SLAM SUMMER SCHOOL 2009

The 4th Summer School in Simultaneous Localisation and Mapping (SLAM) will be hosted by the Australian Centre for Field Robotics, University of Sydney on 20-23 January 2009.

For more than a decade the robotics community has focussed extensively on the concept of Simultaneous Localisation and Mapping (SLAM) and it has become one of the central themes in the implementation of many autonomous systems. SLAM is a set of algorithms, techniques, heuristics and paradigms which come together to solve a very difficult problem - “how can a mobile robot navigate in an a-priori unknown environment”.

There is a plethora of research activity in this area, most of which is focussed on indoor applications, with simple robots and simple sensors, operating in structured environments. Some of the techniques developed have worked their way into more complex mobile robot systems operating in outdoor, natural and semi-structured environments, however with limited success. Despite the widespread use of GPS in such environments it has its limitations and many systems require a localisation solution that can operate where GPS is denied, cannot be accessed or with limited availability. Classic examples include planetary exploration, underwater robotics, systems operating under extensive canopy or around tall buildings, where GPS has been intentionally jammed, and in disaster zones. Even when GPS is available, SLAM provides a means of incorporating redundancy in the navigation solution for the purposes of reliability.

SLAM has been a major challenge for the robotics community and with the increased interest in its implementation for outdoor systems has opened up a number of key questions:

• How can a mobile robot conduct SLAM efficiently in large scale environments?;
• What role does higher order perception have in the implementation of SLAM and in general autonomous situational awareness?; and
• How does perception and action come together to provide a mobile robot with improved knowledge of its surroundings for better maping, localisation and situational awareness?

These are some of the key ideas addressed in this workshop.

The goal of this summer school is to provide lectures and laboratory work on the basics as well as the state-of-the-art of SLAM, with a bent towards outdoor applications and perception in outdoor environments. A number of leading international researchers will be presenting their ideas and solutions to this difficult problem, focussing on ideas of machine learning for perception and situational awareness, large scale SLAM and Active-SLAM. The summer school will provide the opportunity for research students who are new to, or interested in, this exciting area to see what methods are being employed and what systems have been demonstrated, as well as to get hands on experience with some of the algorithmic methods. It will also provide the opportunity to interact with fellow researchers in this field with the aim of generating collaborative initiatives.

Applications are invited from research students to attend the Summer School.

It is expected that the Summer School will be oversubscribed. Priority will be given to students who can demonstrate the relevance and benefit of attending.

Applications should include:

• A statement outlining why attendance at the Summer School would be beneficial to your research (one page maximum, in pdf format);
• A letter of support from a referee (in pdf format);

Applications should be emailed to with a subject heading "SLAM Summer School 2009". Closing date for applications is Friday 7 November 2008, although we encourage and appreciate your early submission.

All successful applicants will be notified by email by Friday 14 November 2008 and requested to complete a registration form and return with payment.

Registration Fees

The registration fee for the Summer School is AUD975.

The registration fee covers 5 nights accommodation (19-24 January 2009), breakfast, morning and afternoon tea and lunch each day of the programme and a banquet dinner on one evening. (Dinner on all other nights will be at the participant's expense.)

There is also a subsidised fee of AUD585 offered to those students to which the committee feels it should apply. If you feel you have valid reasons please provide these in the body of your application email.

Payment may be sent in the form of:

• Cheque in AUD payable to ACFR, The University of Sydney
• Credit card (Visa, Mastercard, AMEX or Diners)

Cancellation Policy

Cancellations received on or before 14 December 2008: Refund of 50% of the registration fee

Cancellations received after 31 December 2008: No refund

Tuesday 20 January 2009

09:00-10:00 Probabilistic Formulation of SLAM - Tim Bailey
10:00-11:00 From Bayes' rule to the SLAM EKF - Jose Neira
11:00-11:15 Break
11:15-12:15 Advanced EKF SLAM: Building Large Maps - Juan Tardos
12:15-13:15 Metric or Topological SLAM? - Henrik Christensen
13:15-14:00 Lunch
14:00-17:00 Practical - EKF and Data Association - Jose Neira and Juan Tardos


Wednesday 21 January 2009

09:00-10:00 3D Outdoor SLAM Using Vision - Andrew Davison
10:00-11:00 3D Mapping - Wolfram Burgard
11:00-11:15 Break
11:15-12:15 Smoothing and Mapping with Large Scale SLAM - Frank Delleart
12:15-13:15 Action Based SLAM - Mitch Bryson
13:15-14:00 Lunch
14:00-17:00 Practical - Information SLAM and Control - Mitch Bryson and Frank Delleart


Thursday 22 January 2009

09:00-10:00 Multi-Sensor Data Association using CRF - Fabio Ramos
10:00-11:00 Multi-Sensor Mapping - Luke Fletcher
11:00-11:15 Break
11:15-12:15 Probabilistic Representations of Objects using NLDR - Fabio Ramos
12:15-13:15 Appearance-Based Methods for Loop Closing - Mark Cummins
13:15-14:00 Lunch
14:00-17:00 Practical - Learning Techniques/FabMap - Fabio Ramos/Mark Cummins


Friday 23 January 2009

09:00-10:00 Airborne SLAM and Mapping - Mitch Bryson
10:00-11:00 Air/Ground Mapping - Simon Lacroix
11:00-11:15 Break
11:15-12:15 3D Mapping Applications - Wolfram Burgard
12:15-13:15 Subsea SLAM - Stefan Williams
13:15-14:00 Lunch
14:00-15:00 Perception and SLAM in Natural Ground - Steve Scheding
15:00-16:00 Perception and Mapping - Urban Ground Vehicles Luke Fletcher
16:00-17:00 Close

Dr Tim Bailey
Dr Mitch Bryson
Prof Wolfram Burgard
Mark Cummins/Dr Paul Newman
Prof Henrik Christensen
Dr Andrew Davison
Assoc. Prof Frank Dellaert
Dr Luke Fletcher
Dr Simon Lacroix
Assoc. Prof Jose Neira
Dr Fabio Ramos
Prof Juan Tardos Solano
Dr Steve Scheding
Dr Stefan Williams

The SLAM Summer School will be held at the Peter Nichol Russell lecture theatre located at the Darlington Campus within the University of Sydney. See map for location details (ref P24).

Getting There

By train
Catch a train to Central station, which is close by, then take a bus from Railway Square at the station to the University - details below. Trains operate regularly from Sydney Airport direct to Central station, timetables can be found at City Rail

(Even though Redfern station is closer to the University than Central station, we strongly recommend not to use Redfern).

By bus
The closest bus stops to Darlington campus are on City Road. If travelling from the city catch routes 422, 423, 426, 428 from Castlereagh Street or Railway Square (outside Central Station). Timetables can be found at Sydney Buses.

Accommodation
Single rooms have been reserved for participants at Wesley College, which is on campus and very close to the conference venue. Five nights accommodation are included in the registration fee.

Wesley College can be found at location K11 on the following map.

Sydney is a vibrant, dynamic and accessible city with a rich blend of cultures. The City of Sydney website provides a wealth of information on the many tourist attractions and places to visit.

Climate in Sydney in January can be hot, humid and prone to showers with average temperatures of 19-26 degrees Celsius.

There are a number of suburbs surrounding the University that offer a wide range of restaurants, cafes and entertainment. These include Newtown, Glebe and Chinatown and further information can be found here.