Research Internship / Master’s Thesis (Deep Learning)
10 January 2019
Open until filled
Technical university of Munich - Campus for Research Excellence and Technological Enterprise (TUMCREATE) is a research platform for the improvement of Singapore's public transportation, including the deployment of electric and autonomous mobility. Researchers from Technical University Munich and Nanyang Technological University join forces and are funded by Singapore’s National Research Foundation as part of the Campus for Research Excellence And Technological Enterprise (CREATE).
At TUMCREATE, over 100 scientists, researchers and engineers work together, led by Professors from the Technical University of Munich and Nanyang Technological University. The Mission of TUMCREATE is to seek the ultimate public transport system for the people of Singapore. Our innovative road transport solutions will provide high comfort and a positive travel experience, best protection of the environment and maximum benefit to the society and the economy.
More Information about TUMCREATE can be found by viewing our web pages at http://www.tum-create.edu.sg/
Deep learning applied to Real World Robotic System
TUMCREATE is a leading Research Institute set up by the Technical University of Munich, Germany in col-laboration with the Singapore Government. TUMCREATE has received funding and support for the SPEED-CARGO project from the Civil Aviation Authority of Singapore (CAAS) & the national Research Foundation (NRF) to develop automation solutions that will transform the Air Freight Logistics sector. The SPEEDCARGO solution will be the world's first AI-powered robotic solution for automatic build-up and break down of aviation cargo pallets and will help Singapore lead the transformation of the Logistics industry globally.
The project is seeking technical experts with a passion for creating world class products, and a willingness to work in a fast paced, quality obsessed, multi-cultural global environment. On successful completion, the project will be spun off as a start-up with members of the project team having the option to join the start-up with benefits that in-clude attractive ESOPs. Apply now if you are interested in working on cutting edge technologies, changing the world with your work and joining a dynamic start-up team.
More details on the project: https://www.speedcargo.sg/
The design of real-world robotic systems is a multi-disciplinary effort. It involves the development of advanced perception systems, artificial intelligence-based decision making, mechanical elements like sensors and actu-ators, electronic components for connecting and controlling the mechanical elements and software for higher-level planning and process control.
This work will focus on development of specific computer vision modules for the perception system within SPEEDCARGO. It will involve the following specific task which the successful candidate will have to execute towards a real-world working application.
Photo realistic texture generation and mapping for synthesizing geometry and appearance of airfreight shipments. This data will be used for training a deep neural network
Implementing a C++ pipeline for a deep edge neural network trained on the data set specific in point 1
Integrating, testing a deploying the module within CargoEye
Algorithm for generating synthetic data of closely packed boxes on an airfreight ULD pallet adhering to airline regulations. Using this dataset to do deep edge learning using the framework specified in point 2
Design, modelling and implementation of a 3D calibration framework for 3D camera sets using a non-planer and precision engineered cubic pattern
Objective & Tasks
Successful candidate will be working in a team to primarily integrate software components of a large robotic system that includes an industrial robot, actuating end effectors, vision sensors, high level robot control and intelligent systems. There will be potential to do development in a wide range of these areas. The primary responsibility of the candidate will be development, testing and deployment of tasks specified above.
Since the project will focus on real world deployment of industrial robotics system, we require the candidate to have hands on experience working on computer vision for real world systems (preferable in Industry).
Master/Bachelor Degree from a reputed university
Strong fundamentals in computer science and mathematics related to Computer Vision.
Past internships/working experience in reputed universities and robotics research labs is essential
What we expect from you
Relevant experience in deep learning frameworks (tensor flow and cafe) and applied to practical and real world system
Statistical analysis, State Estimation (Kalman Filters, Particle Filters) and Machine Learning (SVM, Deci-sion Trees, Neural Networks).
Experience with parallel computing like CUDA etc.
Experience working in a software development team with best practice methods implemented