM, Queen’s Goodwin 221B
Dr. Martin Magnusson
Automated Construction Vehicles for Handling Piled Materials
Abstract: In my talk, I will present recent results from the ALLO project (autonomous long-term load-haul-dump operations). This project is performed in collaboration with Volvo Construction Equipment and is concerned with automating construction vehicles for handling of piled materials—including auto-loading, mapping, navigation and planning in a dynamic environment. I will talk about what we are doing to learn efficient strategies for auto-loading, how we cope with distorted 3D data from a moving platform, and how we aim to use appearance-based localisation in changing environments.
Biography: Dr. Martin Magnusson is a researcher and lecturer working ath the Mobile Robotics and Olfaction Lab at AASS, Örebro university, Sweden. His main research interests are 3D perception with application to localisation and mapping, as well as autonomous loading of piled materials. Martin Magnusson obtained his PhD in computer science from Örebro University in 2009, and his MSc in computer science from Uppsala University in 2004. The PhD thesis presents the 3D normal-distributions transform and shows how it can be used for registration and loop-closure detection.
Oct 10, 1:30 PM, Queen’s Goodwin 221B
Dr. Achim Lilienthal
Mobile Robot Olfaction
Abstract: In this presentation, I will start with an overview of the field of Mobile Robot Olfaction (MRO), which is concerned with gas-sensitive mobile robots. The potential of “gasbots” arises from the combination of gas sensors with their mobility, on-board intelligence and other sensing modalities. I will introduce the components of Mobile Robot Olfaction systems, name the key challenges in the field and highlight major contributions. Then I will describe ongoing work and argue that, after 20 years of research, MRO has reached a cross-roads where basic research is necessary to advance the field to scientifically firm ground and thus enable a new generation ofgasbots.
Biography: Prof. Achim Lilienthal is head of the Mobile Robotics and Olfaction Lab at AASS, ÷rebro University, Sweden. His main research interests are mobile robot olfaction, rich 3D perception, robot vision, and safe navigation for autonomous transport robots. Achim Lilienthal obtained his Ph.D. in computer science fromT¸bingen University, Germany and his M.Sc. and B.Sc. in Physics from the University of Konstanz, Germany. The Ph.D. thesis addresses gas distribution mapping and gas source localisation with a mobile robot. The M.Sc. thesis is concerned with an investigation of the structure of charged C60 clusters using gas phase ion chromatography.
Oct 10, 2:30 PM, Queen’s Goodwin 221B
Dr. Marcello Cirillo
A Lattice-based Approach to Multi-Vehicle Motion Planning
Abstract: Coordinating multiple autonomous non-holonomic vehicles is paramount to many industrial applications. While there exist solutions to efficiently calculate trajectories for individual vehicles, an effective methodology to coordinate their motions and to avoid deadlocks is still missing. Decoupled approaches, in which motions are calculated independently for each vehicle and then centrally scheduled for execution, have the means to identify deadlocks, but not to solve them. In this talk, I will present a novel approach that overcomes this limitation.
Biography: Dr. Marcello Cirillo is a postdoctoral researcher at the Center for Applied Sensor Systems (AASS) at Örebro University, Sweden. He focuses in the application of AI techniques to mobile robots. His research interests include automated planning, search algorithms, motion planning and the combination of task and motion planning for autonomous robots.
For more information about these talks, contact Joshua Marshall.