{{ResearchProjInfo
|Title=AIMS
|ContactInformation=Björn Åstrand
|ShortDescription=Automatic Inventory and Mapping of Stock
|Description=The state of the art in autonomous robotics has advanced sufficiently that open implementations of many core technologies are now readily available. Consequently, there is growing research on the design and development of innovative solutions that leverage insights from several specialist domains. The AIMS project lies in this category. Its goal is to develop a system that seamlessly combines inventory management with autonomous forklift trucks in intelligent warehouses. Information compatible with human operators, management systems, as well as mobile robots is of particular importance here. A rich and ``life'' map combining metric and semantic information is a crucial ingredient for effective management of logistics and inventory, especially for autonomous fleets working in the same space as humans and human-operated devices.
|LogotypeFile=Procedure.png
|ProjectResponsible=Björn Åstrand
|ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf
|FundingMSEK=12
|ProjectStart=2012/01/01
|ProjectEnd=2016/01/01
|ApplicationArea=Intelligent Vehicles
|Lctitle=No
}}
{{AssignProjPartner
|projectpartner=KOLLMORGEN
}}
{{AssignProjPartner
|projectpartner=OPTRONIC
}}
{{AssignProjPartner
|projectpartner=Toyota Material Handling Europe
}}
__NOTOC__
{{ShowResearchProject}}

== Introduction ==
An important skill for future robots and automated guided vehicles (AGVs) is the ability to recognize and describe objects that the robot shall handle and the environment in which the robot operates. This is an important step towards making robots more intelligent (situation awareness). The ability to structure and sort information provided by sensors increases the system’s flexibility and ability to adapt to new settings (which in the end means lower costs). To do this with as few input parameters as possible is also a challenge. The goal with this project is to develop a system for automatic inventory and mapping of goods in a warehouse setting and associate these with articles in the warehouse management system. Objects are augmented into a semantic map and can be both goods and objects belonging to the warehouse infrastructure, e.g. pallet rack and pallets. The semantic map can be further expanded with objects belonging to the building (doors, columns, etc.) and mobile objects that appear in the path of the robot (pedestrians, forklift trucks, etc.). The project thus also includes building a concept map of the area of operation

This project is a collaboration between the CAISR, Kollmorgen, Optronic and Toyota Material Handling Europe.

[[File:AIMSoverall.png|thumb|caption|"Overall of the AIMS project"]]

== Motivations ==
An important skill for future robots and automated guided vehicles (AGV:s) is the ability to recognize and describe objects that the robot shall handle and the environment in which the robot operates. The ability to structure and sort information provided by sensors increases the system's flexibility and ability to adapt to new settings. The purpose of AIMS is to make autonomous systems and AGV:s operating in a warehouse setting more intelligent, by extending their functionality with a system for automatic inventory and mapping of goods. Achievement of this purpose requires:
* situation awareness: through different types of sensors, data fusion and employment of novel methods for interpretations of the information.
* maintaining practicability by means of flexibility and adaptability for handling variety of environments and sensor's data.

== Objectives ==
acquiring the skills of ''situation awareness'', ''flexibility'' and ''adaptability'', demands accomplishment in different disciplinary areas:
* ''Mapping and semantic annotation'', both as a foundation of the semantic map for addressing articles and trucks in the environment, and to provide an automatic surveying and layout design for initial installation.
[[File:AIMSSemiSuprvised|thumb|caption|"Semi-supervised semantic annotation"]]
* ''Inventory list maintenance''; a dynamic map maintenance approach in order to keep track of the inventory, linked with the warehouse management system.
[[File:Aims semantic.png|thumb|caption|"AIMS"]]
* ''3D Perception''; serving the objectives of obstacle avoidance and articles' quantity estimation for inventory list.

File:AIMSSemiSuprvised.png

2015-06-30T19:21:40Z

Saesha:

AIMS

2015-06-30T19:16:03Z

Saesha:

{{ResearchProjInfo
|Title=AIMS
|ContactInformation=Björn Åstrand
|ShortDescription=Automatic Inventory and Mapping of Stock
|Description=The state of the art in autonomous robotics has advanced sufficiently that open implementations of many core technologies are now readily available. Consequently, there is growing research on the design and development of innovative solutions that leverage insights from several specialist domains. The AIMS project lies in this category. Its goal is to develop a system that seamlessly combines inventory management with autonomous forklift trucks in intelligent warehouses. Information compatible with human operators, management systems, as well as mobile robots is of particular importance here. A rich and ``life'' map combining metric and semantic information is a crucial ingredient for effective management of logistics and inventory, especially for autonomous fleets working in the same space as humans and human-operated devices.
|LogotypeFile=Procedure.png
|ProjectResponsible=Björn Åstrand
|ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf
|FundingMSEK=12
|ProjectStart=2012/01/01
|ProjectEnd=2016/01/01
|ApplicationArea=Intelligent Vehicles
|Lctitle=No
}}
{{AssignProjPartner
|projectpartner=KOLLMORGEN
}}
{{AssignProjPartner
|projectpartner=OPTRONIC
}}
{{AssignProjPartner
|projectpartner=Toyota Material Handling Europe
}}
[[File:Aims semantic.png|thumb|caption|"AIMS"]]
__NOTOC__
{{ShowResearchProject}}

== Introduction ==
An important skill for future robots and automated guided vehicles (AGVs) is the ability to recognize and describe objects that the robot shall handle and the environment in which the robot operates. This is an important step towards making robots more intelligent (situation awareness). The ability to structure and sort information provided by sensors increases the system’s flexibility and ability to adapt to new settings (which in the end means lower costs). To do this with as few input parameters as possible is also a challenge. The goal with this project is to develop a system for automatic inventory and mapping of goods in a warehouse setting and associate these with articles in the warehouse management system. Objects are augmented into a semantic map and can be both goods and objects belonging to the warehouse infrastructure, e.g. pallet rack and pallets. The semantic map can be further expanded with objects belonging to the building (doors, columns, etc.) and mobile objects that appear in the path of the robot (pedestrians, forklift trucks, etc.). The project thus also includes building a concept map of the area of operation

This project is a collaboration between the CAISR, Kollmorgen, Optronic and Toyota Material Handling Europe.

[[File:AIMSoverall.png|thumb|caption|"Overall of the AIMS project"]]

== Motivations ==
An important skill for future robots and automated guided vehicles (AGV:s) is the ability to recognize and describe objects that the robot shall handle and the environment in which the robot operates. The ability to structure and sort information provided by sensors increases the system's flexibility and ability to adapt to new settings. The purpose of AIMS is to make autonomous systems and AGV:s operating in a warehouse setting more intelligent, by extending their functionality with a system for automatic inventory and mapping of goods. Achievement of this purpose requires:
* situation awareness: through different types of sensors, data fusion and employment of novel methods for interpretations of the information.
* maintaining practicability by means of flexibility and adaptability for handling variety of environments and sensor's data.

== Objectives ==
acquiring the skills of ''situation awareness'', ''flexibility'' and ''adaptability'', demands accomplishment in different disciplinary areas:
* ''Mapping and semantic annotation'', both as a foundation of the semantic map for addressing articles and trucks in the environment, and to provide an automatic surveying and layout design for initial installation.
* ''Inventory list maintenance''; a dynamic map maintenance approach in order to keep track of the inventory, linked with the warehouse management system.
* ''3D Perception''; serving the objectives of obstacle avoidance and articles' quantity estimation for inventory list.

2015-06-30T15:55:51Z

Saesha:

AIMS

2015-06-30T15:52:38Z

Saesha:

{{ResearchProjInfo
|Title=AIMS
|ContactInformation=Björn Åstrand
|ShortDescription=Automatic Inventory and Mapping of Stock
|Description=An important skill for future robots and automated guided vehicles (AGVs) is the ability to recognize and describe objects that the robot shall handle and the environment in which the robot operates. This is an important step towards making robots more intelligent (situation awareness). The ability to structure and sort information provided by sensors increases the system’s flexibility and ability to adapt to new settings (which in the end means lower costs). To do this with as few input parameters as possible is also a challenge. The goal with this project is to develop a system for automatic inventory and mapping of goods in a warehouse setting and associate these with articles in the warehouse management system. Objects are augmented into a semantic map and can be both goods and objects belonging to the warehouse infrastructure, e.g. pallet rack and pallets. The semantic map can be further expanded with objects belonging to the building (doors, columns, etc.) and mobile objects that appear in the path of the robot (pedestrians, forklift trucks, etc.). The project thus also includes building a concept map of the area of operation

The project is a collaboration between the CAISR, Kollmorgen, Optronic, Toyota Material Handling Europe.
|LogotypeFile=Procedure.png
|ProjectResponsible=Björn Åstrand
|ProjectDetailsPDF=CAISR Poster 2013 AIMS.pdf
|FundingMSEK=12
|ProjectStart=2012/01/01
|ProjectEnd=2016/01/01
|ApplicationArea=Intelligent Vehicles
|Lctitle=No
}}
{{AssignProjPartner
|projectpartner=KOLLMORGEN
}}
{{AssignProjPartner
|projectpartner=OPTRONIC
}}
{{AssignProjPartner
|projectpartner=Toyota Material Handling Europe
}}
[[File:Aims semantic.png|thumb|caption|"AIMS"]]

__NOTOC__
{{ShowResearchProject}}
{{ShowProjectPublications}}

Pallet Detection and Mapping

2014-11-21T17:08:45Z

Saesha:

{{StudentProjectTemplate
|Summary=Pallet Detection and Mapping in a Warehouse Environment
|Programme=Mobile and Autonomous Systems
|Keywords=Object Recognition, Classification, Mapping, Scene Understanding
|TimeFrame=January 2015 until June 2015, with possible extension until September 2015.
|References=Belongie, Serge, Jitendra Malik, and Jan Puzicha. "Shape matching and object recognition using shape contexts." Pattern Analysis and Machine Intelligence, IEEE Transactions on 24.4 (2002): 509-522.

Viola, Paul, and Michael Jones. "Rapid object detection using a boosted cascade of simple features." Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on. Vol. 1. IEEE, 2001.

Lowe, David G. "Local feature view clustering for 3D object recognition." Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on. Vol. 1. IEEE, 2001.

Lowe, David G. "Distinctive image features from scale-invariant keypoints." International journal of computer vision 60.2 (2004): 91-110.

Bay, Herbert, et al. ”Speeded-up robust features (SURF).” Computer vision and image understanding 110.3 (2008): 346-359.

Pinto, Nicolas, David D. Cox, and James J. DiCarlo. "Why is real-world visual object recognition hard?." PLoS computational biology 4.1 (2008): e27.
|Prerequisites=Image analysis, programming skills (preferably C++ or Python), familiarity with pattern recognition, Familiarity with filtering techniques (eg. EKF) for mobile robots mapping.
|Supervisor=Björn Åstrand, Saeed Gholami Shahbandi,
|Level=Master
|Status=Open
}}
concise description:
This project [as a subset of AIMS project], targets the automation of the logistic management system of a warehouse, by the means of automatic guided vehicles (AGVs, eg. lift trucks). Achieving this objective is feasible if the operating robots (AGVs) understand their surrounding through a high level model of the world. An essential element of this model is the inventory list. Locating stored articles and modulating the inventory list with respect to human’s expectation delivers a more effective system. A common element of the storage in warehouses is the pallet. By detecting and mapping the pallets in a warehouse, the problem of constructing the inventory list will be simplified to the problem of identification of those objects stored over each pallet.

RQ: Detection of pallets falls into the category of object recognition. Although the pallet’s pattern is relatively simple and unique, yet the recognition process will be challenging. To reach a reliable result, one should deal with problems such as segmenting stacked pallets, cluttered environment, bad illumination and different view points.

WP1: startup: literature review and data acquisition
WP2: pallet detection
WP3: pallet mapping 2D, [3D: bonus]

Deliverable: an implementation and demonstration of the developed method for detection and mapping pallets, based on a dataset acquired in a real world warehouse.
[bonus] conference publication (ETFA, ECMR, TAROS).

Pallet Detection and Mapping

2014-11-21T17:06:57Z

Saesha:

2014-08-29T07:12:53Z

Saesha:

{{Person
|Family Name=Gholami Shahbandi
|Given Name=Saeed
|Title=M.Sc
|Phone=+46-35-16-7537
|Position=PhD Candidate
|Email=saesha@hh.se
|Image=Saaed_small.jpg‎
|Office=E522
|url=http://se.linkedin.com/pub/saeed-gholami-shahbandi/41/365/4b0/
|Subject=Robotics
}}
{{AssignProjects
|project=AIMS
}}
{{AssignSubjectAreas
|SubjectArea=Robotics
}}
{{AssignSubjectAreas
|SubjectArea=Computer Vision
}}
{{AssignSubjectAreas
|SubjectArea=Machine Learning
}}
{{AssignApplicationAreas
|ApplicationArea=Intelligent Vehicles
}}

{{ShowPerson}}
{{InsertSubjAreas}}
{{InsertProjects}}
{{PublicationsList}}

[[Category:Staff]]

Saeed Gholami Shahbandi

2014-08-29T07:10:09Z

Saesha:

{{Person
|Family Name=Gholami Shahbandi
|Given Name=Saeed
|Title=M.Sc
|Phone=+46-35-16-7537
|Position=PhD Candidate
|Email=saesha@hh.se
|Image=Saaed_small.jpg‎
|Office=E522
|Subject=Robotics
}}
{{AssignProjects
|project=AIMS
}}
{{AssignSubjectAreas
|SubjectArea=Robotics
}}
{{AssignSubjectAreas
|SubjectArea=Computer Vision
}}
{{AssignSubjectAreas
|SubjectArea=Machine Learning
}}
{{AssignApplicationAreas
|ApplicationArea=Intelligent Vehicles
}}


{{ShowPerson}}
{{InsertSubjAreas}}
{{InsertProjects}}
{{PublicationsList}}

[[Category:Staff]]