Model behaviour of agents in a warehouse setting
|Title||Model behaviour of agents in a warehouse setting|
|Summary||Model behaviour of agents in a warehouse setting|
|Keywords||Machine learning, simulation|
|TimeFrame||January 2017 until June 2017, with possible extension until September 2017|
|References|| SAS2-project, http://islab.hh.se/mediawiki/SAS2
Lidström, Kristoffer, Situation-Aware vehicles – supporting the next generation of cooperative traffic system, PhD thesis, Örebro university, 2012.
Lundström, Jens, Järpe, Eric & Verikas, Antanas, Detecting and exploring deviating behaviour of smart home residents, Expert systems with applications., 55, s. 429-440, 2016
|Prerequisites||Programming skills (preferably C++ or Python)|
A central issue for robots and automated guided vehicles (AGVs) is safety; the robot or AGV must not harm humans or damage objects in the environment. Safety concerns have become more and more important as the use of AGVs has spread and advances in sensor technology, sensor integration, and object detection and avoidance have been more widely adapted. Today’s safety systems don’t consider the behaviour or the identity of different agents in close proximity to the robot and AGV.
The goal with this project [as a subset of SAS2 project] is to develop a method for model behaviour of different agents in a warehouse setting and thus use that for predict behaviour in different scenarios. The idea is to investigate if different agents can automatically divided into categories depending on their behaviour and how that information can be used to foresee actions of different agents.
The study also includes construction of a simulator where the validity of the developed method for behaviour modelling, is evaluated. Real data can also be used to verify the system. Preferable the solutions are designed as ROS-packages (or, c++, python, matlab -code).
Resources: Facilities for data logging, cameras, depth sensor, data logging equipment, data set from warehouse and collaboration with industrial partners.
RQ: How to learn behaviour different categories of agents (e.g. manual driven trucks, humans, AGVs) especially if they they are only partially observed in time. How to represent behaviour of an agent?
WP1: Literature review and construction of a dataset. WP2: Develop methods for model behaviour of agents in a warehouse setting. WP3: Comparison study and development of improvements of the different systems. WP4: [bonus] conference publication (ETFA, ECMR, TAROS)
Deliverable: an implementation and demonstration of the developed system for model behaviour of agents using simulated data and data acquired in a real warehouse or mine.