DPAC - Dependable Platforms for Autonomous systems and Control

The DPAC profile establishes a leading research profile targeting dependable platforms for autonomous systems and control, hosted at Mälardalen University in the Embedded Systems (ES) research environment. This will be accomplished through close collaboration and interaction between ES research groups at MDH and the participating industrial companies. The profile will leverage our solid track record of close cooperation to conduct excellent research, knowledge transfer, and support commercialization with industrial partners. DPAC shall create synergy effects between the partners and a significant increase in coproduction is to be expected.

The ultimate goal of the DPAC profile is to establish a nationally leading and internationally renowned research centre that facilitate close cooperation between academia and industry to achieve a significant increase in research and available knowhow on advanced dependable platforms for embedded systems. Embedded computer systems are nowadays incorporated in many kinds of products including many mission critical applications such as trains, autonomous utility vehicles, aviation, smart grid power management etc. These systems offer advanced functionality and serve an important role for the competitiveness of companies and the future national and global infrastructure. The scientific and technical results of DPAC will support future innovation by providing dependable platforms that can be used to efficiently realize dependable, reliable and safe electronically controlled products.

Four established research groups from MDH will in addition to the staff from companies provide the core competence thrust within DPAC. The research will be organized around three main research areas:

• Predictability and dependability in parallel architectures
• Autonomous systems and control
• Design methodologies

These combined competences give DPAC a unique opportunity to address system-wide research challenges that span several traditional research areas and wide industrial applications as well as forming a robust basis for the research in DPAC.

DPAC brings a wide industrial participation ranging from small-medium enterprises to large multinational corporations. The initial industrial partners are; ABB CRC, ABB Control Technologies, Alten, Arcticus Systems, Bombardier Transportation, BAP, Enea, Ericsson, Hök Instruments, Saab, Volvo Construction Equipment, and Volvo Group Trucks Technology. These companies represent the core of this proposal’s research target and will bring their unique competence and relevant use-cases to facilitate and strengthen the research within DPAC.

DPAC allows a unique opportunity for ES to focus established researchers and new recruits towards the area of dependable systems and platforms. This area is identified as key-area for future growth in both education and research, and where industrial support is already large and anticipated to grow further during the coming decade.

[Show all publications]

3DLaneNAS: Neural Architecture Search for Accurate and Light-Weight 3D Lane Detection (Sep 2022)
Ali Zoljodi, Mohammad Loni, Sadegh Abadijou , Mina Alibeigi , Masoud Daneshtalab
ICANN2022: 31st International Conference on Artificial Neural Networks (ICANN2022)

A novel method for detecting UAVs using parallel neural networks with re-inference (Sep 2022)
Hubert Stepien , Martin Bilger , Håkan Forsberg, Billy Lindgren , Johan Hjorth
33rd Congress of the International Council of the Aeronautical Sciences (ICAS 2022)

FastStereoNet: A Fast Neural Architecture Search for Improving the Inference of Disparity Estimation on Resource-Limited Platforms (Jul 2022)
Mohammad Loni, Ali Zoljodi, Amin Majd , Byung Hoon Ahn , Masoud Daneshtalab, Mikael Sjödin, Hadi Esmaeilzadeh
IEEE Transactions on Systems, Man, and Cybernetics: Systems (SMCS)

AVB-aware Routing and Scheduling for Critical Traffic in Time-sensitive Networks with Preemption (Jun 2022)
Aldin Berisa, Luxi Zhao , Silviu Craciunas , Mohammad Ashjaei, Saad Mubeen, Masoud Daneshtalab, Mikael Sjödin
The 30th International Conference on Real-Time Networks and Systems (RTNS'22)

FaCT-LSTM: Fast and Compact Ternary Architecture for LSTM Recurrent Neural Networks (Jun 2022)
Najmeh Nazari , Seyed Ahmad Mirsalari , Sima Sinaei, Mostafa Salehi , Masoud Daneshtalab
IEEE Design and Test (IEEE D&T)

Formal Methods for Scalable Synthesis and Verification of Autonomous Systems (May 2022)
Rong Gu